# Multi Agent Systems

Multi-agent systems are collections of autonomous AI agents that coordinate and collaborate through shared communication, tools, and protocols to perform complex tasks and achieve collective goals.

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

## Europe's Supermarket Cyberattacks Expose a Bigger Problem With Connected Infrastructure

DevFeed: [Europe's Supermarket Cyberattacks Expose a Bigger Problem With Connected Infrastructure](<https://devfeed.tech/articles/europe-s-supermarket-cyberattacks-expose-a-bigger-problem-with-connected-infrastructure-146453.md>)

Original publisher: [Read original article](<https://hackernoon.com/europes-supermarket-cyberattacks-expose-a-bigger-problem-with-connected-infrastructure?source=rss>)

Author: Fabrizio Marozzo

Published: 2026-11-20T14:27:57Z

Content type: article

Language: en

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

Topics: [Cybersecurity](<https://devfeed.tech/topics/cybersecurity.md>), [ai-assisted attacks](<https://devfeed.tech/topics/ai-assisted-attacks.md>), [Multi Agent Systems](<https://devfeed.tech/topics/multi-agent-systems.md>), [Agentic AI](<https://devfeed.tech/topics/what-is-agentic-ai.md>), [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [Legacy Modernization](<https://devfeed.tech/topics/legacy-modernization.md>), [Network](<https://devfeed.tech/topics/network.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [ai-agent-swarms](<https://devfeed.tech/tags/ai-agent-swarms.md>), [ai-cybersecurity](<https://devfeed.tech/tags/ai-cybersecurity.md>), [ai-systems](<https://devfeed.tech/tags/ai-systems.md>), [artificial-intelligence](<https://devfeed.tech/tags/artificial-intelligence.md>), [attacks](<https://devfeed.tech/tags/attacks.md>), [autonomous](<https://devfeed.tech/tags/autonomous.md>), [connectivity](<https://devfeed.tech/tags/connectivity.md>), [controls](<https://devfeed.tech/tags/controls.md>), [critical-infrastructure](<https://devfeed.tech/tags/critical-infrastructure.md>), [cyberattacks](<https://devfeed.tech/tags/cyberattacks.md>), [cybersecurity](<https://devfeed.tech/tags/cybersecurity.md>), [euro-supermarket-cyberattacks](<https://devfeed.tech/tags/euro-supermarket-cyberattacks.md>), [europe](<https://devfeed.tech/tags/europe.md>), [hackernoon-top-story](<https://devfeed.tech/tags/hackernoon-top-story.md>), [industrial-cybersecurity](<https://devfeed.tech/tags/industrial-cybersecurity.md>), [infrastructure](<https://devfeed.tech/tags/infrastructure.md>), [iot-security](<https://devfeed.tech/tags/iot-security.md>), [network-security](<https://devfeed.tech/tags/network-security.md>), [offensive-vs-defensive-ai](<https://devfeed.tech/tags/offensive-vs-defensive-ai.md>), [outdated](<https://devfeed.tech/tags/outdated.md>), [supermarket](<https://devfeed.tech/tags/supermarket.md>), [systems](<https://devfeed.tech/tags/systems.md>)

### AI overview

Cyberattacks manipulated supermarket refrigeration controls, extending defrost cycles and causing food losses, including reported cold-room or freezer temperatures of 50°C. The text says these incidents expose risks from remotely accessible equipment, outdated software, unchanged default passwords, and devices no longer supported by manufacturers; it notes there is no evidence AI agents were involved. It describes a Corma experiment in a controlled enterprise network: attackers established reboot-surviving backdoors in 85% of engagements, while defenders identified planted artifacts in 22% of cases with verified backdoors. The figures measure different outcomes in one setup, not a universal performance gap. Defense is difficult because legitimate and malicious actions can look alike, false alarms can disrupt essential services, and detection depends on available signals. Suggested resilience measures include updating systems, segmenting networks, avoiding unnecessary internet connections, and keeping practical alternatives and emergency supplies for service disruptions.

### Source excerpt

As AI agent swarms grow more powerful, outdated and interconnected systems expose a widening cybersecurity gap between attackers and defenders.

## An insider's look at SAP's 'Autonomous Enterprise'

DevFeed: [An insider's look at SAP's 'Autonomous Enterprise'](<https://devfeed.tech/articles/an-insider-s-look-at-sap-s-autonomous-enterprise-146154.md>)

Original publisher: [Read original article](<https://www.cio.com/article/4249833/sap-caio-we-need-to-be-more-precise-in-managing-the-use-of-ai.html>)

Author: Manfred Bremmer

Published: 2026-11-20T10:01:00Z

Content type: news

Language: en

Sources: [CIO](<https://devfeed.tech/sources/cio.md>)

Topics: [Agentic AI](<https://devfeed.tech/topics/what-is-agentic-ai.md>), [agentic workflows](<https://devfeed.tech/topics/agentic-workflows.md>), [Multi Agent Systems](<https://devfeed.tech/topics/multi-agent-systems.md>), [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [ai-agents](<https://devfeed.tech/tags/ai-agents.md>), [ai-platform](<https://devfeed.tech/tags/ai-platform.md>), [artificial-intelligence](<https://devfeed.tech/tags/artificial-intelligence.md>), [artificial-intelligence-enterprise-applications-erp-systems-sap-vendors-and-providers](<https://devfeed.tech/tags/artificial-intelligence-enterprise-applications-erp-systems-sap-vendors-and-providers.md>), [autonomous-enterprise](<https://devfeed.tech/tags/autonomous-enterprise.md>), [edition-us](<https://devfeed.tech/tags/edition-us.md>), [enterprise-applications](<https://devfeed.tech/tags/enterprise-applications.md>), [erp-systems](<https://devfeed.tech/tags/erp-systems.md>), [joule](<https://devfeed.tech/tags/joule.md>), [joule-work](<https://devfeed.tech/tags/joule-work.md>), [language-en](<https://devfeed.tech/tags/language-en.md>), [sap](<https://devfeed.tech/tags/sap.md>), [storytype-interview](<https://devfeed.tech/tags/storytype-interview.md>), [vendors-and-providers](<https://devfeed.tech/tags/vendors-and-providers.md>)

### AI overview

SAP's agent governance approach combines use case and consumption estimates with per-user or departmental budgets, visible daily usage limits, and optional analysis of agent outcomes. Joule Work offers model modes and model selection for custom agents; SAP is testing automatic routing, while noting that choosing models for transactional tasks is more complex. Joule Studio access is assigned by IT, with role-based sharing, version control, review status, and company-specific approvals. Monitoring, generated tests, agent mining, and process mining feed findings into iterative improvement. SAP says it still needs to link AI consumption more directly to business value, and cross-provider governance remains difficult without a common standard. The interview also says clear, rule-based tasks may be cheaper and faster with classic workflows, while hybrid workflows can reserve agents for steps needing additional intelligence.

### Source excerpt

At the TechEd developer conference in Berlin, SAP presented additional details of its "Autonomous Enterprise" concept, which includes AI capabilities via Joule Work and SAP Autonomous Suite, built on the SAP Business AI Platform. The company's focus is not just AI, but AI agents capable of acting automatically within the SAP system by performing analyses and answering queries. This raises questions, such as: How can the costs of AI agents be controlled? Who is allowed to develop the agents, and how can companies maintain oversight? Jonathan von Rüden, chief AI officer of SAP, explains in an interview with Computerwoche how the software provider is addressing these questions -- and where work still needs to be done. Computerwoche: Companies are increasingly using AI and developing more and more AI agents. But it is often difficult to predict how costs in this area will develop over time. How is SAP addressing this? Jonathan von Rüden: We generally proceed in three steps. First, we clarify together with the customer or in product management which use cases are relevant and what should be achieved with them. We distinguish between different areas of focus. First, there's general productivity: transcriptions, summaries, presentations, or information research. This now extends far beyond classic office tasks. For example, information from the internet can be combined with SAP data and used for financial analysis. However, this area is difficult to define precisely because it encompasses so many tasks in everyday work. In addition, there are dedicated AI agents that are centrally deployed and managed by IT. These can be standard agents from SAP or customer-specific agents from Joule Studio. Finally, there are use cases where companies can differentiate themselves significantly. Here, they should consider whether they can develop their own solution. Based on this information, we estimate consumption. To do this, we consider factors such as the number of employees, how frequ

## Best Enterprise AI Agent Platforms in 2026

DevFeed: [Best Enterprise AI Agent Platforms in 2026](<https://devfeed.tech/articles/best-enterprise-ai-agent-platforms-in-2026-146951.md>)

Original publisher: [Read original article](<https://www.swytchcode.com/content/best-enterprise-ai-agent-platforms>)

