# agentic

Published articles for agentic.

This is one page of public article previews, not the complete archive. Follow Next page to continue. Summaries are not the original full articles.

## "We are not querying like humans anymore": OpenSearch's Bianca Lewis on why AI agent mistakes look like successes

DevFeed: ["We are not querying like humans anymore": OpenSearch's Bianca Lewis on why AI agent mistakes look like successes](<https://devfeed.tech/articles/we-are-not-querying-like-humans-anymore-opensearch-s-bianca-lewis-on-why-ai-agent-mistakes-look-like-successes-146621.md>)

Original publisher: [Read original article](<https://thenewstack.io/opensearch-ai-agent-observability/>)

Author: Chris J. Preimesberger

Published: 2026-11-20T19:37:08Z

Content type: news

Language: en

Sources: [The New Stack](<https://devfeed.tech/sources/the-new-stack.md>)

Topics: [opensearch](<https://devfeed.tech/topics/opensearch.md>), [AI Agent](<https://devfeed.tech/topics/ai-agent.md>)

Tags: [agent](<https://devfeed.tech/tags/agent.md>), [agentic](<https://devfeed.tech/tags/agentic.md>), [agentic-ai](<https://devfeed.tech/tags/agentic-ai.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-agent](<https://devfeed.tech/tags/ai-agent.md>), [ai-agents](<https://devfeed.tech/tags/ai-agents.md>), [ai-models](<https://devfeed.tech/tags/ai-models.md>), [ai-strategy](<https://devfeed.tech/tags/ai-strategy.md>), [analytics](<https://devfeed.tech/tags/analytics.md>), [api](<https://devfeed.tech/tags/api.md>), [apis](<https://devfeed.tech/tags/apis.md>), [applications](<https://devfeed.tech/tags/applications.md>), [cncf](<https://devfeed.tech/tags/cncf.md>), [community](<https://devfeed.tech/tags/community.md>), [context](<https://devfeed.tech/tags/context.md>), [control](<https://devfeed.tech/tags/control.md>), [cost](<https://devfeed.tech/tags/cost.md>), [dashboard](<https://devfeed.tech/tags/dashboard.md>), [data-gravity](<https://devfeed.tech/tags/data-gravity.md>), [error](<https://devfeed.tech/tags/error.md>), [hosting](<https://devfeed.tech/tags/hosting.md>), [mistakes](<https://devfeed.tech/tags/mistakes.md>), [opensearch](<https://devfeed.tech/tags/opensearch.md>), [podcast](<https://devfeed.tech/tags/podcast.md>), [sponsor-cncf](<https://devfeed.tech/tags/sponsor-cncf.md>), [sponsored](<https://devfeed.tech/tags/sponsored.md>), [sponsored-podcast](<https://devfeed.tech/tags/sponsored-podcast.md>), [video](<https://devfeed.tech/tags/video.md>)

### AI overview

AI agents can make the wrong API calls yet receive successful responses, leaving ordinary error logs and green dashboards unable to reveal that a run went off course. OpenSearch Software Foundation executive director Bianca Lewis describes using OpenSearch with OpenTelemetry to trace the services and APIs an agent called, and adding cost data to spot expensive steps. Those traces help developers investigate plausible but incorrect results and reconsider the context made available to the agent. Lewis also says teams may use OpenSearch for both observability and search, drawing on existing skills and reviewing duplicated data, while weighing platform-change costs against operating costs. Moving platforms takes time because production systems, contracts and team skills persist. The excerpt also points to community contributions through pull requests, Slack discussions and user groups.

### Source excerpt

This situation is more common than one might think: An AI agent calls the wrong API, gets a perfectly good The post "We are not querying like humans anymore": OpenSearch's Bianca Lewis on why AI agent mistakes look like successes appeared first on The New Stack.

## Bell Canada says 'agentic' hacker stole enterprise customer data

DevFeed: [Bell Canada says 'agentic' hacker stole enterprise customer data](<https://devfeed.tech/articles/bell-canada-says-agentic-hacker-stole-enterprise-customer-data-146589.md>)

Original publisher: [Read original article](<https://www.bleepingcomputer.com/news/security/bell-canada-says-agentic-hacker-stole-enterprise-customer-data/>)

Author: Lawrence Abrams

Published: 2026-11-20T18:51:43Z

Content type: news

Language: en

Sources: [BleepingComputer](<https://devfeed.tech/sources/bleepingcomputer.md>)

Topics: [enterprise data protection](<https://devfeed.tech/topics/enterprise-data-protection.md>), [Agentic AI](<https://devfeed.tech/topics/what-is-agentic-ai.md>), [Threat monitoring](<https://devfeed.tech/topics/threat-monitoring.md>)

Tags: [17](<https://devfeed.tech/tags/17.md>), [2026](<https://devfeed.tech/tags/2026.md>), [agentic](<https://devfeed.tech/tags/agentic.md>), [agentic-ai](<https://devfeed.tech/tags/agentic-ai.md>), [agentic-threat-actor](<https://devfeed.tech/tags/agentic-threat-actor.md>), [bell-canada](<https://devfeed.tech/tags/bell-canada.md>), [canada](<https://devfeed.tech/tags/canada.md>), [circuits](<https://devfeed.tech/tags/circuits.md>), [computer-help](<https://devfeed.tech/tags/computer-help.md>), [computer-security](<https://devfeed.tech/tags/computer-security.md>), [computers](<https://devfeed.tech/tags/computers.md>), [customer-data](<https://devfeed.tech/tags/customer-data.md>), [cybersecurity](<https://devfeed.tech/tags/cybersecurity.md>), [data](<https://devfeed.tech/tags/data.md>), [data-breach](<https://devfeed.tech/tags/data-breach.md>), [enterprise](<https://devfeed.tech/tags/enterprise.md>), [infosec](<https://devfeed.tech/tags/infosec.md>), [infosec-computer-security](<https://devfeed.tech/tags/infosec-computer-security.md>), [linux](<https://devfeed.tech/tags/linux.md>), [mac](<https://devfeed.tech/tags/mac.md>), [malware](<https://devfeed.tech/tags/malware.md>), [malware-removal](<https://devfeed.tech/tags/malware-removal.md>), [november-17](<https://devfeed.tech/tags/november-17.md>), [security](<https://devfeed.tech/tags/security.md>), [spyware](<https://devfeed.tech/tags/spyware.md>), [support](<https://devfeed.tech/tags/support.md>), [systems](<https://devfeed.tech/tags/systems.md>), [tech-support](<https://devfeed.tech/tags/tech-support.md>), [technical-support](<https://devfeed.tech/tags/technical-support.md>), [virus](<https://devfeed.tech/tags/virus.md>), [virus-removal](<https://devfeed.tech/tags/virus-removal.md>), [windows](<https://devfeed.tech/tags/windows.md>)

### AI overview

Bell Canada says an "agentic threat actor" breached systems on November 17, 2026, and exfiltrated enterprise customer data, including records from a pre-production Maximo system used to order and provision network connections. Potentially exposed information includes business contacts, ticket titles, some IP addresses tied to network elements or systems, and limited context. Bell said the dataset did not include credentials, highly sensitive personal information, PDFs, attachments, or other supplementary Maximo information. It contained the incident and secured systems, reporting no customer service impact. Bell is sharing indicators of compromise and threat-hunting information with enterprise customers and Canada's Centre for Cyber Security, but has not publicly released the indicators. Attribution, the number of affected customers, and the amount of data taken remain undisclosed. Bell advised customers to watch for unsolicited requests and impersonation attempts.

### Source excerpt

Bell Canada has confirmed that an "agentic" threat actor breached its systems on November 17, 2026, and stole enterprise customer data, including information from a system used to order and provision telecommunications circuits. [...]

## Forrester Recognizes Checkmarx in The Forrester Wave™: Agentic Development Security Tools, Q4 2026

DevFeed: [Forrester Recognizes Checkmarx in The Forrester Wave™: Agentic Development Security Tools, Q4 2026](<https://devfeed.tech/articles/forrester-recognizes-checkmarx-in-the-forrester-wavetm-agentic-development-security-tools-q4-2026-146870.md>)

Original publisher: [Read original article](<https://checkmarx.com/blog/checkmarx-forrester-wave-agentic-development-security-tools-q4-2026/>)

Author: Checkmarx Team

Published: 2026-11-20T17:03:20Z

Content type: article

Language: en

Sources: [Checkmarx](<https://devfeed.tech/sources/checkmarx.md>)

Topics: [code security](<https://devfeed.tech/topics/code-security.md>), [AI software supply chain security](<https://devfeed.tech/topics/ai-software-supply-chain-security.md>), [Static code analysis](<https://devfeed.tech/topics/static-code-analysis.md>), [AI-assisted coding](<https://devfeed.tech/topics/ai-assisted-coding.md>), [LLM security](<https://devfeed.tech/topics/llm-security.md>), [DevSecOps](<https://devfeed.tech/topics/devsecops.md>)

Tags: [2026](<https://devfeed.tech/tags/2026.md>), [agent](<https://devfeed.tech/tags/agent.md>), [agentic](<https://devfeed.tech/tags/agentic.md>), [agentic-development](<https://devfeed.tech/tags/agentic-development.md>), [agentic-development-lifecycle](<https://devfeed.tech/tags/agentic-development-lifecycle.md>), [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-application](<https://devfeed.tech/tags/ai-application.md>), [ai-llm-tools-in-application-security](<https://devfeed.tech/tags/ai-llm-tools-in-application-security.md>), [analyst-reports](<https://devfeed.tech/tags/analyst-reports.md>), [application](<https://devfeed.tech/tags/application.md>), [aspm](<https://devfeed.tech/tags/aspm.md>), [autonomous](<https://devfeed.tech/tags/autonomous.md>), [blog](<https://devfeed.tech/tags/blog.md>), [checkmarx](<https://devfeed.tech/tags/checkmarx.md>), [code](<https://devfeed.tech/tags/code.md>), [development](<https://devfeed.tech/tags/development.md>), [forrester](<https://devfeed.tech/tags/forrester.md>), [forrester-wave](<https://devfeed.tech/tags/forrester-wave.md>), [q4](<https://devfeed.tech/tags/q4.md>), [remediation](<https://devfeed.tech/tags/remediation.md>), [security](<https://devfeed.tech/tags/security.md>), [security-tools](<https://devfeed.tech/tags/security-tools.md>), [tools](<https://devfeed.tech/tags/tools.md>)

### AI overview

Checkmarx says Forrester's Q4 2026 Agentic Development Security Tools evaluation gave it the highest possible scores for AI application flaws, autonomous proprietary code remediation, and ASPM for AI. The article frames agentic development security as a response to coding agents that generate code, choose dependencies, invoke tools, and execute tasks at machine speed. Checkmarx describes a three-part approach: combine rules-based and AI analysis, then consolidate findings and flag false positives; prevent issues through Developer Assist and prioritize existing findings by reachability, exploitability, business context, and compensating controls for guided-to-autonomous fixes; and correlate risk, assign owners, enforce policy gates, and deterministically govern models, MCP servers, and agents. It also says malicious and hallucinated packages are blocked in real time against a database of more than 550,000 known malicious packages. These are Checkmarx's descriptions of its capabilities; the text notes that Forrester does not endorse vendors or advise selection based on ratings.

### Source excerpt

Checkmarx received the highest score possible in the criteria of AI application flaws, autonomous proprietary code remediation, and ASPM for AI.