Author: Swytchcode Team

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

Content type: comparison

Language: en

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

Topics: [AI Agent](<https://devfeed.tech/topics/ai-agent.md>), [agent orchestration](<https://devfeed.tech/topics/agent-orchestration.md>), [Multi Agent Systems](<https://devfeed.tech/topics/multi-agent-systems.md>), [agent observability](<https://devfeed.tech/topics/agent-observability.md>)

Tags: [2026](<https://devfeed.tech/tags/2026.md>), [agent](<https://devfeed.tech/tags/agent.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>), [best](<https://devfeed.tech/tags/best.md>), [enterprise](<https://devfeed.tech/tags/enterprise.md>), [enterprise-ai](<https://devfeed.tech/tags/enterprise-ai.md>), [frameworks](<https://devfeed.tech/tags/frameworks.md>), [platforms](<https://devfeed.tech/tags/platforms.md>), [runtimes](<https://devfeed.tech/tags/runtimes.md>)

### AI overview

The article argues that enterprise AI agent platforms serve different stages, so a single ranking obscures their roles. LangGraph, CrewAI and OpenAI Agents SDK handle agent reasoning; Composio, Arcade, Pipedream and Zapier MCP make tools reachable, with differences in OAuth, deployment, pricing and production access. Workato is positioned for mostly deterministic integration flows. The article describes Swytchcode as a production runtime that governs calls after an agent chooses them: it checks schemas and policies, injects credentials at execution, validates responses, audits calls, and retries POST/PATCH only when an idempotency key is set. It says catalogs' public docs do not describe write idempotency as of November 2026. Swytchcode is presented for costly or sensitive writes, but it lacks a hosted branded OAuth connection flow for large numbers of end users; the article suggests pairing it with a catalog when both needs apply. The text is a vendor-authored comparison that includes Swytchcode among the nine platforms.

### Source excerpt

We score the real enterprise AI agent platforms (frameworks, catalogs, iPaaS, runtimes) against the seven stages where agent builds actually break.

## Best Agent Frameworks for Production Use

DevFeed: [Best Agent Frameworks for Production Use](<https://devfeed.tech/articles/best-agent-frameworks-for-production-use-146945.md>)

Original publisher: [Read original article](<https://www.swytchcode.com/content/best-agent-frameworks-production>)

Author: Swytchcode Team

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

Content type: comparison

Language: en

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

Topics: [Microsoft Agent Framework](<https://devfeed.tech/topics/microsoft-agent-framework.md>), [Multi Agent Systems](<https://devfeed.tech/topics/multi-agent-systems.md>), [Agent Harness](<https://devfeed.tech/topics/agent-harness.md>), [ai-governance](<https://devfeed.tech/topics/ai-governance.md>), [audit](<https://devfeed.tech/topics/audit.md>), [agent observability](<https://devfeed.tech/topics/agent-observability.md>), [Production Engineering](<https://devfeed.tech/topics/production-engineering.md>), [SDK](<https://devfeed.tech/topics/sdk.md>), [llm-reasoning](<https://devfeed.tech/topics/llm-reasoning.md>)

Tags: [2026](<https://devfeed.tech/tags/2026.md>), [agent-frameworks](<https://devfeed.tech/tags/agent-frameworks.md>), [ai-agents](<https://devfeed.tech/tags/ai-agents.md>), [audit](<https://devfeed.tech/tags/audit.md>), [best](<https://devfeed.tech/tags/best.md>), [permissions](<https://devfeed.tech/tags/permissions.md>), [production](<https://devfeed.tech/tags/production.md>), [retries](<https://devfeed.tech/tags/retries.md>)

### AI overview

The excerpt's central finding is that agent frameworks manage reasoning and tool orchestration, while API execution controls such as credentials, policy checks, idempotent retries, and independent audit generally require another layer. LangGraph is suited to branching, stateful workflows with checkpointing and human review; OpenAI Agents SDK offers native handoffs and scoped guardrails, with gaps around handoffs, hosted tools, retries, and audit; Claude Agent SDK's local tool approvals fit supervised coding and internal tools. CrewAI adds runtime controls and credential hygiene, while Vercel AI SDK offers provider and runtime flexibility but leaves credentials, sandboxing, approvals, and idempotency to the caller. Microsoft Agent Framework provides broad orchestration, with governance positioned in Azure AI Foundry. Temporal adds durable state and retries after failures, but does not decide whether a call is authorized. The excerpt describes a separate execution layer as handling allowlists, live schema validation, policy, credential injection, safe retries, response checks, and audit.

### Source excerpt

We rank six agent frameworks used in production as of November 2026 and show why none of them handle API permissions, retries, or audit by design.

## How AI Agents Could Change Workplace Communication Forever

DevFeed: [How AI Agents Could Change Workplace Communication Forever](<https://devfeed.tech/articles/how-ai-agents-could-change-workplace-communication-forever-146214.md>)

Original publisher: [Read original article](<https://hackernoon.com/how-ai-agents-could-change-workplace-communication-forever?source=rss>)

Author: Isaac Correa

Published: 2026-11-20T06:00:07Z

Content type: opinion

Language: en

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

Topics: [agent to agent communication](<https://devfeed.tech/topics/agent-to-agent-communication.md>), [Multi Agent Systems](<https://devfeed.tech/topics/multi-agent-systems.md>), [human in the loop agent](<https://devfeed.tech/topics/human-in-the-loop-agent.md>)

Tags: [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-agents](<https://devfeed.tech/tags/ai-agents.md>), [ai-in-the-workplace](<https://devfeed.tech/tags/ai-in-the-workplace.md>), [autonomous-ai-agents](<https://devfeed.tech/tags/autonomous-ai-agents.md>), [business-communication](<https://devfeed.tech/tags/business-communication.md>), [communication](<https://devfeed.tech/tags/communication.md>), [future-of-work](<https://devfeed.tech/tags/future-of-work.md>), [productivity](<https://devfeed.tech/tags/productivity.md>), [remote-work](<https://devfeed.tech/tags/remote-work.md>), [workplace-transformation](<https://devfeed.tech/tags/workplace-transformation.md>)

### AI overview

The author argues that personal AI agents could reduce workplace miscommunication by carrying full written context between colleagues, then explaining it in terms each recipient understands. In the described workflow, an agent gathers emails, attachments, and product context, turns them into a role-assigned task, and drafts a reply; people retain judgment and approve decisions. The author says this could reduce meetings and prevent information loss, including in exchanges between companies, while access controls must protect role-restricted data and external messages must not reveal unintended intent. The main cost is weaker workplace belonging as colleagues interact more with agents. A further risk is that people may stop checking original sources and miss agent errors; the proposed safeguard is human decision-making, with written records making mistakes traceable. The author presents the model as already in use at their company and expects broader adoption within a decade.

### Source excerpt

Communication at work will stop passing through people: each person will have an agent, and the burden of being understood moves to the listener.

## Attacks and Defenses in Decentralized Multi-Agent Systems with Hop-by-Hop Task Decomposition and Delegation

DevFeed: [Attacks and Defenses in Decentralized Multi-Agent Systems with Hop-by-Hop Task Decomposition and Delegation](<https://devfeed.tech/articles/attacks-and-defenses-in-decentralized-multi-agent-systems-with-hop-by-hop-task-decomposition-and-delegation-146019.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.25056>)

Author: Matthew D. Laws, Maria Lazou, Alina Oprea, Cristina Nita-Rotaru

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 security](<https://devfeed.tech/topics/ai-security.md>), [Multi Agent Systems](<https://devfeed.tech/topics/multi-agent-systems.md>), [LLM security](<https://devfeed.tech/topics/llm-security.md>), [hierarchical agent systems](<https://devfeed.tech/topics/hierarchical-agent-systems.md>), [Cybersecurity](<https://devfeed.tech/topics/cybersecurity.md>), [agent to agent communication](<https://devfeed.tech/topics/agent-to-agent-communication.md>)

Tags: [agent](<https://devfeed.tech/tags/agent.md>), [attacks](<https://devfeed.tech/tags/attacks.md>), [availability](<https://devfeed.tech/tags/availability.md>), [cryptographic](<https://devfeed.tech/tags/cryptographic.md>), [cs-cr](<https://devfeed.tech/tags/cs-cr.md>), [cs-ma](<https://devfeed.tech/tags/cs-ma.md>), [decentralized](<https://devfeed.tech/tags/decentralized.md>), [delegation](<https://devfeed.tech/tags/delegation.md>), [execution](<https://devfeed.tech/tags/execution.md>), [integrity](<https://devfeed.tech/tags/integrity.md>), [latency](<https://devfeed.tech/tags/latency.md>), [llm](<https://devfeed.tech/tags/llm.md>), [malicious](<https://devfeed.tech/tags/malicious.md>), [memory](<https://devfeed.tech/tags/memory.md>), [mitigation](<https://devfeed.tech/tags/mitigation.md>), [model](<https://devfeed.tech/tags/model.md>), [multi-agent](<https://devfeed.tech/tags/multi-agent.md>), [multi-agent-systems](<https://devfeed.tech/tags/multi-agent-systems.md>), [overhead](<https://devfeed.tech/tags/overhead.md>), [protocol](<https://devfeed.tech/tags/protocol.md>), [runtime](<https://devfeed.tech/tags/runtime.md>), [security](<https://devfeed.tech/tags/security.md>)

### AI overview

The abstract reports that one malicious agent in a decentralized multi-agent LLM system can cause up to 100% task failure, raise token use by up to 7.7x and runtime by up to 3.2x, or exfiltrate up to 94% of relevant prior tasks. The proposed cryptographic protocol creates a verifiable execution trace, which an auditor analyzes to detect and attribute malicious behavior. On HiddenBench, evaluations with gpt-6.1-sol and Qwen3.8-27B-FP8 found negligible latency overhead and 98% detection and correct attribution of attacks, including attacks that complied with the protocol.

### Source excerpt

arXiv:2611.25056v1 Announce Type: new Abstract: Decentralized multi-agent LLM systems enable independently administered agents, each with its own operator, model, memory, and configuration, to collaborate on complex tasks without centralized coordination. Agents autonomously decompose tasks, execute subtasks and delegate remaining work to peers, enabling scalability and eliminating single points of failure. However, decentralization also introduces significant security challenges, as no single entity has complete visibility into task execution or the authority to enforce correct behavior across agents. In this paper, we systematize threats from malicious agents in decentralized multi-agent systems and propose mitigation techniques. We first design and evaluate attacks against integrity, availability, and confidentiality, demonstrating that a single malicious agent can cause up to 100% task failure, inflate token consumption and runtime by up to 7.7x and 3.2x, respectively, and exfiltrate up to 94% of relevant prior tasks from benign agents. We then present a cryptographic protocol that produces an irrefutable verified execution trace of every action taken in the system and develop an auditor that analyzes these traces to detect and attribute malicious behavior. Evaluations on HiddenBench using gpt-6.1-sol and Qwen3.8-27B-FP8 show that our protocol incurs negligible latency overhead, while the auditor detects and correctly attributes 98% of attacks, including those that comply with the protocol.

## Context as a Resource

DevFeed: [Context as a Resource](<https://devfeed.tech/articles/context-as-a-resource-145662.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.26346>)

Author: Xufei Tian, Han Hu, Wenli Du

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

Content type: article

Language: en

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

Topics: [AI Context Management](<https://devfeed.tech/topics/ai-context-management.md>), [Multi Agent Systems](<https://devfeed.tech/topics/multi-agent-systems.md>), [scheduling](<https://devfeed.tech/topics/scheduling.md>)

Tags: [agent](<https://devfeed.tech/tags/agent.md>), [architecture](<https://devfeed.tech/tags/architecture.md>), [arxiv](<https://devfeed.tech/tags/arxiv.md>), [benchmarks](<https://devfeed.tech/tags/benchmarks.md>), [blocks](<https://devfeed.tech/tags/blocks.md>), [bus](<https://devfeed.tech/tags/bus.md>), [cells](<https://devfeed.tech/tags/cells.md>), [completion](<https://devfeed.tech/tags/completion.md>), [concurrent](<https://devfeed.tech/tags/concurrent.md>), [constraint](<https://devfeed.tech/tags/constraint.md>), [context](<https://devfeed.tech/tags/context.md>), [continuous](<https://devfeed.tech/tags/continuous.md>), [cross](<https://devfeed.tech/tags/cross.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [events](<https://devfeed.tech/tags/events.md>), [gate](<https://devfeed.tech/tags/gate.md>), [generative](<https://devfeed.tech/tags/generative.md>), [handoffs](<https://devfeed.tech/tags/handoffs.md>), [interface](<https://devfeed.tech/tags/interface.md>), [linear](<https://devfeed.tech/tags/linear.md>), [resource](<https://devfeed.tech/tags/resource.md>)

### AI overview

ClonAct proposes routerless management of concurrent agent contexts, using a non-generative Context MMU, in-place Context Cells, a footprint-aware Synaptic Bus with an isolated trial merge gate, and a wave-flushed Shared Trunk. The abstract reports that the merge gate raises true-conflict repository merge success from a 33.3% three-run mean to 63.3%; ClonAct reaches that rate with 45.9% fewer prompt tokens and avoids router collapse on compact models. Across three multi-stream benchmarks and three model families, it also matches the best reported completion rate under continuous surges (95.0%), with the lowest median wait and no timed-out status checks. These are abstract-level claims; the supplied text gives no further benchmark methodology or results.

### Source excerpt

arXiv:2611.26346v1 Announce Type: new Abstract: Managing concurrent tasks across separate agent sessions quickly exhausts human attention, motivating always-on personal agents behind a single continuous interface. Yet when every context shares identical frozen backbone weights, funneling interleaved dialogues and external events into one linear session induces cross-topic constraint bleed and head-of-line stalling. Conversely, router-ticket hierarchies incur lossy prose handoffs, heavy routing overhead, and blind merges - collapsing true-conflict repository merges to a 33.3% three-run mean despite high isolated branch passes. Rather than scheduling anthropomorphic roles, we introduce ClonAct, a routerless architecture that virtualizes context blocks directly through a pluggable single-pass non-generative Context MMU, in-place Context Cells, a footprint-aware Synaptic Bus with an isolated trial merge gate, and a wave-flushed Shared Trunk. Across three programmatic multi-stream benchmarks and three model families, our portable trial merge gate lifts true-conflict merges to 63.3%, while ClonAct's routerless virtualization attains this ceiling with 45.9% fewer prompt tokens and prevents compact-model router collapse. Under continuous surge streams, ClonAct matches top completion (95.0%) with the lowest median wait and zero timed-out status checks.

## DSFlow: A Neuro-Symbolic Data Workflow Agent with Statistical Diagnostic Guardrails

DevFeed: [DSFlow: A Neuro-Symbolic Data Workflow Agent with Statistical Diagnostic Guardrails](<https://devfeed.tech/articles/dsflow-a-neuro-symbolic-data-workflow-agent-with-statistical-diagnostic-guardrails-145469.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.25111>)

Author: Junfeng Nie, Xiaohui Chen

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

Content type: article

Language: en

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

Topics: [Data Science](<https://devfeed.tech/topics/data-science.md>), [Multi Agent Systems](<https://devfeed.tech/topics/multi-agent-systems.md>), [Large Language Model](<https://devfeed.tech/topics/llm.md>), [clustering](<https://devfeed.tech/topics/clustering.md>), [linear-regression](<https://devfeed.tech/topics/linear-regression.md>)

Tags: [agent](<https://devfeed.tech/tags/agent.md>), [clustering](<https://devfeed.tech/tags/clustering.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [data](<https://devfeed.tech/tags/data.md>), [diagnostic](<https://devfeed.tech/tags/diagnostic.md>), [guardrails](<https://devfeed.tech/tags/guardrails.md>), [langgraph](<https://devfeed.tech/tags/langgraph.md>), [language-models](<https://devfeed.tech/tags/language-models.md>), [large-language-models-llms](<https://devfeed.tech/tags/large-language-models-llms.md>), [regression](<https://devfeed.tech/tags/regression.md>), [reports](<https://devfeed.tech/tags/reports.md>), [skills](<https://devfeed.tech/tags/skills.md>), [workflow](<https://devfeed.tech/tags/workflow.md>)

### AI overview

DSFlow combines reusable skills selected by an LLM with deterministic statistical checks to guide data-science workflows. Its symbolic validation can accept a proposed method, ask for clarification or replanning, override an unsuitable choice, or provide a safe fallback. Regression and clustering case studies show diagnostic evidence correcting method choices, with decisions recorded in auditable reports. The supplied text is an abstract and does not provide implementation details or case-study results.

### Source excerpt

arXiv:2611.25111v1 Announce Type: new Abstract: Data science workflows often require tools that presume non-trivial technical knowledge. Large language models (LLMs) reduce this barrier, but a gap remains between flexible general-purpose agents and statistically controlled pipelines. We introduce DSFlow, a LangGraph-based neuro-symbolic data-agent platform that combines reusable, LLM-selected skills with deterministic diagnostic guardrails. Skills provide extensible task knowledge. Symbolic validation can accept a proposed method, request clarification or replanning, override an unsuitable method, or supply a safe fallback. Regression and clustering case studies illustrate how DSFlow uses diagnostic evidence to correct method choices and documents those decisions in auditable reports.