## Microsoft named a Leader in the 2026 Gartner® Magic Quadrant™ for SIEM

DevFeed: [Microsoft named a Leader in the 2026 Gartner® Magic Quadrant™ for SIEM](<https://devfeed.tech/articles/microsoft-named-a-leader-in-the-2026-gartner-magic-quadranttm-for-siem-146679.md>)

Original publisher: [Read original article](<https://www.microsoft.com/en-us/security/blog/2026/11/20/microsoft-named-a-leader-in-the-2026-gartner-magic-quadrant-for-siem/>)

Author: Rob Lefferts

Published: 2026-11-20T17:00:00Z

Content type: article

Language: en

Sources: [Microsoft Security](<https://devfeed.tech/sources/microsoft-security-blog.md>)

Topics: [Security Information and Event Management (SIEM)](<https://devfeed.tech/topics/siem-security.md>), [alert triage](<https://devfeed.tech/topics/alert-triage.md>), [Threat monitoring](<https://devfeed.tech/topics/threat-monitoring.md>)

Tags: [2026](<https://devfeed.tech/tags/2026.md>), [agentic](<https://devfeed.tech/tags/agentic.md>), [agentic-soc](<https://devfeed.tech/tags/agentic-soc.md>), [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [alert-triage](<https://devfeed.tech/tags/alert-triage.md>), [analytics](<https://devfeed.tech/tags/analytics.md>), [attack-disruption](<https://devfeed.tech/tags/attack-disruption.md>), [automation](<https://devfeed.tech/tags/automation.md>), [blog](<https://devfeed.tech/tags/blog.md>), [business-email-compromise](<https://devfeed.tech/tags/business-email-compromise.md>), [cloud](<https://devfeed.tech/tags/cloud.md>), [gartner](<https://devfeed.tech/tags/gartner.md>), [gartner-magic-quadrant](<https://devfeed.tech/tags/gartner-magic-quadrant.md>), [gartner-magic-quadranttm](<https://devfeed.tech/tags/gartner-magic-quadranttm.md>), [leader](<https://devfeed.tech/tags/leader.md>), [microsoft](<https://devfeed.tech/tags/microsoft.md>), [security](<https://devfeed.tech/tags/security.md>), [security-blog](<https://devfeed.tech/tags/security-blog.md>), [security-information-and-event-management](<https://devfeed.tech/tags/security-information-and-event-management.md>), [siem](<https://devfeed.tech/tags/siem.md>)

### AI overview

Microsoft says it was named a Leader in the 2026 Gartner Magic Quadrant for SIEM. Its post describes Microsoft Sentinel as a cloud-native SIEM with more than 500 Microsoft and third-party connectors, built-in detections, threat hunting and response capabilities, and a data lake for historical and real-time security data. Microsoft also describes the Integrated Security Operations Center (ISOC) in Defender, introduced September 23, 2026, as combining Sentinel SIEM with XDR, threat intelligence, posture management, and response. The post says Defender can correlate signals and automatically contain compromised users and devices in high-confidence attacks, reporting an average ransomware disruption time of 30 seconds across customers. It presents AI agents as supporting tasks such as threat hunting, triage, and investigations, with people providing judgment and accountability. These recognition and performance statements are Microsoft's claims in the supplied text.

### Source excerpt

We're honored that Microsoft has once again been recognized as a Leader in the 2026 Gartner® Magic Quadrant™ for Security Information and Event Management (SIEM). The post Microsoft named a Leader in the 2026 Gartner® Magic Quadrant™ for SIEM appeared first on Microsoft Security Blog.

## What's next for Azure networking?

DevFeed: [What's next for Azure networking?](<https://devfeed.tech/articles/what-s-next-for-azure-networking-146430.md>)

Original publisher: [Read original article](<https://www.networkworld.com/article/4251523/whats-next-for-azure-networking.html>)

Author: Sean Michael Kerner

Published: 2026-11-20T16:48:53Z

Content type: news

Language: en

Sources: [Network World](<https://devfeed.tech/sources/network-world.md>)

Topics: [AI Networking](<https://devfeed.tech/topics/ai-networking.md>), [Cloud Networking](<https://devfeed.tech/topics/cloud-networking.md>), [Azure Kubernetes Service](<https://devfeed.tech/topics/azure-kubernetes-service.md>), [Azure](<https://devfeed.tech/topics/azure.md>)

Tags: [agent](<https://devfeed.tech/tags/agent.md>), [agentic](<https://devfeed.tech/tags/agentic.md>), [agentic-ai](<https://devfeed.tech/tags/agentic-ai.md>), [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-agents](<https://devfeed.tech/tags/ai-agents.md>), [ai-workloads](<https://devfeed.tech/tags/ai-workloads.md>), [aks](<https://devfeed.tech/tags/aks.md>), [amazon-web-services-aws](<https://devfeed.tech/tags/amazon-web-services-aws.md>), [apis](<https://devfeed.tech/tags/apis.md>), [at-t](<https://devfeed.tech/tags/at-t.md>), [azure](<https://devfeed.tech/tags/azure.md>), [cloud](<https://devfeed.tech/tags/cloud.md>), [cloud-computing](<https://devfeed.tech/tags/cloud-computing.md>), [cloud-computing-networking](<https://devfeed.tech/tags/cloud-computing-networking.md>), [connectivity](<https://devfeed.tech/tags/connectivity.md>), [data-center](<https://devfeed.tech/tags/data-center.md>), [data-centers](<https://devfeed.tech/tags/data-centers.md>), [edition-us](<https://devfeed.tech/tags/edition-us.md>), [enterprises](<https://devfeed.tech/tags/enterprises.md>), [exploit](<https://devfeed.tech/tags/exploit.md>), [fabric](<https://devfeed.tech/tags/fabric.md>), [language-en](<https://devfeed.tech/tags/language-en.md>), [networking](<https://devfeed.tech/tags/networking.md>), [storytype-news](<https://devfeed.tech/tags/storytype-news.md>)

### AI overview

AI workloads increase east-west traffic and shift demand across locations, so Microsoft is flattening its data center fabric, extending connectivity, and adding network controls. Its two-tier fabric cuts a five-hop path to three and is reported to be over 20% more power efficient; hollow core fiber is said to reduce latency by about one-third. For customers, Azure Multicloud Interconnect provisions cloud cross-connects through APIs (AWS generally available; GCP and Lumen offerings in preview, AT&T coming soon). AKS Fleet Manager peers clusters with failover and shared policy, while Route Server route maps filter, summarize, and influence routes. Agent Grid applies identity-based controls without changing agent code; Azure Firewall Premium's AI add-on uses two inline small language models to detect malware and exploit requests. Adaptive Virtual Patching applies mitigations until patches arrive. The excerpt also describes Microsoft's use of over 100 network agents, which handled more than 30,000 cases and reduced backlog by about three quarters over the past year.

### Source excerpt

AI workloads change how traffic moves inside a data center. GPUs exchange data with other GPUs, servers, and storage, which shifts traffic from north-south to east-west. AI agents add another layer. They span compute, GPUs, the network, and data centers, and demand can move from one place to another overnight. At its Ignite conference this week, Microsoft detailed Azure networking updates for this shift, including new services for enterprises as well as how Microsoft itself is using agentic AI for networking. (It also previewed Windows Server 2028, its largest platform update since Windows Server 2025.) Networking-related announcements made at Ignite include: Azure Multicloud Interconnect: Provisions cross-connects between Azure and other clouds through APIs. Amazon Web Services (AWS) is generally available. Google Cloud Platform (GCP) is in preview, as is Azure Last Mile Interconnect with Lumen. AT&T is coming soon. Cross-cluster networking for Azure Kubernetes Service (AKS): Peers clusters through Azure Kubernetes Fleet Manager with failover and one network policy. Azure Route Server route maps: Filter and summarize routes and apply autonomous system (AS) path prepending. Agent Grid: Enforces identity-based microsegmentation, isolation, and traffic policies for AI agents on the network. Azure Firewall AI add-on: Runs two inline small language models on Azure Firewall Premium to detect malware and exploit requests. Azure Adaptive Virtual Patching: Maps published vulnerabilities to workloads on virtual machines and applies inline mitigations until the actual patch arrives. Microsoft points to the shifts in traffic, location, and security that AI creates. "So, with all of these shifts, the network is no longer about connectivity. It is really becoming the intelligent control for the agentic world," said Igor Sakhnov, corporate vice president and general manager of Azure Networking, in a session at Microsoft Ignite. Azure flattens its fabric and adds hollow core fiber

## Google Donates Agent Substrate and gVisor to the CNCF to Secure AI Agents at Scale

DevFeed: [Google Donates Agent Substrate and gVisor to the CNCF to Secure AI Agents at Scale](<https://devfeed.tech/articles/google-donates-agent-substrate-and-gvisor-to-the-cncf-to-secure-ai-agents-at-scale-146237.md>)

Original publisher: [Read original article](<https://www.infoq.com/news/2026/11/google-substrate-gvisor-cncf/>)

Author: Craig Risi

Published: 2026-11-20T12:00:00Z

Content type: news

Language: en

Sources: [InfoQ](<https://devfeed.tech/sources/infoq.md>)

Topics: [AI Infrastructure](<https://devfeed.tech/topics/ai-infrastructure.md>), [Cloud Native Operations](<https://devfeed.tech/topics/cloud-native-operations.md>), [Open Source](<https://devfeed.tech/topics/open-source.md>), [Google](<https://devfeed.tech/topics/google.md>), [container native](<https://devfeed.tech/topics/container-native.md>), [linux foundation](<https://devfeed.tech/topics/linux-foundation.md>)

Tags: [agent](<https://devfeed.tech/tags/agent.md>), [agent-infrastructure](<https://devfeed.tech/tags/agent-infrastructure.md>), [agent-state](<https://devfeed.tech/tags/agent-state.md>), [agent-substrate](<https://devfeed.tech/tags/agent-substrate.md>), [agentic](<https://devfeed.tech/tags/agentic.md>), [agentic-systems](<https://devfeed.tech/tags/agentic-systems.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-agent-infrastructure](<https://devfeed.tech/tags/ai-agent-infrastructure.md>), [ai-agents](<https://devfeed.tech/tags/ai-agents.md>), [ai-coding-agents](<https://devfeed.tech/tags/ai-coding-agents.md>), [ai-generated-code](<https://devfeed.tech/tags/ai-generated-code.md>), [ai-ml-data-engineering](<https://devfeed.tech/tags/ai-ml-data-engineering.md>), [aiops](<https://devfeed.tech/tags/aiops.md>), [cloud-native](<https://devfeed.tech/tags/cloud-native.md>), [cloud-native-computing-foundation](<https://devfeed.tech/tags/cloud-native-computing-foundation.md>), [cncf](<https://devfeed.tech/tags/cncf.md>), [containers](<https://devfeed.tech/tags/containers.md>), [devops](<https://devfeed.tech/tags/devops.md>), [google](<https://devfeed.tech/tags/google.md>), [google-substrate-gvisor-cncf](<https://devfeed.tech/tags/google-substrate-gvisor-cncf.md>), [gvisor](<https://devfeed.tech/tags/gvisor.md>), [kubernetes](<https://devfeed.tech/tags/kubernetes.md>), [ml-data-engineering](<https://devfeed.tech/tags/ml-data-engineering.md>), [news](<https://devfeed.tech/tags/news.md>), [open-source](<https://devfeed.tech/tags/open-source.md>), [open-source-governance](<https://devfeed.tech/tags/open-source-governance.md>), [scale](<https://devfeed.tech/tags/scale.md>), [secure-ai-agents](<https://devfeed.tech/tags/secure-ai-agents.md>), [vendor-neutral-open-source](<https://devfeed.tech/tags/vendor-neutral-open-source.md>)

### AI overview

Google is donating Agent Substrate and gVisor to the CNCF, alongside its OpenRL project, to support open governance of infrastructure for AI agents. Agent Substrate separates persistent agent sessions ("actors") from reusable, pre-warmed Kubernetes workers: it can save idle agents' state, release compute, and restore sessions in under 500 milliseconds without creating a Pod for every execution, according to Google. gVisor adds isolation by intercepting system calls in a user-space application kernel; Agent Substrate also supports Cloud Hypervisor microVMs for workloads needing hardware-level virtualization. The approach targets agents' frequent pauses and resumptions, costly idle compute, Kubernetes control-plane load, and risks from executing generated code. The text presents these projects as one contribution to a wider effort that also includes technologies such as Kata Containers and Firecracker.