## ALIoTh: Orchestrating Multi-Agent LLMs for Autonomous IoT Penetration Testing

DevFeed: [ALIoTh: Orchestrating Multi-Agent LLMs for Autonomous IoT Penetration Testing](<https://devfeed.tech/articles/alioth-orchestrating-multi-agent-llms-for-autonomous-iot-penetration-testing-146047.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.25809>)

Author: Pironti Francesco Aurelio, Arena Luigi, Blefari Francesco, Lupinacci Matteo, Romeo Francesco, Maresca Alessio

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: [Hacking](<https://devfeed.tech/topics/hacking.md>), [Internet of things](<https://devfeed.tech/topics/iot.md>), [Multi Agent Systems](<https://devfeed.tech/topics/multi-agent-systems.md>), [AI Agent](<https://devfeed.tech/topics/ai-agent.md>), [Multi-step AI processes](<https://devfeed.tech/topics/multi-step-ai-processes.md>), [LLM security](<https://devfeed.tech/topics/llm-security.md>), [Enhancing AI model performance](<https://devfeed.tech/topics/enhancing-ai-model-performance.md>), [smartdevices](<https://devfeed.tech/topics/smartdevices.md>)

Tags: [agent](<https://devfeed.tech/tags/agent.md>), [architecture](<https://devfeed.tech/tags/architecture.md>), [assessment](<https://devfeed.tech/tags/assessment.md>), [attack](<https://devfeed.tech/tags/attack.md>), [autonomous](<https://devfeed.tech/tags/autonomous.md>), [cameras](<https://devfeed.tech/tags/cameras.md>), [cs-cr](<https://devfeed.tech/tags/cs-cr.md>), [deployment](<https://devfeed.tech/tags/deployment.md>), [devices](<https://devfeed.tech/tags/devices.md>), [enumeration](<https://devfeed.tech/tags/enumeration.md>), [exploit](<https://devfeed.tech/tags/exploit.md>), [exploitation](<https://devfeed.tech/tags/exploitation.md>), [framework](<https://devfeed.tech/tags/framework.md>), [gathering](<https://devfeed.tech/tags/gathering.md>), [generation](<https://devfeed.tech/tags/generation.md>), [group-policy](<https://devfeed.tech/tags/group-policy.md>), [iiot](<https://devfeed.tech/tags/iiot.md>), [iot](<https://devfeed.tech/tags/iot.md>), [llms](<https://devfeed.tech/tags/llms.md>), [multi-agent](<https://devfeed.tech/tags/multi-agent.md>), [penetration-testing](<https://devfeed.tech/tags/penetration-testing.md>)

### AI overview

ALIoTh is a workflow-driven framework that coordinates specialized LLM agents through LangGraph and a Self-RAG architecture to automate IoT and IIoT penetration testing. Its described pipeline covers network, device, and service enumeration, vulnerability assessment, payload generation, reverse-shell deployment, and privilege escalation. Self-RAG gives agents contextual access to IoT security documentation, tool manuals, and known attack techniques, supporting scenarios involving multiple devices and group-policy manipulation. The supplied text describes the approach but provides no evaluation results or comparative performance.

### Source excerpt

arXiv:2611.25809v1 Announce Type: new Abstract: Penetration testing in Internet of Things (IoT) environments, especially those composed of various different devices, e.g., smart plugs, smart cameras, and smart doors, presents great challenges across the phases of information gathering, attack surface enumeration, privilege escalation, and lateral movement. This paper introduces ALIoTh, a multi-agent, workflow-driven penetration testing framework that integrates Large Language Models agents within a Self-Retrieval-Augmented Generation (Self-RAG) architecture to autonomously identify and exploit vulnerabilities in IoT and Industrial-IoT (IIoT) environments. By leveraging state-of-the-art language models and orchestrating specialized agents via the LangGraph framework, ALIoTh dynamically plans and executes a full-spectrum offensive pipeline. This includes network, devices, and service enumeration, vulnerability assessment, payload generation, reverse shell deployment, and privilege escalation on each device. The Self-RAG mechanism equips expert agents with contextual access to IoT security knowledge, e.g., related documentation, tool manuals, and known attack techniques, enhancing their reasoning capabilities in scenarios involving multiple device exploitation and group policy manipulation.

## Insights Generator: Systematic Corpus-Level Trace Diagnostics for LLM Agents

DevFeed: [Insights Generator: Systematic Corpus-Level Trace Diagnostics for LLM Agents](<https://devfeed.tech/articles/insights-generator-systematic-corpus-level-trace-diagnostics-for-llm-agents-144897.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2605.21347>)

Author: Akshay Manglik, Vijay S. Kalmath, Jason Qin, Apaar Shanker, Kaustubh Deshpande, Yash Maurya, Veronica Chatrath, Levi Lentz, Yuan Xue

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>), [arXiv: Software Engineering](<https://devfeed.tech/sources/arxiv-software-engineering.md>)

Topics: [agent observability](<https://devfeed.tech/topics/agent-observability.md>), [Multi Agent Systems](<https://devfeed.tech/topics/multi-agent-systems.md>), [Large Language Model](<https://devfeed.tech/topics/llm.md>), [ai evaluation](<https://devfeed.tech/topics/ai-evaluation.md>)

Tags: [agents](<https://devfeed.tech/tags/agents.md>), [architecture](<https://devfeed.tech/tags/architecture.md>), [assessment](<https://devfeed.tech/tags/assessment.md>), [benchmarks](<https://devfeed.tech/tags/benchmarks.md>), [coding-agents](<https://devfeed.tech/tags/coding-agents.md>), [coverage](<https://devfeed.tech/tags/coverage.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [cs-se](<https://devfeed.tech/tags/cs-se.md>), [diagnostics](<https://devfeed.tech/tags/diagnostics.md>), [grounded](<https://devfeed.tech/tags/grounded.md>), [insights](<https://devfeed.tech/tags/insights.md>), [llm](<https://devfeed.tech/tags/llm.md>), [llm-agents](<https://devfeed.tech/tags/llm-agents.md>), [multi-agent](<https://devfeed.tech/tags/multi-agent.md>), [multi-agent-system](<https://devfeed.tech/tags/multi-agent-system.md>), [performance](<https://devfeed.tech/tags/performance.md>), [quality](<https://devfeed.tech/tags/quality.md>), [report](<https://devfeed.tech/tags/report.md>), [stable](<https://devfeed.tech/tags/stable.md>), [tokens](<https://devfeed.tech/tags/tokens.md>), [trace](<https://devfeed.tech/tags/trace.md>), [traces](<https://devfeed.tech/tags/traces.md>)

### AI overview

The Insights Generator (IG) analyzes groups of LLM-agent execution traces by proposing and testing hypotheses, then produces natural-language findings linked to supporting evidence. The authors report that experts using IG reports improved scaffold performance by 30.4 percentage points over an unmodified baseline, while coding agents using IG-derived insights showed consistent, stable gains. Across benchmarks, IG's scout-investigator architecture had detection coverage comparable to competing approaches; domain experts rated its reports highest for depth and evidence quality.

### Source excerpt

arXiv:2605.21347v5 Announce Type: replace-cross Abstract: Diagnosing failures in LLM agents remains largely manual. Practitioners inspect a small subset of execution traces, form ad-hoc hypotheses, and iterate. This process misses patterns that only emerge across trace populations and does not scale to production corpora where individual traces span tens of thousands of tokens. We formalize the problem of corpus-level trace diagnostics. Given a corpus of execution traces, the goal is to produce grounded natural-language insights that characterize systematic behavioral patterns across trace groups, each linked to supporting evidence. We present the Insights Generator (IG), a multi-agent system that answers diagnostic questions by proposing and testing hypotheses across the trace corpus to produce an evidence-backed insights report. We evaluate IG across qualitative and objective dimensions, spanning rubric-based report assessment and downstream performance improvements achieved by implementing IG insights. Human experts using IG reports improve scaffold performance by 30.4 pp over the unmodified baseline scaffold, and coding agents leveraging IG-derived insights show consistent and stable gains. Across benchmarks, IG's scout-investigator architecture produces findings comparable in detection coverage to competing approaches, while domain experts rated IG reports as leading depth and evidence quality.