### Source excerpt

Google has announced it is donating Agent Substrate and gVisor to the Cloud Native Computing Foundation (CNCF), placing two important components of its AI agent infrastructure under vendor-neutral open-source governance. By Craig Risi

## 7 Ways AI Agents Fail in Production (and How to Catch Each One)

DevFeed: [7 Ways AI Agents Fail in Production (and How to Catch Each One)](<https://devfeed.tech/articles/7-ways-ai-agents-fail-in-production-and-how-to-catch-each-one-146247.md>)

Original publisher: [Read original article](<https://machinelearningmastery.com/7-ways-ai-agents-fail-in-production-and-how-to-catch-each-one/>)

Author: Nahla Davies

Published: 2026-11-20T11:00:00Z

Content type: article

Language: en

Sources: [MachineLearningMastery.com](<https://devfeed.tech/sources/machinelearningmastery-com.md>)

Topics: [Test-driven development](<https://devfeed.tech/topics/tdd.md>), [ReAct agent Python](<https://devfeed.tech/topics/react-agent-python.md>), [OpenTelemetry](<https://devfeed.tech/topics/opentelemetry.md>), [Integration testing](<https://devfeed.tech/topics/integration-testing.md>), [Chaos Engineering](<https://devfeed.tech/topics/chaos-engineering.md>), [Exception handling](<https://devfeed.tech/topics/exception-handling.md>), [long-running](<https://devfeed.tech/topics/long-running.md>), [rate-limiting](<https://devfeed.tech/topics/rate-limiting.md>)

Tags: [agent-evaluation](<https://devfeed.tech/tags/agent-evaluation.md>), [agentic](<https://devfeed.tech/tags/agentic.md>), [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-agents](<https://devfeed.tech/tags/ai-agents.md>), [artificial-intelligence](<https://devfeed.tech/tags/artificial-intelligence.md>), [fail](<https://devfeed.tech/tags/fail.md>), [how-to](<https://devfeed.tech/tags/how-to.md>), [production](<https://devfeed.tech/tags/production.md>)

### AI overview

A green tool response does not prove an agent completed its task; verify outcomes in resulting state and external records. The excerpt proposes seven regression checks: strictly validate tool arguments; compare extracted fields and source versions with confirmed ground truth; test whether injected document instructions are proposed and ensure they never execute; deny unauthorized cross-tenant or unapproved actions and assert stored data stays unchanged; retry with a stable operation ID and deduplicate matching requests; restart from persistent checkpoints and assert completion only when an authorized receipt exists; and stop repeated actions when progress stalls, using separate limits for calls, time, spend, and graph execution. Correlate run events under one ID, distinguish proposed, denied, waiting, and complete states, and pair each failing fixture with a passing control. The excerpt notes limits: confidence scores and citations do not establish correctness, in-memory checkpoints are lost on restart, and a timeout may leave an action's outcome unknown.

### Source excerpt

Three events that look alike need separate names.

## Best API Catalogs and Registries for AI Agents

DevFeed: [Best API Catalogs and Registries for AI Agents](<https://devfeed.tech/articles/best-api-catalogs-and-registries-for-ai-agents-146946.md>)

Original publisher: [Read original article](<https://www.swytchcode.com/content/best-api-catalogs-registries-agents>)

Author: Swytchcode Team

Published: 2026-11-20T09:00:00Z

Content type: comparison

Language: en

Sources: [Swytchcode](<https://devfeed.tech/sources/swytchcode.md>)

Topics: [REST API](<https://devfeed.tech/topics/rest-api.md>), [Postman](<https://devfeed.tech/topics/postman.md>), [Swagger](<https://devfeed.tech/topics/swagger.md>), [OpenTelemetry](<https://devfeed.tech/topics/opentelemetry.md>), [Slack](<https://devfeed.tech/topics/slack.md>)

Tags: [2026](<https://devfeed.tech/tags/2026.md>), [actions](<https://devfeed.tech/tags/actions.md>), [agentic](<https://devfeed.tech/tags/agentic.md>), [agentic-workflows](<https://devfeed.tech/tags/agentic-workflows.md>), [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-agents](<https://devfeed.tech/tags/ai-agents.md>), [api](<https://devfeed.tech/tags/api.md>), [api-catalog](<https://devfeed.tech/tags/api-catalog.md>), [api-governance](<https://devfeed.tech/tags/api-governance.md>), [api-management](<https://devfeed.tech/tags/api-management.md>), [api-testing](<https://devfeed.tech/tags/api-testing.md>), [apps](<https://devfeed.tech/tags/apps.md>), [arcade](<https://devfeed.tech/tags/arcade.md>), [backstage](<https://devfeed.tech/tags/backstage.md>), [engineering](<https://devfeed.tech/tags/engineering.md>), [postman](<https://devfeed.tech/tags/postman.md>), [registries](<https://devfeed.tech/tags/registries.md>), [schema](<https://devfeed.tech/tags/schema.md>)

### AI overview

The comparison centers on whether an API catalog checks schemas against live providers when an agent calls a method. Backstage stores manually maintained YAML entities; Postman's Catalog surfaces governance and validation but describes no live endpoint polling; Stoplight lints specs during design; Composio, Arcade, Pipedream, and Zapier MCP offer broad agent tool catalogs, but their cited docs do not describe call-time schema drift checks. Swagger Catalog is presented as aiming to validate in real time, though its implementation could not be verified from public pages and it was still rolling out at the time checked. The excerpt says Swytchcode validates each execution against the real API and records audit results, while cautioning that semantic discovery can select the wrong provider unless scoped. It also says Swytchcode lacks hosted end-user SaaS connection screens, making Composio or Arcade faster for that use case. Catalog size, authorization, design-time governance, and call-time freshness address different needs.

### Source excerpt

We rank Backstage, Postman, Stoplight, SwaggerHub and the agent-native catalogs on one question: does the schema stay current at call time?

## Agentic AI repeats same old enterprise adoption cycle

DevFeed: [Agentic AI repeats same old enterprise adoption cycle](<https://devfeed.tech/articles/agentic-ai-repeats-same-old-enterprise-adoption-cycle-146087.md>)

Original publisher: [Read original article](<https://www.infoworld.com/article/4249734/agentic-ai-repeats-same-old-enterprise-adoption-cycle.html>)

Author: David Linthicum

Published: 2026-11-20T09:00:00Z

Content type: opinion

Language: en

Sources: [InfoWorld](<https://devfeed.tech/sources/infoworld.md>)

Topics: [Agentic AI](<https://devfeed.tech/topics/what-is-agentic-ai.md>), [Enterprise Architecture](<https://devfeed.tech/topics/enterprise-architecture.md>), [AI Integration Strategies](<https://devfeed.tech/topics/ai-integration-strategies.md>), [agentic workflows](<https://devfeed.tech/topics/agentic-workflows.md>), [business logic](<https://devfeed.tech/topics/business-logic.md>), [API Governance](<https://devfeed.tech/topics/api-governance.md>), [observability](<https://devfeed.tech/topics/observability.md>), [LLM security](<https://devfeed.tech/topics/llm-security.md>)

Tags: [adoption](<https://devfeed.tech/tags/adoption.md>), [agentic](<https://devfeed.tech/tags/agentic.md>), [agentic-ai](<https://devfeed.tech/tags/agentic-ai.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-agents](<https://devfeed.tech/tags/ai-agents.md>), [apis](<https://devfeed.tech/tags/apis.md>), [architecture](<https://devfeed.tech/tags/architecture.md>), [artificial-intelligence](<https://devfeed.tech/tags/artificial-intelligence.md>), [artificial-intelligence-emerging-technology-generative-ai](<https://devfeed.tech/tags/artificial-intelligence-emerging-technology-generative-ai.md>), [automate](<https://devfeed.tech/tags/automate.md>), [complexity](<https://devfeed.tech/tags/complexity.md>), [cost](<https://devfeed.tech/tags/cost.md>), [costs](<https://devfeed.tech/tags/costs.md>), [data](<https://devfeed.tech/tags/data.md>), [decision](<https://devfeed.tech/tags/decision.md>), [emerging-technology](<https://devfeed.tech/tags/emerging-technology.md>), [enterprise](<https://devfeed.tech/tags/enterprise.md>), [exception-handling](<https://devfeed.tech/tags/exception-handling.md>), [generative-ai](<https://devfeed.tech/tags/generative-ai.md>), [guardrails](<https://devfeed.tech/tags/guardrails.md>), [language-en](<https://devfeed.tech/tags/language-en.md>), [logging](<https://devfeed.tech/tags/logging.md>), [observability](<https://devfeed.tech/tags/observability.md>), [production](<https://devfeed.tech/tags/production.md>), [project](<https://devfeed.tech/tags/project.md>), [storytype-opinion](<https://devfeed.tech/tags/storytype-opinion.md>)

### AI overview

A distributor's agentic AI sales system ran successfully, but after supporting integration, governance, security, testing and operational costs were included, it cost roughly 20 times as much as a traditional architecture for about the same ROI. The article argues that agents are most useful when work requires interpretation, adaptation and semi-autonomous action; stable, rules-based or highly regulated workflows may be served more economically by conventional applications, workflow engines, rules or API integration. It recommends starting with measurable business value and assessing production costs and governance needs rather than adopting an architecture because it is fashionable. The text compares this adoption pattern with SOA, microservices and cloud-native systems, each of which can deliver benefits but also impose complexity when used without a fitting need or organizational maturity.

### Source excerpt

The pitch sounded perfect. A large regional distributor needed to build a new sales transaction management system. The goal was straightforward: automate parts of order intake, discount approvals, exception handling, customer communications, and inventory checks. It was not a trivial system, but it was also something the industry had built before. Then the vendor presentations began. Every software provider seemed to have a new agentic AI story. Their platforms had agents that could make decisions, orchestrate workflows, interpret customer intent, route exceptions, and learn from business context. One vendor described its offering as a common LLM brain that could make decisions as if the company had hired 10,000 experts, except those experts were not on the payroll. That line was from an actual sales pitch, and it landed well in the boardroom. The company decided to go agentic. The architecture would use AI agents to manage decision flows, invoke tools, check policies, interact with enterprise systems, and escalate only when needed. It looked modern. It looked strategic. It looked like the future. Then reality arrived. Building the system required far more integration work than expected. Each agent needed access to clean data, governed APIs, business rules, security controls, observability, exception handling, and human override mechanisms. The team had to build guardrails around decisions, logging around reasoning, test harnesses for unpredictable outcomes, and new operational processes for things traditional systems handled more predictably. Costs ballooned. Security reviews took longer. Operational complexity increased. The project ultimately ran fine once in production, but six months later, the company realized the uncomfortable truth: the system cost roughly 20 times more than a traditional architecture would have cost when all supporting complexity was included, and it delivered about the same ROI. I am hearing versions of this story once or twice a week from

## Human in the Loop AI: How to Safely Scale Agentic Workloads with Tunable Autonomy

DevFeed: [Human in the Loop AI: How to Safely Scale Agentic Workloads with Tunable Autonomy](<https://devfeed.tech/articles/human-in-the-loop-ai-how-to-safely-scale-agentic-workloads-with-tunable-autonomy-146217.md>)

Original publisher: [Read original article](<https://hackernoon.com/human-in-the-loop-ai-how-to-safely-scale-agentic-workloads-with-tunable-autonomy?source=rss>)

Author: PlayerZero

Published: 2026-11-20T06:49:40Z

Content type: article

Language: en

Sources: [HackerNoon](<https://devfeed.tech/sources/hackernoon.md>)

Topics: [human in the loop agent](<https://devfeed.tech/topics/human-in-the-loop-agent.md>), [agentic workflows](<https://devfeed.tech/topics/agentic-workflows.md>), [human review](<https://devfeed.tech/topics/human-review.md>), [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [Agentic AI](<https://devfeed.tech/topics/what-is-agentic-ai.md>)

Tags: [accountability](<https://devfeed.tech/tags/accountability.md>), [adoption](<https://devfeed.tech/tags/adoption.md>), [agent](<https://devfeed.tech/tags/agent.md>), [agent-identity](<https://devfeed.tech/tags/agent-identity.md>), [agentic](<https://devfeed.tech/tags/agentic.md>), [agentic-ai](<https://devfeed.tech/tags/agentic-ai.md>), [agentic-ai-governance](<https://devfeed.tech/tags/agentic-ai-governance.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-agent](<https://devfeed.tech/tags/ai-agent.md>), [ai-agent-accountability](<https://devfeed.tech/tags/ai-agent-accountability.md>), [ai-agent-autonomy-levels](<https://devfeed.tech/tags/ai-agent-autonomy-levels.md>), [ai-engineering-context](<https://devfeed.tech/tags/ai-engineering-context.md>), [ai-workflow-automation](<https://devfeed.tech/tags/ai-workflow-automation.md>), [autonomous-ai-workflows](<https://devfeed.tech/tags/autonomous-ai-workflows.md>), [autonomy](<https://devfeed.tech/tags/autonomy.md>), [engineering](<https://devfeed.tech/tags/engineering.md>), [good-company](<https://devfeed.tech/tags/good-company.md>), [guardrails](<https://devfeed.tech/tags/guardrails.md>), [how-to](<https://devfeed.tech/tags/how-to.md>), [human-in-the-loop](<https://devfeed.tech/tags/human-in-the-loop.md>), [human-in-the-loop-ai](<https://devfeed.tech/tags/human-in-the-loop-ai.md>), [metrics](<https://devfeed.tech/tags/metrics.md>), [performance](<https://devfeed.tech/tags/performance.md>), [performance-metrics](<https://devfeed.tech/tags/performance-metrics.md>), [safely](<https://devfeed.tech/tags/safely.md>), [scale](<https://devfeed.tech/tags/scale.md>), [teams](<https://devfeed.tech/tags/teams.md>), [tunable-ai-autonomy](<https://devfeed.tech/tags/tunable-ai-autonomy.md>)

### AI overview

The article recommends expanding AI agent autonomy gradually, based on evidence and workflow risk, while keeping humans accountable at critical checkpoints. It defines four levels: manual approval, recommend-only, auto-with-approval at key steps, and fully autonomous within boundaries; teams can tune these by service, repository, severity, ticket type, or team. Begin with human review, then weigh approval rates alongside MTTR, regressions, escaped defects, rollbacks, and cycle time. Also assess whether agents understand system and business context, know whom to involve, and follow team processes. Autonomy gates are especially important for cross-team handoffs and disruptive or hard-to-reverse actions. The proposed safeguards are audit trails, attributable actions, reversibility, and runtime policy constraints such as tool allowlists and scope isolation. The article reports that Cyrano Video reduced engineering support and bug-fix time by roughly 80%; Cayuse reportedly found and fixed 90% of issues before users noticed and cut average resolution time by 80%.