## Toward a Science of AI Agent Societies

DevFeed: [Toward a Science of AI Agent Societies](<https://devfeed.tech/articles/toward-a-science-of-ai-agent-societies-145508.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.25404>)

Author: Geon Lee, Fanchen Bu, Soo Yong Lee, Sunwoo Kim, Kijung Shin

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

Content type: article

Language: en

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

Topics: [Multi Agent Systems](<https://devfeed.tech/topics/multi-agent-systems.md>), [AI Agent](<https://devfeed.tech/topics/ai-agent.md>), [future of AI](<https://devfeed.tech/topics/future-of-ai.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [ai-agent](<https://devfeed.tech/tags/ai-agent.md>), [autonomy](<https://devfeed.tech/tags/autonomy.md>), [behaviors](<https://devfeed.tech/tags/behaviors.md>), [challenges](<https://devfeed.tech/tags/challenges.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [evaluation](<https://devfeed.tech/tags/evaluation.md>), [governance](<https://devfeed.tech/tags/governance.md>), [implementation](<https://devfeed.tech/tags/implementation.md>), [multi-agent-systems](<https://devfeed.tech/tags/multi-agent-systems.md>), [objectives](<https://devfeed.tech/tags/objectives.md>), [research](<https://devfeed.tech/tags/research.md>), [scale](<https://devfeed.tech/tags/scale.md>), [society](<https://devfeed.tech/tags/society.md>)

### AI overview

The paper proposes studying AI agent societies as a distinct research object, rather than simply scaling up individual agents or simulating human society. It defines four core properties for such societies: individualized objectives, rules and governance, autonomy, and scale and complexity. The authors identify economic behavior, conflict of interest, unsafe or unethical behavior, and system-level behavior as areas to investigate. They highlight property parameterization, parameter balancing, and robust implementation as technical challenges, and assess existing multi-agent systems as satisfying only subsets of the proposed properties. The abstract says progress could support useful models and inform platform design, evaluation, and governance.

### Source excerpt

arXiv:2611.25404v1 Announce Type: new Abstract: AI agents are rapidly evolving from isolated personal assistants into networked actors that interact with one another at scale. We envision the emergence of AI agent societies, with their own social and economic dynamics, as a new research frontier. We argue that AI agent societies should be studied as a distinct object of inquiry: neither simply larger collections of individual agents nor merely simulations of human society. To formalize this perspective, we propose four core properties that a valid AI agent society should satisfy: individualized objectives, rules and governance, autonomy, and scale and complexity. Building on this framework, we identify four classes of societal behaviors worth studying in AI agent societies: economic behaviors, behaviors under conflict-of-interest, unsafe and unethical behaviors, and system-level behaviors. We then outline key technical challenges--including property parameterization, parameter balancing, and robust implementation--and argue that progress on these challenges could enable scientifically informative and practically useful models of AI agent societies. Finally, we revisit existing multi-agent systems through the lens of the proposed core properties, show that they instantiate only subsets of them, and discuss implications for platform design, evaluation, and governance.

## Topology-Driven Anti-Entanglement Control for Soft Robots

DevFeed: [Topology-Driven Anti-Entanglement Control for Soft Robots](<https://devfeed.tech/articles/topology-driven-anti-entanglement-control-for-soft-robots-145326.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2605.05236>)

Author: Haoyang Le, Shengxuan Wang, Mohan Chen, Shuo Feng

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

Content type: article

Language: en

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

Topics: [Multi Agent Systems](<https://devfeed.tech/topics/multi-agent-systems.md>), [Physical AI](<https://devfeed.tech/topics/physical-ai.md>), [Distributed Systems & Parallel Computing](<https://devfeed.tech/topics/distributed-systems-parallel-computing.md>)

Tags: [control](<https://devfeed.tech/tags/control.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cs-ro](<https://devfeed.tech/tags/cs-ro.md>), [entanglement](<https://devfeed.tech/tags/entanglement.md>), [robots](<https://devfeed.tech/tags/robots.md>), [topology](<https://devfeed.tech/tags/topology.md>)

### AI overview

The paper proposes topology-driven multi-agent reinforcement learning (TD-MARL) to coordinate soft robots unwinding in constrained environments. It combines centralized learning, where agents share topological state to account for one another's strategies and reduce training instability, with distributed execution that removes the need for inter-robot communication. A topological safety layer uses invariants to assess and mitigate entanglement risk. The abstract reports that full simulation experiments outperform current deep reinforcement learning methods in convergence and anti-entanglement performance; it provides no quantitative results or experimental details.

### Source excerpt

arXiv:2605.05236v3 Announce Type: replace-cross Abstract: In the field of precision manufacturing in complex constrained environments, the role of soft robots is increasingly prominent, and the realization of anti-winding control based on multi-intelligent body reinforcement learning has become a research hotspot. One of the core problems at present is to coordinate multiple robots to complete the unwinding operation in a highly constrained environment. The existing distributed training framework faces some observability challenges in high-density barrier and unstable environments, resulting in poor learning results. This paper proposes a topology-driven Multi-Agent Reinforcement Learning (TD-MARL) framework to coordinate multi-robot systems to avoid entanglement. Specifically, the critical network adopts centralized learning, so that each intelligent body can perceive the strategies of other intelligent bodies by sharing the topological state, thus alleviating the training instability caused by complex interactions; eliminating the demand for communication resources between robots through distributed execution, Upgrade system reliability; the integrated topological security layer uses topological invariants to accurately assess and mitigate the risk of entanglement to avoid the strategy from falling into local difficulties. Finally, the full simulation experiments carried out in the real simulation environment show that the method is better than the current advanced deep reinforcement learning (DRL) method in terms of convergence and anti-winding effect.

## FinVeriQA: Financial Research Agents for Question Answering: Routing, Retrieval, MCP Tool Use, and Provenance-Aware Evidence Verification

DevFeed: [FinVeriQA: Financial Research Agents for Question Answering: Routing, Retrieval, MCP Tool Use, and Provenance-Aware Evidence Verification](<https://devfeed.tech/articles/finveriqa-financial-research-agents-for-question-answering-routing-retrieval-mcp-tool-use-and-provenance-aware-evidence-verification-145463.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.25071>)

Author: Meenakshi Rajpurohit, Anna Phan, Ravikumar Komandur Narayanan, Gunanidhi Ramakrishnan, Nathan Howland

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

Content type: article

Language: en

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

Topics: [Multi Agent Systems](<https://devfeed.tech/topics/multi-agent-systems.md>), [Finance](<https://devfeed.tech/topics/finance.md>), [AI Chat](<https://devfeed.tech/topics/ai-chat.md>), [llamaindex](<https://devfeed.tech/topics/llamaindex.md>), [Open Source](<https://devfeed.tech/topics/open-source.md>)

Tags: [advice](<https://devfeed.tech/tags/advice.md>), [agent](<https://devfeed.tech/tags/agent.md>), [agents](<https://devfeed.tech/tags/agents.md>), [alphabet](<https://devfeed.tech/tags/alphabet.md>), [amd](<https://devfeed.tech/tags/amd.md>), [arxiv](<https://devfeed.tech/tags/arxiv.md>), [benchmark](<https://devfeed.tech/tags/benchmark.md>), [better](<https://devfeed.tech/tags/better.md>), [case-study](<https://devfeed.tech/tags/case-study.md>), [code](<https://devfeed.tech/tags/code.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>), [cs-ma](<https://devfeed.tech/tags/cs-ma.md>), [financial](<https://devfeed.tech/tags/financial.md>), [mcp](<https://devfeed.tech/tags/mcp.md>), [provenance](<https://devfeed.tech/tags/provenance.md>), [question](<https://devfeed.tech/tags/question.md>), [research](<https://devfeed.tech/tags/research.md>), [retrieval](<https://devfeed.tech/tags/retrieval.md>), [routing](<https://devfeed.tech/tags/routing.md>), [tool](<https://devfeed.tech/tags/tool.md>), [tool-use](<https://devfeed.tech/tags/tool-use.md>), [verification](<https://devfeed.tech/tags/verification.md>)

### AI overview

FinVeriQA assigns financial QA tasks to specialized components: Laya routes questions and screens out advice requests, Python performs calculations, retrieval and tools gather evidence, and Mistral-7B writes cited answers. Laya routed better than Mistral-7B in live experiments (0.85 vs. 0.52); DeepSeek-R1-8B also did better but took about 9.9 times longer. Python got all 100 tested calculations right versus 29% for Mistral-7B, and a live quote reduced price error from 210% to zero. Hybrid retrieval reached 76% Hit@5 on filing questions. However, both answers in a case study passed validation despite mislabeling AMD data as NVIDIA and Alphabet data. On FinRank, checks against shared evidence caught fewer errors than checks against original passages, supporting the authors' conclusion that verification should be independent of the evidence used to draft an answer.