### Source excerpt

Learn how tunable autonomy helps engineering teams expand AI agent responsibilities through human approval, performance metrics, autonomy gates, and guardrails.

## Verifiable Logic in Medical LLMs: A Critical Review of Agentic Clinical Reasoning Optimization and Neuro-Symbolic Grounding

DevFeed: [Verifiable Logic in Medical LLMs: A Critical Review of Agentic Clinical Reasoning Optimization and Neuro-Symbolic Grounding](<https://devfeed.tech/articles/verifiable-logic-in-medical-llms-a-critical-review-of-agentic-clinical-reasoning-optimization-and-neuro-symbolic-grounding-145116.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.25898>)

Author: Youssef ElNahas, Adel Ammar, Soumaya Chaffar, Wadii Boulila

Published: 2026-11-20T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Artificial Intelligence](<https://devfeed.tech/sources/arxiv-artificial-intelligence.md>), [arXiv: Machine Learning](<https://devfeed.tech/sources/arxiv-machine-learning.md>)

Topics: [llm-reasoning](<https://devfeed.tech/topics/llm-reasoning.md>), [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [Automated reasoning](<https://devfeed.tech/topics/automated-reasoning.md>), [Agentic AI](<https://devfeed.tech/topics/what-is-agentic-ai.md>), [LLM evaluation / benchmarking](<https://devfeed.tech/topics/llm-evaluation-benchmarking.md>), [LLM security](<https://devfeed.tech/topics/llm-security.md>)

Tags: [abstract](<https://devfeed.tech/tags/abstract.md>), [agent](<https://devfeed.tech/tags/agent.md>), [agentic](<https://devfeed.tech/tags/agentic.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-safety](<https://devfeed.tech/tags/ai-safety.md>), [also](<https://devfeed.tech/tags/also.md>), [amplify](<https://devfeed.tech/tags/amplify.md>), [architecture](<https://devfeed.tech/tags/architecture.md>), [arxiv](<https://devfeed.tech/tags/arxiv.md>), [audit](<https://devfeed.tech/tags/audit.md>), [benchmarks](<https://devfeed.tech/tags/benchmarks.md>), [bounded](<https://devfeed.tech/tags/bounded.md>), [critical](<https://devfeed.tech/tags/critical.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cs-cl](<https://devfeed.tech/tags/cs-cl.md>), [cs-cy](<https://devfeed.tech/tags/cs-cy.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [grounding](<https://devfeed.tech/tags/grounding.md>), [llms](<https://devfeed.tech/tags/llms.md>), [logic](<https://devfeed.tech/tags/logic.md>), [medical](<https://devfeed.tech/tags/medical.md>), [optimization](<https://devfeed.tech/tags/optimization.md>), [reasoning](<https://devfeed.tech/tags/reasoning.md>), [review](<https://devfeed.tech/tags/review.md>)

### AI overview

Clinical LLMs can produce correct answers through invalid reasoning that final-answer benchmarks miss, while multi-agent and tool-augmented systems may propagate early errors. This review examines hallucination, agentic error cascades, process reward models that supervise reasoning step by step, and neuro-symbolic grounding using logic engines, ontology reasoners, and knowledge graphs to constrain neural outputs. Symbolic veto layers provide guarantees only within their encoded knowledge; reported safety gains come from individual studies, mostly simulated or small-sample, and are not directly comparable with neural baselines. Process reward models are limited by their training data. The authors propose matching agentic failure modes to symbolic interventions and recommend auditing reasoning trajectories alongside benchmark accuracy in clinical AI certification.

### Source excerpt

arXiv:2611.25898v1 Announce Type: cross Abstract: Clinical large language models are usually judged by whether the final answer is right. Yet a model can reach a fluent, plausible output through invalid reasoning that static benchmarks do not detect, and confident hallucination, causally invalid inference, and spurious demographic shortcuts can pass conventional evaluation. This critical review covers four paradigms in turn: how clinical hallucination arises and why static metrics miss it; the agentic hallucination cascade, in which multi-agent and tool-augmented systems propagate and amplify early reasoning errors; process reward modeling as step-level supervision; and neuro-symbolic grounding, in which formal logic engines, ontology reasoners, and knowledge graphs place verifiable constraints on neural output. Within their encoded domains, systems with symbolic veto layers offer guarantees that hold relative to their encoded knowledge, and they report large gains on the safety measures they use. These results come from single studies, mostly in simulated or small-sample settings, and are not directly comparable with neural baselines. Process reward models remain bounded by the statistics of their training data. We propose a conceptual framework that maps each agentic failure mode to a symbolic intervention point, and we argue that clinical AI safety depends substantially on system architecture. Because current regulation emphasizes performance and does not require verification of reasoning steps, we argue that responsible certification should also audit reasoning trajectories alongside accuracy on static benchmarks.

## Why Trust Your Agent? Empirical Security Gains from TRiSM-Guided Agentic Workflows in Healthcare

DevFeed: [Why Trust Your Agent? Empirical Security Gains from TRiSM-Guided Agentic Workflows in Healthcare](<https://devfeed.tech/articles/why-trust-your-agent-empirical-security-gains-from-trism-guided-agentic-workflows-in-healthcare-145354.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2606.28666>)

Author: Liam Kearns

Published: 2026-11-20T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Artificial Intelligence](<https://devfeed.tech/sources/arxiv-artificial-intelligence.md>), [arXiv: Cryptography and Security](<https://devfeed.tech/sources/arxiv-cryptography-and-security.md>)

Topics: [LLM security](<https://devfeed.tech/topics/llm-security.md>), [ai security](<https://devfeed.tech/topics/ai-security.md>), [least privilege](<https://devfeed.tech/topics/least-privilege.md>), [Security](<https://devfeed.tech/topics/security.md>), [Large Language Model](<https://devfeed.tech/topics/llm.md>), [Retrieval Augmented Generation (RAG)](<https://devfeed.tech/topics/retrieval-augmented-generation-rag.md>)

Tags: [agent](<https://devfeed.tech/tags/agent.md>), [agentic](<https://devfeed.tech/tags/agentic.md>), [agentic-workflows](<https://devfeed.tech/tags/agentic-workflows.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-trust](<https://devfeed.tech/tags/ai-trust.md>), [attack](<https://devfeed.tech/tags/attack.md>), [automation](<https://devfeed.tech/tags/automation.md>), [breaches](<https://devfeed.tech/tags/breaches.md>), [claude-haiku-4-5](<https://devfeed.tech/tags/claude-haiku-4-5.md>), [client](<https://devfeed.tech/tags/client.md>), [construction](<https://devfeed.tech/tags/construction.md>), [covid-19](<https://devfeed.tech/tags/covid-19.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cs-cr](<https://devfeed.tech/tags/cs-cr.md>), [data](<https://devfeed.tech/tags/data.md>), [diagnosis](<https://devfeed.tech/tags/diagnosis.md>), [disclosure](<https://devfeed.tech/tags/disclosure.md>), [gemini](<https://devfeed.tech/tags/gemini.md>), [generation](<https://devfeed.tech/tags/generation.md>), [healthcare](<https://devfeed.tech/tags/healthcare.md>), [security](<https://devfeed.tech/tags/security.md>), [trust](<https://devfeed.tech/tags/trust.md>)

### AI overview

In a medical report-generation application tested with five LLMs, a TRiSM-guided workflow reduced attack success for RAG poisoning (31% to 10%) and data-field injection (42% to 25%), eliminated client-side network injection by construction, and increased report accuracy from 72.5% to 86.5%. In an exploratory grouping, attacks aimed beyond the reporting task, including data disclosure and tool abuse, fell from 21.7% to 2.5%, with no patient records disclosed under the redesign. However, attacks that changed the Covid-19 diagnosis remained effective, making up 32 of 35 successful attacks against the redesign. The findings suggest least privilege limits what injections can reach but cannot ensure the model resists injected content within its task; clinical outputs still need independent verification. No tested model resisted all three attack vectors.

### Source excerpt

arXiv:2606.28666v2 Announce Type: replace-cross Abstract: Agent-based AI has enabled the automation of tasks by exposing application tools and resources to large language models (LLMs). However, to improve scope and accuracy, agents are often given access rights that exceed those of ordinary users, introducing significant security risks and potential regulatory breaches. This paper applies the AI Trust, Risk, and Security Management (TRiSM) framework to a medical report-generation application to demonstrate how an insecure baseline workflow can be transformed into a security-conscious agentic workflow. Both designs were evaluated with five LLMs (Claude Haiku 4.5, GPT-4.1-nano, GPT-4.1-mini, GPT-5.4-mini and Gemini 2.5 Flash) across 800 report generations and 500 attack trials covering RAG poisoning, data-field injection and client-side network injection. The redesign reduced attack success from 31% to 10% for RAG poisoning and from 42% to 25% for data-field injection (McNemar p < 0.001 for both), removed network injection by construction, and raised report accuracy from 72.5% to 86.5%. In an exploratory post-hoc grouping by attack goal, success against attacks aimed outside the report task, such as data disclosure and tool abuse, fell from 21.7% to 2.5% and no patient record was disclosed under the redesign. Attacks altering the reported Covid-19 diagnosis remained effective, accounting for 32 of the 35 successful attacks against the redesign. Least-privilege architecture limits what an injection can reach, but not whether a model follows injected content within its task, so clinical outputs need verification independent of the LLM. No model resisted all three attack vectors, so model selection cannot substitute for secure workflow design.

## Perfumer: A Large Language Model-based Agentic Framework Accelerating Structural Relaxation and Electronic Band Prediction for First-Principle Calculation

DevFeed: [Perfumer: A Large Language Model-based Agentic Framework Accelerating Structural Relaxation and Electronic Band Prediction for First-Principle Calculation](<https://devfeed.tech/articles/perfumer-a-large-language-model-based-agentic-framework-accelerating-structural-relaxation-and-electronic-band-prediction-for-first-principle-calculation-145166.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.26349>)

Author: Zhiwei Li, Yuhao Zhou, Yikai Yang, Haonan Wang, Qing Ye, Jiancheng Lv, Kazunari Matsuda

Published: 2026-11-20T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Machine Learning](<https://devfeed.tech/sources/arxiv-machine-learning.md>)

Topics: [Large Language Model](<https://devfeed.tech/topics/llm.md>), [Neural Network](<https://devfeed.tech/topics/neural-network.md>)

Tags: [about](<https://devfeed.tech/tags/about.md>), [absolute](<https://devfeed.tech/tags/absolute.md>), [abstract](<https://devfeed.tech/tags/abstract.md>), [agent](<https://devfeed.tech/tags/agent.md>), [agentic](<https://devfeed.tech/tags/agentic.md>), [arxiv](<https://devfeed.tech/tags/arxiv.md>), [automatically](<https://devfeed.tech/tags/automatically.md>), [band](<https://devfeed.tech/tags/band.md>), [based](<https://devfeed.tech/tags/based.md>), [combines](<https://devfeed.tech/tags/combines.md>), [composition](<https://devfeed.tech/tags/composition.md>), [cond-mat-mtrl-sci](<https://devfeed.tech/tags/cond-mat-mtrl-sci.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [electronic](<https://devfeed.tech/tags/electronic.md>), [first](<https://devfeed.tech/tags/first.md>), [framework](<https://devfeed.tech/tags/framework.md>), [language](<https://devfeed.tech/tags/language.md>), [language-model](<https://devfeed.tech/tags/language-model.md>), [large](<https://devfeed.tech/tags/large.md>), [large-language-model](<https://devfeed.tech/tags/large-language-model.md>), [model](<https://devfeed.tech/tags/model.md>), [prediction](<https://devfeed.tech/tags/prediction.md>)

### AI overview

Perfumer links natural-language requests to workflows that combine Quantum ESPRESSO (QE) with predictive models for structural relaxation and electronic bands. In tested structures, pre-relaxation with Perfumer-relax followed by QE refinement produced a reported 2.75-fold overall speedup over QE alone. Perfumer-band predicts 12 band energies at requested wavevectors using a periodic graph neural network and latent Hermitian spectral head, preserving reciprocal-lattice periodicity and time-reversal symmetry without constructing a Hamiltonian. Trained on 125,153 band structures, it achieved a median per-material mean absolute error of 0.157 eV across 2,607 test materials, with inference taking about 97 ms per material on two consumer CPU cores. The described agent handles workflows from uploaded structures to automatically constructed candidates; the supplied excerpt does not establish performance beyond the reported tests.

### Source excerpt

arXiv:2611.26349v1 Announce Type: cross Abstract: First-principles structural relaxation and band calculations require substantial computation and expertise. Here we present Perfumer, a large language model-based agentic framework that couples Quantum ESPRESSO with two predictive models. Across tested structures, pre-relaxation with Perfumer-relax model followed by QE refinement yielded a 2.75-fold overall speedup over QE alone. Perfumer-band model combines a periodic graph neural network with a latent Hermitian spectral head returns 12 band energies at any requested wavevector, preserving reciprocal lattice periodicity and time-reversal symmetry without constructing Hamiltonian. Trained on 125,153 self-curated band structures, Perfumer-band model reaches a median per-material mean absolute error of 0.157 eV on 2,607 test materials, including lanthanide, actinide and magnetic compounds, from held-out composition families spanning 85 elements, taking about 97 ms per material on two consumer CPU cores. The agent turns natural-language requests into relaxation-to-band workflows, from a single uploaded structure to automatically constructed new candidates and returns predicted properties.

## Replication of Agentic Security Events: Audit and Investigation (ROGUE-AI)

DevFeed: [Replication of Agentic Security Events: Audit and Investigation (ROGUE-AI)](<https://devfeed.tech/articles/replication-of-agentic-security-events-audit-and-investigation-rogue-ai-145684.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.26553>)

Author: Mengxiao Wang, Mahbub Alam, Kalyan Nakka, Nitesh Saxena

Published: 2026-11-20T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Artificial Intelligence](<https://devfeed.tech/sources/arxiv-artificial-intelligence.md>), [arXiv: Cryptography and Security](<https://devfeed.tech/sources/arxiv-cryptography-and-security.md>)

Topics: [LLM security](<https://devfeed.tech/topics/llm-security.md>), [audit](<https://devfeed.tech/topics/audit.md>), [ai security](<https://devfeed.tech/topics/ai-security.md>), [Security](<https://devfeed.tech/topics/security.md>)

Tags: [agent-framework](<https://devfeed.tech/tags/agent-framework.md>), [agentic](<https://devfeed.tech/tags/agentic.md>), [agentic-security](<https://devfeed.tech/tags/agentic-security.md>), [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [audit](<https://devfeed.tech/tags/audit.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cs-cr](<https://devfeed.tech/tags/cs-cr.md>), [cs-ma](<https://devfeed.tech/tags/cs-ma.md>), [database](<https://devfeed.tech/tags/database.md>), [deepseek](<https://devfeed.tech/tags/deepseek.md>), [delete](<https://devfeed.tech/tags/delete.md>), [events](<https://devfeed.tech/tags/events.md>), [failures](<https://devfeed.tech/tags/failures.md>), [files](<https://devfeed.tech/tags/files.md>), [framework](<https://devfeed.tech/tags/framework.md>), [gemini](<https://devfeed.tech/tags/gemini.md>), [investigation](<https://devfeed.tech/tags/investigation.md>), [multi-agent](<https://devfeed.tech/tags/multi-agent.md>), [replication](<https://devfeed.tech/tags/replication.md>), [rogue-ai](<https://devfeed.tech/tags/rogue-ai.md>), [security](<https://devfeed.tech/tags/security.md>), [security-events](<https://devfeed.tech/tags/security-events.md>)

### AI overview

ROGUE-AI audits reported agent failures by reconstructing incidents offline and comparing agent runs with matched controls that omit only the suspected cause. In 108 attempted replications, it reproduced reported harm in 89%; across five GPT, Claude, Gemini, and DeepSeek models, the reported mistake occurred in 18-33% of runs versus at most 1% in controls. Among 72 incidents involving real-world harm, 62 had no attacker: agents followed their tasks but missed ordinary hazards. These replications caused more harm than prompt-injection cases for all five models, exposing a gap for defenses focused on injected instructions. A warning after each tool output that named the hazard and its consequence reduced harm for all five models; an equally long generic note left most harm in place. The abstract presents the replications as a reusable audit framework vendors can rerun before releases.

### Source excerpt

arXiv:2611.26553v1 Announce Type: cross Abstract: Agents based on large language models (LLMs) can now delete files and send payments on behalf of their users. News media reports routinely describe failures of these agents (e.g., Replit's coding agent deleting a production database), but a report often only says what went wrong and rarely (in)validates the incident or finds its root cause. Incident catalogs collect these reports, and benchmarks record whether agents fail, but neither replicates an incident nor tests the cause its report might identify. In this paper, we present ROGUE-AI (Replication of Agentic Security Events: Audit and Investigation), a multi-agent framework that closes the above gap and rebuilds each reported incident offline together with a matched control that lacks only the blamed cause, and runs agents on both. Our results suggest that ROGUE-AI is able to reproduce the reported harm in 89% of its 108 attempted replications. Agents built on five current GPT, Claude, Gemini and DeepSeek models made the reported mistake in 18% to 33% of runs, against at most 1% without the blamed cause. Of the 72 incidents with real-world harm, 62 had no underlying attacker, and in these, agents did what their task asked for but missed an ordinary hazard, such as a database shared with the live site. Replications without an attacker caused more harm than replications of prompt injection for all five models. Defenses against prompt injection look for injected instructions, but these replications contain none. Further, a warning after each tool output that names the hazard and its consequence lowered harm for all five models, whereas a note of the same length that does not mention the hazard left most of the harm in place. Built from real incidents, the ROGUE-AI replications form a reusable audit framework that vendors can rerun before each new release.

## Cost-Aware Agentic Feature Optimization System for Fleet-Scale Ranking Models

DevFeed: [Cost-Aware Agentic Feature Optimization System for Fleet-Scale Ranking Models](<https://devfeed.tech/articles/cost-aware-agentic-feature-optimization-system-for-fleet-scale-ranking-models-145193.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.26531>)

Author: Chang Yang, Yao Xuan, Wendan Yan, Nhat Le, Jiang Liu, Longhao Jin, Zhen Peggy Yao, Alireza Vahdatpour, Djordje Gligorijevic

Published: 2026-11-20T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Artificial Intelligence](<https://devfeed.tech/sources/arxiv-artificial-intelligence.md>), [arXiv: Machine Learning](<https://devfeed.tech/sources/arxiv-machine-learning.md>)

Topics: [Feature Engineering](<https://devfeed.tech/topics/feature-engineering.md>), [AI Agent](<https://devfeed.tech/topics/ai-agent.md>), [Combinatorial optimization](<https://devfeed.tech/topics/combinatorial-optimization.md>)

Tags: [agentic](<https://devfeed.tech/tags/agentic.md>), [asynchronous](<https://devfeed.tech/tags/asynchronous.md>), [blending](<https://devfeed.tech/tags/blending.md>), [budget](<https://devfeed.tech/tags/budget.md>), [candidate](<https://devfeed.tech/tags/candidate.md>), [cost](<https://devfeed.tech/tags/cost.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cs-ir](<https://devfeed.tech/tags/cs-ir.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [entropy](<https://devfeed.tech/tags/entropy.md>), [experiments](<https://devfeed.tech/tags/experiments.md>), [feature](<https://devfeed.tech/tags/feature.md>), [feature-selection](<https://devfeed.tech/tags/feature-selection.md>), [features](<https://devfeed.tech/tags/features.md>), [fleet](<https://devfeed.tech/tags/fleet.md>), [large](<https://devfeed.tech/tags/large.md>), [llm](<https://devfeed.tech/tags/llm.md>), [models](<https://devfeed.tech/tags/models.md>), [optimization](<https://devfeed.tech/tags/optimization.md>), [ranking](<https://devfeed.tech/tags/ranking.md>), [ranking-models](<https://devfeed.tech/tags/ranking-models.md>), [scale](<https://devfeed.tech/tags/scale.md>), [system](<https://devfeed.tech/tags/system.md>)

### AI overview

The system optimizes features across fleets of ranking models while respecting shared and per-model resource limits, including pipeline cost and serving throughput. LLM agents generate and shortlist cross features, while deterministic tools run and verify experiments. Several importance rankings are blended, using Pareto fronts for multi-task models; a Researcher agent then tunes selections through 10-25 asynchronous trials under resource caps, followed by trimming to meet pipeline budgets. Across production models, normalized entropy rose by 0.31% on average within each model's budget. Trimming reduced pipeline cost by 2.3% with no regression beyond measurement noise, and online A/B tests reported a 0.20% gain in a primary metric.

### Source excerpt

arXiv:2611.26531v1 Announce Type: cross Abstract: Large Web platforms operate large fleets of ranking models, each selecting features from a shared pool of tens of thousands. We present an end-to-end agentic system that optimizes features across the fleet under resource constraints shared across models and those set per model, such as feature pipeline cost and serving throughput (QPS), respectively. In this system, LLM agents propose hypotheses, and deterministic tools execute experiments and verify them. For each model, an LLM generates and shortlists cross features from a combinatorial candidate space, and all features are then ranked by several importance methods. Feature blending mixes these rankings into a single selection, using Pareto fronts across tasks for multi-task models. An LLM Researcher agent then tunes the feature selection in 10--25 asynchronous trials under resource caps, and a trimming step keeps the pipeline cost within budget. Across production models, the system improves normalized entropy by 0.31% on average within each model's budget, and the trimming step cuts pipeline cost by 2.3% with no regression beyond measurement noise. The optimized models were launched, and in online A/B tests they improved a primary online metric by 0.20%.