### Source excerpt

arXiv:2611.25071v1 Announce Type: cross Abstract: Large language models (LLMs) write fluent financial analyses but miscompute ratios, recall stale prices, and route questions to the wrong tool with high confidence. We ask which component should do each job in a financial question-answering assistant, and study it with FinVeriQA, an open-source multi-agent research prototype over SEC filings and live market data: a compact typed-decision model (Laya) routes each question and screens out advice requests, Python computes every number, retrieval and tools fetch evidence, Mistral-7B writes a cited answer, a code validator checks that cited IDs exist and that numbers match computed notes, and a Model Context Protocol (MCP) server exposes the pipeline. In live experiments, Laya routed better than Mistral-7B (0.85 vs. 0.52; overall 0.86 vs. 0.68, McNemar p = 0.0003); a 12B Mistral decided no better, and DeepSeek-R1-8B decided better (0.79 vs. 0.68, p = 0.0192) but about 9.9 times more slowly. Mistral-7B computed 29% of 100 financial calculations correctly against 100% for Python, a live quote cut price error from 210% to 0.00%, and hybrid retrieval reached 76% Hit@5 on 50 filing questions. Yet in a live case study, both agent answers passed validation while describing AMD sample data under NVIDIA's and Alphabet's names. A controlled upper-bound study on the FinRank benchmark explains why: when one figure in the shared evidence is corrupted, self-consistency stays confident (agreement 0.55 to 0.59 while accuracy falls from 0.50 to 0.00), and a shared-evidence check (the kind our validator performs) catches 35% of the errors, whereas a check against the original passage catches 77% ($p = 5.96 \times 10^{-8}$); for DeepSeek-R1-8B, 68% vs. 90%. Verification must be independent of the evidence the writer saw.

## MAWAM: A Multi-Agent World-Action Model for Coordinated Manipulation

DevFeed: [MAWAM: A Multi-Agent World-Action Model for Coordinated Manipulation](<https://devfeed.tech/articles/mawam-a-multi-agent-world-action-model-for-coordinated-manipulation-145467.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.25105>)

Author: Xianzhe Fan, Chi-Pin Huang, Fu-En Yang, Jing Wang, Yecheng Wu, Yu-Cheng Chou, Johan Bjorck, Linxi "Jim" Fan, Jan Kautz, Yu-Chiang Frank Wang, Zhiding Yu, Hengshuang Zhao, Zhiqi Li

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

Content type: article

Language: en

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

Topics: [Multi Agent Systems](<https://devfeed.tech/topics/multi-agent-systems.md>), [Robot Manipulation](<https://devfeed.tech/topics/robot-manipulation.md>), [World models](<https://devfeed.tech/topics/world-models.md>), [Physical AI](<https://devfeed.tech/topics/physical-ai.md>)

Tags: [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cs-cv](<https://devfeed.tech/tags/cs-cv.md>), [cs-ro](<https://devfeed.tech/tags/cs-ro.md>), [manipulation](<https://devfeed.tech/tags/manipulation.md>), [model](<https://devfeed.tech/tags/model.md>), [multi-agent](<https://devfeed.tech/tags/multi-agent.md>), [robotics](<https://devfeed.tech/tags/robotics.md>)

### AI overview

MAWAM predicts a robot team's physical future alongside its actions: it jointly generates each robot's future views and executable action chunks, using cross-agent attention while keeping separate control interfaces. On three real-robot tasks, it reports 67.8% mean success, 18.9 percentage points above MA-VLA trained on the same demonstrations and cameras. In simulation, it reports 90.3% mean success across eight tasks with teams of up to four arms. Ablations indicate both cross-agent attention and team-stage future-video supervision matter: removing attention reduced four-arm relay success from 95.0% to 39.0%, while removing that video supervision reduced Place Food success from 78.0% to 47.0%.

### Source excerpt

arXiv:2611.25105v1 Announce Type: cross Abstract: Every move in a robot team changes the world in which its teammates must act. Coordinated manipulation therefore calls for predicting the team's actions together with the physical future they jointly create. We introduce MAWAM, a multi-agent world-action model that jointly generates each robot's future views and executable action chunks in a single sample. Built from a pretrained single-robot world-action backbone, MAWAM jointly denoises all robots' action and future-view tokens through cross-agent attention, while preserving a separate control interface for each robot. MAWAM achieves the highest success on all three real-robot tasks (laundry-bag collection, bath-towel folding, and umbrella handover), with 67.8% mean success, 18.9 percentage points above MA-VLA trained on the same demonstrations and cameras. In simulation, MAWAM reaches 90.3% mean success on eight tasks with teams of up to four arms. Ablations show that cross-agent attention and team-stage future-video supervision both improve coordinated control: without attention, a four-arm relay falls from 95.0% to 39.0%, and without this supervision, Place Food falls from 78.0% to 47.0%.

## How the BMW Group governs hundreds of agents across thousands of developers

DevFeed: [How the BMW Group governs hundreds of agents across thousands of developers](<https://devfeed.tech/articles/how-the-bmw-group-governs-hundreds-of-agents-across-thousands-of-developers-144472.md>)

Original publisher: [Read original article](<https://aws.amazon.com/blogs/machine-learning/how-the-bmw-group-governs-hundreds-of-agents-across-thousands-of-developers/>)

Author: Dr. Jens Kohl

Published: 2026-11-19T22:20:23Z

Content type: article

Language: en

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

Topics: [ai-governance](<https://devfeed.tech/topics/ai-governance.md>), [Multi Agent Systems](<https://devfeed.tech/topics/multi-agent-systems.md>), [CI/CD](<https://devfeed.tech/topics/cicd.md>), [LLM observability](<https://devfeed.tech/topics/llm-observability.md>), [Cloud Architecture](<https://devfeed.tech/topics/cloud-architecture.md>), [LLM security](<https://devfeed.tech/topics/llm-security.md>), [AI Infrastructure](<https://devfeed.tech/topics/ai-infrastructure.md>), [agent to agent communication](<https://devfeed.tech/topics/agent-to-agent-communication.md>), [OpenTelemetry](<https://devfeed.tech/topics/opentelemetry.md>), [internal developer platform automation](<https://devfeed.tech/topics/internal-developer-platform-automation.md>)

Tags: [2023](<https://devfeed.tech/tags/2023.md>), [a2a](<https://devfeed.tech/tags/a2a.md>), [a2a-protocol](<https://devfeed.tech/tags/a2a-protocol.md>), [agent](<https://devfeed.tech/tags/agent.md>), [agent-harness](<https://devfeed.tech/tags/agent-harness.md>), [agent-infrastructure](<https://devfeed.tech/tags/agent-infrastructure.md>), [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-agents](<https://devfeed.tech/tags/ai-agents.md>), [automotive](<https://devfeed.tech/tags/automotive.md>), [best-practices](<https://devfeed.tech/tags/best-practices.md>), [bmw](<https://devfeed.tech/tags/bmw.md>), [compliance](<https://devfeed.tech/tags/compliance.md>), [developers](<https://devfeed.tech/tags/developers.md>), [enterprise](<https://devfeed.tech/tags/enterprise.md>), [enterprise-scale](<https://devfeed.tech/tags/enterprise-scale.md>), [governance](<https://devfeed.tech/tags/governance.md>), [intermediate-200](<https://devfeed.tech/tags/intermediate-200.md>), [patterns](<https://devfeed.tech/tags/patterns.md>), [practices](<https://devfeed.tech/tags/practices.md>), [quality](<https://devfeed.tech/tags/quality.md>), [scale](<https://devfeed.tech/tags/scale.md>), [teams](<https://devfeed.tech/tags/teams.md>)

### AI overview

BMW Group's approach to governing agents across its R&D organization centers on reusable architecture and lifecycle controls that let teams experiment while enforcing safety, security, quality, and compliance. Governance rules live outside individual agents--in integration layers, a central registry, and deterministic CI/CD and policy checks--so they can survive framework or model changes. Teams set autonomy per workflow step, from explicit human approval to bounded autonomy, and increase it based on evaluation evidence. Agents are built from composable MCP tools, skills, and flows, with specialized agents and least-privilege access used to contain complexity. CI pipelines run tests, security and governance checks, and ground-truth evaluations before deployment; runtime monitoring flags data or model drift for human review. IaC templates, shared registries, and centrally curated checks support distributed team contributions without mandating a single framework. The article describes these practices and reported benefits but provides no quantitative outcome measures.

### Source excerpt

When hundreds of agents serve thousands of developers, governance cannot be an afterthought. The BMW Group shares the practices and patterns its R&D teams use to build, govern, and operate AI agents at enterprise scale without sacrificing speed, quality, or compliance.