## KernelOPT: Dispatch-Aware Agentic Search for GPU Kernel Optimization

DevFeed: [KernelOPT: Dispatch-Aware Agentic Search for GPU Kernel Optimization](<https://devfeed.tech/articles/kernelopt-dispatch-aware-agentic-search-for-gpu-kernel-optimization-144934.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2609.30059>)

Author: Aheli Poddar, Sanskar Prasad, Arindam Samanta, Subha Chakraborty, Vishal Goyal, Rohit Singh Rathaur

Published: 2026-11-20T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Artificial Intelligence](<https://devfeed.tech/sources/arxiv-artificial-intelligence.md>), [arXiv: Distributed Computing](<https://devfeed.tech/sources/arxiv-distributed-computing.md>), [arXiv: Machine Learning](<https://devfeed.tech/sources/arxiv-machine-learning.md>)

Topics: [Compilers and Linkers](<https://devfeed.tech/topics/compilers-and-linkers.md>), [PyTorch](<https://devfeed.tech/topics/pytorch.md>), [LLM optimization](<https://devfeed.tech/topics/llm-optimization.md>), [Multi-GPU](<https://devfeed.tech/topics/multi-gpu.md>)

Tags: [2](<https://devfeed.tech/tags/2.md>), [abstract](<https://devfeed.tech/tags/abstract.md>), [agent](<https://devfeed.tech/tags/agent.md>), [agentic](<https://devfeed.tech/tags/agentic.md>), [architectures](<https://devfeed.tech/tags/architectures.md>), [arithmetic](<https://devfeed.tech/tags/arithmetic.md>), [artifacts](<https://devfeed.tech/tags/artifacts.md>), [arxiv](<https://devfeed.tech/tags/arxiv.md>), [automatically](<https://devfeed.tech/tags/automatically.md>), [challenge](<https://devfeed.tech/tags/challenge.md>), [changes](<https://devfeed.tech/tags/changes.md>), [code](<https://devfeed.tech/tags/code.md>), [comparison](<https://devfeed.tech/tags/comparison.md>), [compiler](<https://devfeed.tech/tags/compiler.md>), [compilers](<https://devfeed.tech/tags/compilers.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cs-dc](<https://devfeed.tech/tags/cs-dc.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [dispatch](<https://devfeed.tech/tags/dispatch.md>), [gpu](<https://devfeed.tech/tags/gpu.md>), [kernel](<https://devfeed.tech/tags/kernel.md>), [optimization](<https://devfeed.tech/tags/optimization.md>), [search](<https://devfeed.tech/tags/search.md>)

### AI overview

KernelOPT uses profiling-guided agents to inspect compiler artifacts, including generated Triton kernels and external library calls, then synthesize and refine kernels and evaluate the assembled model. Its four validation stages combine execution checks, multi-seed numerical comparisons, model-level checks with a float64 fallback, and an end-to-end performance gate of 1.03x. On 250 KernelBench problems run on NVIDIA H200, it reports geometric mean speedups over torch.compile of 1.40x for single operators, 1.15x for composite operators, and 1.07x for model architectures. The authors note that gains include precision changes and algebraic simplifications within evaluated tolerances, and that isolated kernel improvements can differ from end-to-end performance.

### Source excerpt

arXiv:2609.30059v3 Announce Type: replace-cross Abstract: Deep learning inference and training performance depends critically on GPU kernel efficiency. Modern compilers such as PyTorch Inductor automatically generate GPU kernels from high-level model code, but frequently underperform expert-written implementations by wide margins. Recent LLM-assisted optimizers explore these opportunities through kernel generation and refinement; yet translating isolated kernel improvements into model-level gains remains a challenge. We present KernelOPT, a profiling-guided multi-agent system for GPU kernel optimization. It inspects generated Triton kernels and external library calls in compiler artifacts to guide synthesis and refinement, then assembles and evaluates the resulting model. Four stages of validation combine execution checks, multi-seed numerical comparison, model-level checking with a float64 fallback and end-to-end performance gating ($\gamma{=}1.03$). The system supports PyTorch nn.Modules, standalone Triton kernels, and Helion kernels. It is evaluated on all 250 KernelBench problems on NVIDIA H200 which includes 100 single-operator problems (Level1), 100 composite operators (Level2), and 50 model architectures (Level3). KernelOPT achieves geometric mean speedups over torch.compile of 1.40$\times$, 1.15$\times$ and 1.07$\times$ respectively across L1, L2 and L3. Among problems exceeding 1.03$\times$ speedup, the geomeans are 2.54$\times$ (36 L1), 1.84$\times$ (23 L2), and 1.37$\times$ (11 L3). These gains include arithmetic-precision changes and task-specific algebraic simplifications under the evaluated numerical tolerances. The evaluation also reveals discrepancies between isolated kernel improvements and end-to-end performance, motivating model-level measurement alongside kernel-level optimization. Code is available at https://github.com/TorchedHat/KernelOPT.

## Democratizing Cross-Project Knowledge for Transforming Water Governance and Climate Resilience: an Agentic AI Ecosystem

DevFeed: [Democratizing Cross-Project Knowledge for Transforming Water Governance and Climate Resilience: an Agentic AI Ecosystem](<https://devfeed.tech/articles/democratizing-cross-project-knowledge-for-transforming-water-governance-and-climate-resilience-an-agentic-ai-ecosystem-145666.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.26398>)

Author: Oriol Al\\\`as, Ian Palac\\'in, Iv\\'an Cester, Edgar Rubi\\'on

Published: 2026-11-20T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Artificial Intelligence](<https://devfeed.tech/sources/arxiv-artificial-intelligence.md>)

Topics: [information retrieval](<https://devfeed.tech/topics/information-retrieval.md>), [Retrieval Augmented Generation (RAG)](<https://devfeed.tech/topics/retrieval-augmented-generation-rag.md>), [Agentic AI](<https://devfeed.tech/topics/what-is-agentic-ai.md>), [Enhancing AI model performance](<https://devfeed.tech/topics/enhancing-ai-model-performance.md>), [knowledge-engineering](<https://devfeed.tech/topics/knowledge-engineering.md>), [knowledge-management](<https://devfeed.tech/topics/knowledge-management.md>)

Tags: [adaptive](<https://devfeed.tech/tags/adaptive.md>), [agentic](<https://devfeed.tech/tags/agentic.md>), [agentic-ai](<https://devfeed.tech/tags/agentic-ai.md>), [agentic-retrieval](<https://devfeed.tech/tags/agentic-retrieval.md>), [ai](<https://devfeed.tech/tags/ai.md>), [benchmark](<https://devfeed.tech/tags/benchmark.md>), [budget](<https://devfeed.tech/tags/budget.md>), [climate](<https://devfeed.tech/tags/climate.md>), [collections](<https://devfeed.tech/tags/collections.md>), [controller](<https://devfeed.tech/tags/controller.md>), [cross](<https://devfeed.tech/tags/cross.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cs-cl](<https://devfeed.tech/tags/cs-cl.md>), [cs-ir](<https://devfeed.tech/tags/cs-ir.md>), [data](<https://devfeed.tech/tags/data.md>), [decision](<https://devfeed.tech/tags/decision.md>), [decision-making](<https://devfeed.tech/tags/decision-making.md>), [documentation](<https://devfeed.tech/tags/documentation.md>), [ecosystem](<https://devfeed.tech/tags/ecosystem.md>), [governance](<https://devfeed.tech/tags/governance.md>), [knowledge](<https://devfeed.tech/tags/knowledge.md>), [resilience](<https://devfeed.tech/tags/resilience.md>), [water](<https://devfeed.tech/tags/water.md>)

### AI overview

The paper presents an agentic retrieval system for finding evidence across EU-funded water and climate projects. It organizes documents from IMPETUS, NATALIE, and InnWater into hierarchical section trees with structured metadata, then uses separate water- and climate-domain embedding models. A ReAct-style controller allocates retrieval budget across domain collections and gathers evidence until a stopping criterion is met. In a benchmark on this corpus, the approach improved Mean Reciprocal Rank by 26.7% relative to a single-domain embedding baseline. The excerpt does not describe evaluation beyond that retrieval benchmark.

### Source excerpt

arXiv:2611.26398v1 Announce Type: cross Abstract: EU-funded projects produce extensive evidence in the form of deliverables, reports, and case studies. However, this knowledge is typically scattered across projects and document structures, making it difficult to locate relevant, contextual information when making decisions. This paper introduces an Agentic AI Ecosystem that consolidates heterogeneous project documentation into a domain-aware knowledge base and provides adaptive access through an agentic Retrieval-Augmented Generation pipeline. Documents from three EU-funded projects (IMPETUS, NATALIE, and InnWater) are reconstructed into hierarchical section trees and indexed with structured metadata. Retrieval is supported by two domain-specific embedding models fine-tuned on domain data (water and climate). On top of this knowledge base, a ReAct-style controller iteratively orchestrates retrieval actions by allocating retrieval budget across domain collections and accumulating evidence until a stopping criterion is met. In a retrieval benchmark over the corpus, the proposed approach improves Mean Reciprocal Rank by 26.7% (relative) compared to a single-domain embedding baseline, indicating more consistent retrieval of relevant evidence to support cross-project knowledge synthesis and climate-resilient decision-making.

## From "Weak" Signals to Strong Models: Preference Delta Aggregation with LoRA Merging

DevFeed: [From "Weak" Signals to Strong Models: Preference Delta Aggregation with LoRA Merging](<https://devfeed.tech/articles/from-weak-signals-to-strong-models-preference-delta-aggregation-with-lora-merging-145341.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2606.00357>)

Author: Qi Sun, Siyue Zhang, Yulin Chen, Yuxiang Xue, Ru Peng, Chen Zhao

Published: 2026-11-20T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Artificial Intelligence](<https://devfeed.tech/sources/arxiv-artificial-intelligence.md>)

Topics: [lora](<https://devfeed.tech/topics/lora.md>), [rlhf](<https://devfeed.tech/topics/rlhf.md>), [post-training](<https://devfeed.tech/topics/post-training.md>), [llm-reasoning](<https://devfeed.tech/topics/llm-reasoning.md>), [qwen](<https://devfeed.tech/topics/qwen.md>)

Tags: [adapter](<https://devfeed.tech/tags/adapter.md>), [adapters](<https://devfeed.tech/tags/adapters.md>), [agentic](<https://devfeed.tech/tags/agentic.md>), [aggregation](<https://devfeed.tech/tags/aggregation.md>), [alignment](<https://devfeed.tech/tags/alignment.md>), [capabilities](<https://devfeed.tech/tags/capabilities.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [data](<https://devfeed.tech/tags/data.md>), [delta](<https://devfeed.tech/tags/delta.md>), [evaluations](<https://devfeed.tech/tags/evaluations.md>), [knowledge](<https://devfeed.tech/tags/knowledge.md>), [language-models](<https://devfeed.tech/tags/language-models.md>), [large-language-models-llms](<https://devfeed.tech/tags/large-language-models-llms.md>), [llms](<https://devfeed.tech/tags/llms.md>), [lora](<https://devfeed.tech/tags/lora.md>), [models](<https://devfeed.tech/tags/models.md>), [optimization](<https://devfeed.tech/tags/optimization.md>), [pairs](<https://devfeed.tech/tags/pairs.md>), [pda](<https://devfeed.tech/tags/pda.md>), [qwen3](<https://devfeed.tech/tags/qwen3.md>), [reasoning](<https://devfeed.tech/tags/reasoning.md>)

### AI overview

Preference Delta Aggregation (PDA) turns preference comparisons between weaker models into separate LoRA adapters trained through preference optimization, then merges them to improve a stronger model. Its Geometric Alignment Merging (GAM) aligns the adapters' left and right singular bases with orthogonal Procrustes rotations before averaging their factors. In evaluations on knowledge reasoning and agentic search, PDA-GAM outperformed the strongest individual delta. Three reasoning deltas and four agentic deltas improved Qwen3-8B's average scores by 6.8 and 7.3 points, respectively--2.1 and 4.3 points above the strongest single-delta baselines. The abstract reports similar gains on a second student model and attributes the results to combining complementary capabilities.

### Source excerpt

arXiv:2606.00357v3 Announce Type: replace Abstract: Training strong large language models (LLMs) requires high-quality supervision, which is often scarce. Recent work shows that paired preference data from weak-weaker model pairs (e.g., Qwen3 4B over 1.7B), despite the limited quality of individual responses, can provide an effective supervision signal through relative quality deltas, which we term a "weak" signal. This motivates a key research question: can multiple "weak" signals be constructively aggregated for improving strong models (e.g., Qwen3 8B)? To this end, we propose Preference Delta Aggregation (PDA), the first framework that derives a preference delta from each weak-weaker model pair, instantiates it as a LoRA adapter learned through preference optimization, and aggregates the resulting deltas via LoRA merging. To improve the composition of independently trained adapters, we introduce Geometric Alignment Merging (GAM), which aligns their left and right singular bases through orthogonal Procrustes rotations and averages the aligned factors. Evaluations on knowledge reasoning and agentic search show that PDA-GAM exceeds the strongest individual delta, with further gains along the evaluated sequences of additional deltas. Using three reasoning deltas and four agentic deltas, PDA-GAM improves Qwen3-8B by 6.8 and 7.3 points on average, respectively, exceeding the strongest single-delta baseline by 2.1 and 4.3 points. These configurations achieve the highest average scores among the evaluated merging methods, with similar gains observed on a second student model. Further analysis suggests that these gains come from composing complementary capabilities encoded across distinct preference deltas. Code is available at https://github.com/AlbertQiSun/Preference-Delta-Aggregation.

## FPGA-GEN: Target-Aware RTL Generation via HLS

DevFeed: [FPGA-GEN: Target-Aware RTL Generation via HLS](<https://devfeed.tech/articles/fpga-gen-target-aware-rtl-generation-via-hls-145500.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.25351>)

Author: Luke Ztz Hu, Zhihan Xiao, Zhe Zhao, John Imoleayo Adebisi, Han Gao, Linxiao Yan, Songping Mai

Published: 2026-11-20T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Artificial Intelligence](<https://devfeed.tech/sources/arxiv-artificial-intelligence.md>)

Topics: [fpga](<https://devfeed.tech/topics/fpga.md>), [The Julia Language](<https://devfeed.tech/topics/julia.md>)

Tags: [admission](<https://devfeed.tech/tags/admission.md>), [agentic](<https://devfeed.tech/tags/agentic.md>), [bounded](<https://devfeed.tech/tags/bounded.md>), [conversion](<https://devfeed.tech/tags/conversion.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cs-ar](<https://devfeed.tech/tags/cs-ar.md>), [eval](<https://devfeed.tech/tags/eval.md>), [fpga](<https://devfeed.tech/tags/fpga.md>), [hls](<https://devfeed.tech/tags/hls.md>), [rtl](<https://devfeed.tech/tags/rtl.md>), [rtl-generation](<https://devfeed.tech/tags/rtl-generation.md>), [tensorcore](<https://devfeed.tech/tags/tensorcore.md>), [vivado](<https://devfeed.tech/tags/vivado.md>)

### AI overview

FPGA-GEN uses explicit task contracts and bounded tool-feedback loops to generate, select, repair, and admit HLS-C candidates, recognizing that successful C/C++ compilation alone does not establish correct or efficient FPGA hardware. On HLS-Eval, five outputs per task passed 407 of 425 public-testbench cases (95.8%). In a cumulative conversion campaign, 104 of 107 HLS-LeVeri designs were admitted based on held-out co-simulation, Vivado synthesis and fit, and same-RTL evidence. In focused TensorCore screening, selected candidate 3 reported 73.7% fewer CSynth cycles and 14.6% fewer LUTs than generated/composed C0, but used 26.7% more DSPs; it passed development CoSim.

### Source excerpt

arXiv:2611.25351v1 Announce Type: cross Abstract: Successful C/C++ compilation does not guarantee correct or efficient FPGA hardware after high-level synthesis (HLS). FPGA-GEN is an agentic HLS-C generation workflow that encodes specification, readiness, selection, repair, and admission rules in explicit task contracts and bounded tool-feedback loops for candidate-level decisions. On HLS-Eval, five shared-context outputs per task yield 407/425 (95.8%) public-testbench passes. In a cumulative conversion campaign, FPGA-GEN admits 104/107 (97.2%) HLS-LeVeri designs under held-out co-simulation, Vivado synthesis/fit, and same-RTL evidence. In focused TensorCore screening, selected candidate 3 reports 73.7% fewer CSynth cycles and 14.6% fewer LUTs than generated/composed C0, with 26.7% more DSPs, and passes development CoSim.

## Agent^2 RL-Bench: Can LLM Agents Engineer Agentic RL Post-Training?

DevFeed: [Agent^2 RL-Bench: Can LLM Agents Engineer Agentic RL Post-Training?](<https://devfeed.tech/articles/agent-2-rl-bench-can-llm-agents-engineer-agentic-rl-post-training-145322.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2604.10547>)

Author: Wanyi Chen, Xiao Yang, Xu Yang, Tianming Sha, Qizheng Li, Zhuo Wang, Bowen Xian, Fang Kong, Weiqing Liu, Jiang Bian

Published: 2026-11-20T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Artificial Intelligence](<https://devfeed.tech/sources/arxiv-artificial-intelligence.md>)

Topics: [post-training](<https://devfeed.tech/topics/post-training.md>), [grpo](<https://devfeed.tech/topics/grpo.md>), [Large Language Model](<https://devfeed.tech/topics/llm.md>), [AI Agent](<https://devfeed.tech/topics/ai-agent.md>), [llm-reasoning](<https://devfeed.tech/topics/llm-reasoning.md>)

Tags: [abstract](<https://devfeed.tech/tags/abstract.md>), [agent](<https://devfeed.tech/tags/agent.md>), [agent-behavior](<https://devfeed.tech/tags/agent-behavior.md>), [agentic](<https://devfeed.tech/tags/agentic.md>), [agents](<https://devfeed.tech/tags/agents.md>), [alignment](<https://devfeed.tech/tags/alignment.md>), [api](<https://devfeed.tech/tags/api.md>), [artifacts](<https://devfeed.tech/tags/artifacts.md>), [benchmark](<https://devfeed.tech/tags/benchmark.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [debug](<https://devfeed.tech/tags/debug.md>), [diagnostic](<https://devfeed.tech/tags/diagnostic.md>), [evaluation](<https://devfeed.tech/tags/evaluation.md>), [fine-tuning](<https://devfeed.tech/tags/fine-tuning.md>), [fixed](<https://devfeed.tech/tags/fixed.md>), [foundation](<https://devfeed.tech/tags/foundation.md>), [framework](<https://devfeed.tech/tags/framework.md>), [grpo](<https://devfeed.tech/tags/grpo.md>), [post-training](<https://devfeed.tech/tags/post-training.md>), [rl](<https://devfeed.tech/tags/rl.md>), [training](<https://devfeed.tech/tags/training.md>)

### AI overview

Agent^2 RL-Bench evaluates whether LLM agents can build and run post-training pipelines that improve a model through repeated training and artifact submission under a fixed budget. Its six tasks cover static rule-based training, judge-based optimization, and online RL with trajectory collection; runtime recording and post-hoc summaries support analysis of agent behavior. Across five agent systems and six driver LLMs, one RL-oriented run raised ALFWorld from 4.85 to 93.28 using an SFT warm-up followed by GRPO with online rollouts. DeepSearchQA remained difficult, most successful approaches relied on supervised pipelines, and interactive results varied substantially across agent stacks. The abstract concludes that agents can sometimes engineer online RL, while stable agent-driven RL post-training remains rare under fixed budgets.

### Source excerpt

arXiv:2604.10547v3 Announce Type: replace Abstract: We introduce Agent^2 RL-Bench, a compact diagnostic benchmark for evaluating agentic RL post-training, which tests whether LLM agents can autonomously design, implement, debug, and execute post-training pipelines that improve foundation models. RL post-training increasingly drives model alignment and specialization, yet existing benchmarks are largely static, rewarding supervised fine-tuning or script generation without assessing an agent's ability to close an interactive RL loop. Agent^2 RL-Bench provides a unified agent-facing interface: each run starts from an isolated workspace containing a base model, task data, instructions, and a grading API, and agents must iterate within a fixed budget by training models and submitting artifacts for evaluation. The benchmark spans six tasks across three levels, from static rule-based training to judge-based optimization and closed-loop online RL with trajectory collection. Two diagnostic skills, namely runtime recording and post-hoc summarization, enable structured analysis of agent behavior, facilitating smooth and effective iteration of the benchmark's evaluation framework. Across five agent systems and six driver LLMs, agents show intelligent behavior but clear limitations: one RL-oriented run improves ALFWorld from 4.85 to 93.28 via SFT warm-up and GRPO with online rollouts, yet DeepSearchQA remains difficult, most successful routes rely on supervised pipelines, and interactive outcomes show large differences across agent stacks. Overall, Agent2 RL-Bench shows that current agents can sometimes engineer online RL, but stable agent-driven RL post-training remains rare under fixed budgets. It also demonstrates that our benchmark provides a strong and effective evaluation framework for future research in this direction. Code is available at https://github.com/microsoft/RD-Agent.

## Provable Authority: A Protocol for Verifiable Authority Resolution and Control Across Human, Organizational, and Agentic Transactions

DevFeed: [Provable Authority: A Protocol for Verifiable Authority Resolution and Control Across Human, Organizational, and Agentic Transactions](<https://devfeed.tech/articles/provable-authority-a-protocol-for-verifiable-authority-resolution-and-control-across-human-organizational-and-agentic-transactions-146009.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2610.22899>)

Author: Jeremy Blackburn, Tim Hines, Matthew Koepp, Russell Lessard, Jason Patrick

Published: 2026-11-20T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Cryptography and Security](<https://devfeed.tech/sources/arxiv-cryptography-and-security.md>)

Topics: [Agentic AI](<https://devfeed.tech/topics/what-is-agentic-ai.md>), [Distributed Systems & Parallel Computing](<https://devfeed.tech/topics/distributed-systems-parallel-computing.md>), [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [control-plane](<https://devfeed.tech/topics/control-plane.md>)

Tags: [ach](<https://devfeed.tech/tags/ach.md>), [adapter](<https://devfeed.tech/tags/adapter.md>), [agent](<https://devfeed.tech/tags/agent.md>), [agent-runtime](<https://devfeed.tech/tags/agent-runtime.md>), [agentic](<https://devfeed.tech/tags/agentic.md>), [agentic-commerce](<https://devfeed.tech/tags/agentic-commerce.md>), [agentic-transactions](<https://devfeed.tech/tags/agentic-transactions.md>), [ai](<https://devfeed.tech/tags/ai.md>), [arxiv](<https://devfeed.tech/tags/arxiv.md>), [assertions](<https://devfeed.tech/tags/assertions.md>), [authorization](<https://devfeed.tech/tags/authorization.md>), [autonomous](<https://devfeed.tech/tags/autonomous.md>), [boundary](<https://devfeed.tech/tags/boundary.md>), [bounded](<https://devfeed.tech/tags/bounded.md>), [budget](<https://devfeed.tech/tags/budget.md>), [canonical](<https://devfeed.tech/tags/canonical.md>), [control](<https://devfeed.tech/tags/control.md>), [cs-cr](<https://devfeed.tech/tags/cs-cr.md>), [cs-ma](<https://devfeed.tech/tags/cs-ma.md>), [organizational](<https://devfeed.tech/tags/organizational.md>), [protocol](<https://devfeed.tech/tags/protocol.md>), [transactions](<https://devfeed.tech/tags/transactions.md>)

### AI overview

The ChainIT Authority Protocol proposes a pre-execution control plane to let relying parties verify that a person, organization, or AI agent is authorized for the exact transaction being submitted. It keeps identity, versioned organizational authority, evidence, policy checks, and configured dispositions distinct; binds decisions and human approvals to a canonical transaction digest; reserves capacity atomically; and gates commit on a single-use, sender-constrained credential consumed at the rail adapter. For AI agents, an Agent Subject Profile adds workload registration, attested keys, and a sovereignty boundary. The abstract says it specifies bounded-freshness status rules and enforcement profiles for fiat and stablecoin rails, while also identifying residual risks and non-goals.

### Source excerpt

arXiv:2610.22899v2 Announce Type: replace Abstract: Payment systems authenticate users, devices, accounts, and cryptographic credentials, but a relying party, such as a counterparty, payment rail, marketplace, or autonomous agent runtime, generally cannot obtain compact, independently verifiable evidence that the party presenting one exact transaction holds current organizational authority to execute it under the applicable evidence, policy, budget, and approval state. Agentic commerce makes this gap operationally urgent: a software agent can produce a valid signature while acting outside its delegated purpose, after its sponsor's authority has changed, or on transaction details that differ from those a human approved. We describe the ChainIT Authority Protocol, a subject-neutral and rail-neutral pre-execution authority and evidence control plane. The protocol separates durable identity, a versioned organizational authority record (the Authority Resolution Pactvera), sourced evidence assertions, deterministic reason-coded policy predicates, and organization-configured dispositions; binds each decision and human approval to a canonical transaction digest; reserves capacity atomically so that limits hold under concurrency; and authorizes commit only through a single-use, sender-constrained Execution Authorization Credential consumed at the rail adapter, with append-only lifecycle evidence sealed after the terminal outcome. An Agent Subject Profile adds the workload registration, attested key hierarchy, and sovereignty boundary required when the acting subject is an AI agent, without introducing a separate authority concept. We specify the commit-time execution predicate and bounded-freshness status rules, give enforcement profiles for fiat (ACH, wire, card, instant payment) and stablecoin rails, and state residual risks and non-goals.