## A "headless Slack": Vercel's new message board lets Claude Code and Codex agents work together

DevFeed: [A "headless Slack": Vercel's new message board lets Claude Code and Codex agents work together](<https://devfeed.tech/articles/a-headless-slack-vercel-s-new-message-board-lets-claude-code-and-codex-agents-work-together-144045.md>)

Original publisher: [Read original article](<https://thenewstack.io/vercel-board-agent-swarms/>)

Author: Paul Sawers

Published: 2026-11-19T16:58:48Z

Content type: news

Language: en

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

Topics: [agent to agent communication](<https://devfeed.tech/topics/agent-to-agent-communication.md>), [Multi Agent Systems](<https://devfeed.tech/topics/multi-agent-systems.md>), [agent orchestration](<https://devfeed.tech/topics/agent-orchestration.md>), [agentic workflows](<https://devfeed.tech/topics/agentic-workflows.md>), [agentic-coding](<https://devfeed.tech/topics/agentic-coding.md>), [Claude Code](<https://devfeed.tech/topics/claude-code.md>), [codex](<https://devfeed.tech/topics/codex.md>), [Slack](<https://devfeed.tech/topics/slack.md>), [Vercel](<https://devfeed.tech/topics/vercel.md>), [Linear](<https://devfeed.tech/topics/linear.md>)

Tags: [access-controls](<https://devfeed.tech/tags/access-controls.md>), [agent-communication](<https://devfeed.tech/tags/agent-communication.md>), [agent-fleets](<https://devfeed.tech/tags/agent-fleets.md>), [agent-infrastructure](<https://devfeed.tech/tags/agent-infrastructure.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-keys](<https://devfeed.tech/tags/api-keys.md>), [auditability](<https://devfeed.tech/tags/auditability.md>), [board](<https://devfeed.tech/tags/board.md>), [claude-code](<https://devfeed.tech/tags/claude-code.md>), [codex](<https://devfeed.tech/tags/codex.md>), [coding-agents](<https://devfeed.tech/tags/coding-agents.md>), [developer-tools](<https://devfeed.tech/tags/developer-tools.md>), [headless](<https://devfeed.tech/tags/headless.md>), [message](<https://devfeed.tech/tags/message.md>), [security](<https://devfeed.tech/tags/security.md>), [slack](<https://devfeed.tech/tags/slack.md>), [tasks](<https://devfeed.tech/tags/tasks.md>), [vercel](<https://devfeed.tech/tags/vercel.md>)

### AI overview

Vercel Board is an experimental shared message board for coordinating agents built with different tools, including Claude Code, Codex, Pi, OpenCode, and LangChain. Agents can claim assignments, exchange findings in channels and threads, track dependencies, and record progress; Board can also synchronize updates with Slack, GitHub, and Linear and trigger agents when messages or task statuses change. Developers can follow work, set channel permissions, review findings, and require approval before changes proceed. Vercel says it developed Board for its engineering operations and rebuilt v0's software factory around it, which it says now merges over 50% of PRs. Board is available through the Vercel CLI or JavaScript SDK on all Vercel plans, free during the experimental period, with possible charges later. Vercel warns that agents may treat messages as instructions; it recommends restricting channel access as needed and keeping API keys and tokens off Board.

### Source excerpt

For AI agents to work together effectively, they need a way to communicate and divvy up tasks -- much as The post A "headless Slack": Vercel's new message board lets Claude Code and Codex agents work together appeared first on The New Stack.

## Microsoft positions Copilot as a hub for team collaboration

DevFeed: [Microsoft positions Copilot as a hub for team collaboration](<https://devfeed.tech/articles/microsoft-positions-copilot-as-a-hub-for-team-collaboration-143706.md>)

Original publisher: [Read original article](<https://www.computerworld.com/article/4250734/microsoft-positions-copilot-as-a-hub-for-team-collaboration.html>)

Author: Matthew Finnegan

Published: 2026-11-19T14:46:23Z

Content type: news

Language: en

Sources: [Computerworld](<https://devfeed.tech/sources/computerworld.md>)

Topics: [Multi Agent Systems](<https://devfeed.tech/topics/multi-agent-systems.md>), [AI Chat](<https://devfeed.tech/topics/ai-chat.md>), [generative-ai-tools](<https://devfeed.tech/topics/generative-ai-tools.md>), [microsoft 365](<https://devfeed.tech/topics/microsoft-365.md>), [Microsoft Teams](<https://devfeed.tech/topics/microsoft-teams.md>)

Tags: [agent](<https://devfeed.tech/tags/agent.md>), [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-agent](<https://devfeed.tech/tags/ai-agent.md>), [ai-agent-capabilities](<https://devfeed.tech/tags/ai-agent-capabilities.md>), [ai-assistant](<https://devfeed.tech/tags/ai-assistant.md>), [artificial-intelligence](<https://devfeed.tech/tags/artificial-intelligence.md>), [artificial-intelligence-collaboration-software-generative-ai-microsoft-microsoft-365-office-sui](<https://devfeed.tech/tags/artificial-intelligence-collaboration-software-generative-ai-microsoft-microsoft-365-office-sui.md>), [collaboration](<https://devfeed.tech/tags/collaboration.md>), [collaboration-software](<https://devfeed.tech/tags/collaboration-software.md>), [copilot](<https://devfeed.tech/tags/copilot.md>), [copilot-workspaces](<https://devfeed.tech/tags/copilot-workspaces.md>), [edition-us](<https://devfeed.tech/tags/edition-us.md>), [generative-ai](<https://devfeed.tech/tags/generative-ai.md>), [gold](<https://devfeed.tech/tags/gold.md>), [has](<https://devfeed.tech/tags/has.md>), [ignite](<https://devfeed.tech/tags/ignite.md>), [language-en](<https://devfeed.tech/tags/language-en.md>), [microsoft](<https://devfeed.tech/tags/microsoft.md>), [microsoft-365](<https://devfeed.tech/tags/microsoft-365.md>), [office-suites](<https://devfeed.tech/tags/office-suites.md>), [productivity](<https://devfeed.tech/tags/productivity.md>), [productivity-software](<https://devfeed.tech/tags/productivity-software.md>), [storytype-newsanalysis](<https://devfeed.tech/tags/storytype-newsanalysis.md>), [team](<https://devfeed.tech/tags/team.md>), [team-collaboration](<https://devfeed.tech/tags/team-collaboration.md>), [team-productivity](<https://devfeed.tech/tags/team-productivity.md>), [updates](<https://devfeed.tech/tags/updates.md>), [vendors-and-providers](<https://devfeed.tech/tags/vendors-and-providers.md>)

### AI overview

Microsoft's Copilot Workspaces replaces Copilot Notebooks with a shared project space that retains file-based questions, document drafting, and audio overviews, while adding collaborative documents with live cursors and shared context. Background Autopilot agents are planned; Workspaces is in early access for Microsoft Frontier Copilot customers, with OneNote availability to follow. Analysts describe team collaboration as a potential productivity gain but expect gradual adoption until agents are reliable, and point to security, access-control, data-governance, and vendor lock-in concerns. The article also reports that Office in Copilot brings editable Office apps to paid Copilot subscriptions, while Microsoft's Auto routes complex work across models to manage performance and cost; analysts say its value depends on real-world results and that routing has not resolved all cost and model-selection challenges.

### Source excerpt

Microsoft has unveiled Copilot Workspaces, a new collaborative environment for employees and AI agents to work together on shared projects. It was one of a range of Copilot updates at Microsoft's Ignite conference this week, including deeper Office integration and new AI agent capabilities, as it seeks to position the AI assistant as a hub for team productivity. Workspaces replaces Copilot Notebooks, announced last year, which let users gather files and other reference materials, then ask Copilot to answer questions, draft documents, and generate audio overviews based on this content. Workspaces retains these capabilities in what Microsoft describes as a "team-first" shared space, where colleagues can collaborate on documents, with live cursors showing what they are working on. Users can also interact with Copilot, with support for Autopilot agents that work continuously in the background coming soon, too. "Until now, AI interactions have mostly been single player," said Jared Spataro, Microsoft's chief marketing officer, Copilot, in a blog post. "Workspaces makes it a truly multiplayer experience, where people and agents drive towards a common goal, with shared context." For some teams, working cooperatively on a project is a key requirement, said Jack Gold, principal analyst at J. Gold Associates. That will ultimately include agents, too, once they are considered robust and able to operate "without causing any issues that are security- or interference- related," he said. "But for most organizations, this will be a slow uptake until it's proven to help productivity," said Gold. "There is significant risk that something could go wrong relying too heavily on AI capabilities." Most organizations still use AI for individual productivity, said Max Goss, senior director analyst at Gartner, but there are signs of a shift toward "a collaborative environment where people and agents work together." "Copilot Workspaces fits that direction well and follows what we've seen othe

## Groundcover launches Agent Investigations, a shared workspace for AI agents and engineers

DevFeed: [Groundcover launches Agent Investigations, a shared workspace for AI agents and engineers](<https://devfeed.tech/articles/groundcover-launches-agent-investigations-a-shared-workspace-for-ai-agents-and-engineers-143694.md>)