## LingSante MedGuard Technical Report

DevFeed: [LingSante MedGuard Technical Report](<https://devfeed.tech/articles/lingsante-medguard-technical-report-146034.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.25509>)

Author: LingSante MedGuard Team

Published: 2026-11-20T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Cryptography and Security](<https://devfeed.tech/sources/arxiv-cryptography-and-security.md>)

Topics: [ai safety](<https://devfeed.tech/topics/ai-safety.md>), [Fine-tuning](<https://devfeed.tech/topics/fine-tuning.md>)

Tags: [abstract](<https://devfeed.tech/tags/abstract.md>), [agentic](<https://devfeed.tech/tags/agentic.md>), [ai](<https://devfeed.tech/tags/ai.md>), [benchmark](<https://devfeed.tech/tags/benchmark.md>), [clinical-decision-support](<https://devfeed.tech/tags/clinical-decision-support.md>), [compliance](<https://devfeed.tech/tags/compliance.md>), [consistency](<https://devfeed.tech/tags/consistency.md>), [cs-cr](<https://devfeed.tech/tags/cs-cr.md>), [distillation](<https://devfeed.tech/tags/distillation.md>), [ethics](<https://devfeed.tech/tags/ethics.md>), [f1](<https://devfeed.tech/tags/f1.md>), [fine-tuning](<https://devfeed.tech/tags/fine-tuning.md>), [guardrail](<https://devfeed.tech/tags/guardrail.md>), [hallucination-detection](<https://devfeed.tech/tags/hallucination-detection.md>), [medical](<https://devfeed.tech/tags/medical.md>), [medical-ai](<https://devfeed.tech/tags/medical-ai.md>), [multimodal](<https://devfeed.tech/tags/multimodal.md>), [risk-assessment](<https://devfeed.tech/tags/risk-assessment.md>), [technical](<https://devfeed.tech/tags/technical.md>), [traceability](<https://devfeed.tech/tags/traceability.md>)

### AI overview

LingSante MedGuard combines a medical guardrail teacher with six specialized capability experts in one model to assess medical safety, compliance, and ethics. Training uses supervised fine-tuning on teacher-generated demonstrations, then multi-teacher on-policy distillation from feedback on student responses. Its MedGuardBench covers 11 risk-detection subsets; mean F1 scores are 82.3%, 82.4%, and 87.4% for 4B, 9B, and 27B models. The 4B model reaches 73.9% mean accuracy on MedHallu and MedHALT-NOTA with retrieval enabled. The abstract also reports gains in evidence-supported consistency, source traceability, and rule-guided rationale quality, without specifying their magnitude.

### Source excerpt

arXiv:2611.25509v1 Announce Type: new Abstract: As medical AI is increasingly used for patient consultation and clinical decision support, identifying harmful, non-compliant, or ethically problematic responses is essential for responsible deployment. Assessing these risks requires checking clinical claims against relevant evidence, verifying calculations, and applying medical requirements under their intended conditions. We introduce LingSante MedGuard, a capability-enhanced guardrail that integrates supervision from a medical guardrail teacher model and six specialized medical capability experts into a unified model. The guardrail teacher supervises risk decisions and explanations across medical safety, compliance, and ethics, while the capability experts support medical rule understanding, numerical reasoning, multimodal hallucination detection, agentic safety verification, risk localization, and multimodal entity understanding. We consolidate these sources of supervision through offline supervised fine-tuning on teacher-generated demonstrations, followed by multi-teacher on-policy distillation using feedback on student-generated responses. We further introduce LingSante MedGuardBench, a benchmark comprising 11 risk-detection subsets spanning medical safety, compliance, and ethics. At 4B, 9B, and 27B scales, LingSante MedGuard achieves mean benchmark F1 scores of 82.3%, 82.4%, and 87.4%, respectively. The 4B model also achieves 73.9% mean accuracy across MedHallu and MedHALT-NOTA under retrieval-enabled evaluation. Additional evaluations of the verification components show improvements in evidence-supported consistency, source traceability, and rule-guided rationale quality across model scales. These results support the integration of specialized medical capabilities into a unified guardrail for medical risk assessment and evidence-based medical safety verification.

## TriAxialKV: Toward Extreme Low-Precision KV-Cache Quantization for Agentic Inference Tasks

DevFeed: [TriAxialKV: Toward Extreme Low-Precision KV-Cache Quantization for Agentic Inference Tasks](<https://devfeed.tech/articles/triaxialkv-toward-extreme-low-precision-kv-cache-quantization-for-agentic-inference-tasks-144895.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2605.17170>)

Author: Hanzhang Shen, Haoran Wu, Yiren Zhao, Robert Mullins

Published: 2026-11-20T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Machine Learning](<https://devfeed.tech/sources/arxiv-machine-learning.md>)

Topics: [quantization](<https://devfeed.tech/topics/quantization.md>), [LLM optimization](<https://devfeed.tech/topics/llm-optimization.md>), [AI Infrastructure](<https://devfeed.tech/topics/ai-infrastructure.md>), [Large Language Model](<https://devfeed.tech/topics/llm.md>), [Machine learning](<https://devfeed.tech/topics/machine-learning.md>), [Cache](<https://devfeed.tech/topics/cache.md>), [Transformers](<https://devfeed.tech/topics/transformers.md>)

Tags: [agentic](<https://devfeed.tech/tags/agentic.md>), [agentic-workloads](<https://devfeed.tech/tags/agentic-workloads.md>), [bf16](<https://devfeed.tech/tags/bf16.md>), [budget](<https://devfeed.tech/tags/budget.md>), [cache](<https://devfeed.tech/tags/cache.md>), [capacity](<https://devfeed.tech/tags/capacity.md>), [chat](<https://devfeed.tech/tags/chat.md>), [compression](<https://devfeed.tech/tags/compression.md>), [computer](<https://devfeed.tech/tags/computer.md>), [computer-use](<https://devfeed.tech/tags/computer-use.md>), [context](<https://devfeed.tech/tags/context.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [custom](<https://devfeed.tech/tags/custom.md>), [decode](<https://devfeed.tech/tags/decode.md>), [gpu](<https://devfeed.tech/tags/gpu.md>), [image](<https://devfeed.tech/tags/image.md>), [implement](<https://devfeed.tech/tags/implement.md>), [inference](<https://devfeed.tech/tags/inference.md>), [kv-cache](<https://devfeed.tech/tags/kv-cache.md>), [precision](<https://devfeed.tech/tags/precision.md>), [quantization](<https://devfeed.tech/tags/quantization.md>)

### AI overview

TriAxialKV reduces KV-cache memory for agentic inference by tagging tokens across recency, modality, and semantic role, calibrating sensitivity for each tag, and assigning INT2 or INT4 precision within a fixed memory budget. Its serving system combines calibration, quantization and memory management, and fused Triton decode kernels. In the reported OSWorld computer-use evaluation with Qwen3-VL-32B-Thinking, it matched SGLang's accuracy using a BF16 cache while supporting 4.5x KV-cache capacity and 30% higher end-to-end throughput on real GPUs.

### Source excerpt

arXiv:2605.17170v2 Announce Type: replace Abstract: Agentic workloads have emerged as a major workload for LLM inference. They differ significantly from chat-only workloads, requiring long-context processing, the ability to handle multimodal inputs, and structured multi-turn interactions with tool calling capabilities. As a result, their context exhibits structure that can carry different importance along three key axes: temporal recency to the current turn, modality such as text or image tokens, and semantic role such as user queries, tool calls, observations, or reasoning. These axes capture distinct token behaviors and lead to different sensitivities to KV-cache compression. However, existing KV-cache quantization methods are typically homogeneous or exploit only heterogeneity on a single dimension, such as temporal proximity or modality, overlooking the interactions among them. To this end, we introduce TriAxialKV, a novel mixed-precision KV-cache quantization scheme that assigns each token a triaxial tag, calibrates per-tag sensitivity, and allocates INT2/INT4 bit-widths under a fixed memory budget. We implement TriAxialKV as an end-to-end serving system, comprising calibration, mixed-precision quantization and memory management, and custom fused Triton decode kernels. When using Qwen3-VL-32B-Thinking as a computer-use agent operating the OSWorld, TriAxialKV matches the accuracy of SGLang with BF16 KV cache while supporting 4.5$\times$ KV cache capacity and achieving 30% higher end-to-end throughput, when running on real GPU systems.

## Towards Embodied Air-Ground Cooperative Object Search: Benchmark, Dataset and Agentic Method

DevFeed: [Towards Embodied Air-Ground Cooperative Object Search: Benchmark, Dataset and Agentic Method](<https://devfeed.tech/articles/towards-embodied-air-ground-cooperative-object-search-benchmark-dataset-and-agentic-method-145369.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2609.08402>)

Author: Boao Yu, Zimo Chen, Junreng Rao, Yue Hu, Zhengqiu Zhu, Yong Zhao, Rusheng Ju

Published: 2026-11-20T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Artificial Intelligence](<https://devfeed.tech/sources/arxiv-artificial-intelligence.md>)

Topics: [Machine Perception](<https://devfeed.tech/topics/machine-perception.md>), [Multi-step AI processes](<https://devfeed.tech/topics/multi-step-ai-processes.md>), [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [Image](<https://devfeed.tech/topics/image.md>)

Tags: [agent](<https://devfeed.tech/tags/agent.md>), [agentic](<https://devfeed.tech/tags/agentic.md>), [air](<https://devfeed.tech/tags/air.md>), [approach](<https://devfeed.tech/tags/approach.md>), [automatic](<https://devfeed.tech/tags/automatic.md>), [benchmark](<https://devfeed.tech/tags/benchmark.md>), [benchmark-dataset](<https://devfeed.tech/tags/benchmark-dataset.md>), [computer-science](<https://devfeed.tech/tags/computer-science.md>), [computer-vision](<https://devfeed.tech/tags/computer-vision.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cs-cv](<https://devfeed.tech/tags/cs-cv.md>), [dataset](<https://devfeed.tech/tags/dataset.md>), [decision-making](<https://devfeed.tech/tags/decision-making.md>), [experiments](<https://devfeed.tech/tags/experiments.md>), [first](<https://devfeed.tech/tags/first.md>), [gemini](<https://devfeed.tech/tags/gemini.md>), [gemini-3-6-flash](<https://devfeed.tech/tags/gemini-3-6-flash.md>), [object](<https://devfeed.tech/tags/object.md>), [search](<https://devfeed.tech/tags/search.md>), [vision-language-models-vlms](<https://devfeed.tech/tags/vision-language-models-vlms.md>), [vlms](<https://devfeed.tech/tags/vlms.md>)

### AI overview

The paper introduces AGOS, an urban search task where UAVs find a target vehicle from multi-view references and UGVs verify it at ground level. AGOS-Bench evaluates whether general-purpose vision-language models can coordinate those roles; its companion AGOS-Dataset contains 7.7k automatically constructed episodes across three difficulty levels. The proposed training-free, tool-augmented AGOS-Agent uses a search-handoff-verify protocol, leaving scene understanding and decision-making to the VLMs. Across nine evaluated models, it improves overall success rate for eight and reduces decision steps for all nine. On the hard split, Gemini-3.6-Flash's success rate rises from 8.6% to 55.7%, and its SPL from 7.6% to 44.0%.

### Source excerpt

arXiv:2609.08402v2 Announce Type: replace-cross Abstract: Air-Ground Object Search (AGOS) in urban environments is a challenging embodied task, which requires an Unmanned Aerial Vehicle (UAV) and an Unmanned Ground Vehicle (UGV) to jointly search for and verify a specified target vehicle from multi-view visual references. To study this underexplored problem, we introduce AGOS-Bench, the first dedicated benchmark for evaluating whether general-purpose Vision-Language Models (VLMs) can integrate aerial discoveries and ground-level verification through UAV-UGV cooperation. We further provide AGOS-Dataset as the companion resource of exemplary trajectories constructed by an automatic pipeline. It consists of 7.7k episodes for searching objects of diverse categories and attributes, spanning three difficulty levels. To address the AGOS task, we propose AGOS-Agent, a training-free and tool-augmented approach. The agentic method relieves VLMs from complex and dynamic coordination via a deliberate search-handoff-verify cooperation protocol, only demanding VLMs for scene understanding and decision-making. Extensive experiments on nine VLMs show that AGOS-Agent improves overall success rate for eight of the nine evaluated backbones while reducing decision steps for all nine. On the hard split, the SR and SPL of Gemini-3.6-Flash increase from 8.6% to 55.7% and from 7.6% to 44.0%, respectively.

[Next page](<https://devfeed.tech/tags/agentic.md?cursor=WyIyMDI2LTExLTIwVDA1OjAwOjAwKzAwOjAwIiwgIjg1MjQ4YjIyLWY2NDItNDkwOS1iNGRmLTExMTE5NjQwOGEzZiJd>)