Original publisher: [Read original article](<https://siliconangle.com/2026/11/19/groundcover-launches-agent-investigations-a-shared-workspace-for-ai-agents-and-engineers/>)

Author: Duncan Riley

Published: 2026-11-19T14:00:58Z

Content type: news

Language: en

Sources: [SiliconANGLE](<https://devfeed.tech/sources/siliconangle.md>)

Topics: [Multi Agent Systems](<https://devfeed.tech/topics/multi-agent-systems.md>), [agent to agent communication](<https://devfeed.tech/topics/agent-to-agent-communication.md>), [agent observability](<https://devfeed.tech/topics/agent-observability.md>)

Tags: [agent-investigations](<https://devfeed.tech/tags/agent-investigations.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-agents](<https://devfeed.tech/tags/ai-agents.md>), [amazon-web-services](<https://devfeed.tech/tags/amazon-web-services.md>), [anthropic](<https://devfeed.tech/tags/anthropic.md>), [apps](<https://devfeed.tech/tags/apps.md>), [artificial-intelligence](<https://devfeed.tech/tags/artificial-intelligence.md>), [bring-your-own-cloud](<https://devfeed.tech/tags/bring-your-own-cloud.md>), [claude-code](<https://devfeed.tech/tags/claude-code.md>), [codex](<https://devfeed.tech/tags/codex.md>), [coding-agents](<https://devfeed.tech/tags/coding-agents.md>), [engineers](<https://devfeed.tech/tags/engineers.md>), [groundcover](<https://devfeed.tech/tags/groundcover.md>), [incident-response](<https://devfeed.tech/tags/incident-response.md>), [investigator-agent](<https://devfeed.tech/tags/investigator-agent.md>), [kubernetes](<https://devfeed.tech/tags/kubernetes.md>), [model-context-protocol](<https://devfeed.tech/tags/model-context-protocol.md>), [moderator-agent](<https://devfeed.tech/tags/moderator-agent.md>), [news](<https://devfeed.tech/tags/news.md>), [observability](<https://devfeed.tech/tags/observability.md>), [omer-mayer](<https://devfeed.tech/tags/omer-mayer.md>), [one-peak](<https://devfeed.tech/tags/one-peak.md>), [openai](<https://devfeed.tech/tags/openai.md>), [production-incidents](<https://devfeed.tech/tags/production-incidents.md>), [re-invent](<https://devfeed.tech/tags/re-invent.md>), [series-c](<https://devfeed.tech/tags/series-c.md>), [shahar-azulay](<https://devfeed.tech/tags/shahar-azulay.md>), [slack](<https://devfeed.tech/tags/slack.md>), [the-latest](<https://devfeed.tech/tags/the-latest.md>), [top-story-6](<https://devfeed.tech/tags/top-story-6.md>), [yechezkel-rabinovich](<https://devfeed.tech/tags/yechezkel-rabinovich.md>)

### AI overview

Groundcover's Agent Investigations brings its agents, customer coding agents, and on-call engineers into a shared production-incident workspace. An investigation starts when a monitor issue opens, or can be launched in groundcover or from Slack. Its Investigator agent builds a graph of hypotheses and checks them against logs, metrics, traces, and Kubernetes data; a Moderator reviews proposed conclusions and alone can close a hypothesis, returning claims that lack support. Findings include supporting graphs and end in structured assessments that support or refute each hypothesis. External agents such as Claude Code and Codex can read and contribute through groundcover's Model Context Protocol server. Status and assessments appear in the alert's Slack thread, where replies can steer the investigation. Groundcover says telemetry stays in the customer's cloud account. The feature is available to customers with AI enabled on their backends.

### Source excerpt

Observability company groundcover Inc. today announced the launch of Agent Investigations, a shared workspace designed to allow groundcover's artificial intelligence agents, a team's own coding agents and on-call engineers to work production incidents together. Agent Investigations is aimed at the problem of scattered findings as AI agents take on a bigger role in incident response. [...] The post Groundcover launches Agent Investigations, a shared workspace for AI agents and engineers appeared first on SiliconANGLE.

## Google launches Gemini 4 Neon, touting lower costs for complex AI coding tasks

DevFeed: [Google launches Gemini 4 Neon, touting lower costs for complex AI coding tasks](<https://devfeed.tech/articles/google-launches-gemini-4-neon-touting-lower-costs-for-complex-ai-coding-tasks-143171.md>)

Original publisher: [Read original article](<https://www.infoworld.com/article/4250618/google-launches-gemini-4-neon-touting-lower-costs-for-complex-ai-coding-tasks.html>)

Author: Prasanth Aby Thomas

Published: 2026-11-19T09:49:58Z

Content type: news

Language: en

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

Topics: [agentic-coding](<https://devfeed.tech/topics/agentic-coding.md>), [AI-assisted coding](<https://devfeed.tech/topics/ai-assisted-coding.md>), [hierarchical agent systems](<https://devfeed.tech/topics/hierarchical-agent-systems.md>), [Multi Agent Systems](<https://devfeed.tech/topics/multi-agent-systems.md>), [google-antigravity](<https://devfeed.tech/topics/google-antigravity.md>), [harvestbench](<https://devfeed.tech/topics/harvestbench.md>), [Test-driven development](<https://devfeed.tech/topics/tdd.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [ai-coding](<https://devfeed.tech/tags/ai-coding.md>), [ai-coding-agents](<https://devfeed.tech/tags/ai-coding-agents.md>), [antigravity](<https://devfeed.tech/tags/antigravity.md>), [api](<https://devfeed.tech/tags/api.md>), [api-pricing](<https://devfeed.tech/tags/api-pricing.md>), [artificial-analysis](<https://devfeed.tech/tags/artificial-analysis.md>), [artificial-analysis-intelligence-index](<https://devfeed.tech/tags/artificial-analysis-intelligence-index.md>), [artificial-intelligence](<https://devfeed.tech/tags/artificial-intelligence.md>), [artificial-intelligence-development-tools-software-development](<https://devfeed.tech/tags/artificial-intelligence-development-tools-software-development.md>), [coding-agents](<https://devfeed.tech/tags/coding-agents.md>), [context-window](<https://devfeed.tech/tags/context-window.md>), [cost](<https://devfeed.tech/tags/cost.md>), [costs](<https://devfeed.tech/tags/costs.md>), [debugging](<https://devfeed.tech/tags/debugging.md>), [development-tools](<https://devfeed.tech/tags/development-tools.md>), [enterprise](<https://devfeed.tech/tags/enterprise.md>), [evaluations](<https://devfeed.tech/tags/evaluations.md>), [gemini](<https://devfeed.tech/tags/gemini.md>), [gemini-4](<https://devfeed.tech/tags/gemini-4.md>), [gemini-4-carbon](<https://devfeed.tech/tags/gemini-4-carbon.md>), [gemini-4-neon](<https://devfeed.tech/tags/gemini-4-neon.md>), [google](<https://devfeed.tech/tags/google.md>), [language-en](<https://devfeed.tech/tags/language-en.md>), [software-development](<https://devfeed.tech/tags/software-development.md>), [storytype-news](<https://devfeed.tech/tags/storytype-news.md>)

### AI overview

Google says Gemini 4 Neon can debug and refactor across large code repositories and, in Antigravity, coordinate parallel Gemini 4 Hydrogen subagents. Positioned between Gemini 4 Carbon for demanding projects and Hydrogen for speed, Neon offers four reasoning levels and a context window up to one million tokens. Its listed API prices are $3 per million input tokens, $15 per million output tokens, and $0.15 per million cached input tokens. Google reports 32% lower cost per task than Carbon in one evaluation and 50%-80% savings against competing models on two other benchmarks; these are company-reported results. The excerpt says enterprises should assess total cost per successful task, code quality, environment compatibility, productivity, and human intervention--not benchmark scores alone. It also notes production risks: generated code can be hard for developers to understand, agents may make conflicting changes, and reliability on complex or long-running tasks remains a concern. Experts describe supervised autonomy, developer oversight, and functional, end-to-end, and regression testing as important for production use.

### Source excerpt

Google is rolling out Gemini 4 Neon, a new model designed for complex software engineering tasks that the company says can complete work more economically than larger models, as it seeks to expand the use of AI coding agents among enterprise developers. Neon can work across large code repositories, performing multi-file debugging and refactoring while making targeted changes to existing code, according to Google. Within Google's Antigravity development environment, Neon can also orchestrate multiple Gemini 4 Hydrogen subagents working in parallel. Neon ranked first on the Artificial Analysis Coding Agent Index with a score of 58.6, while achieving 65.2% on Terminal-Bench 4.1, a benchmark used to evaluate AI agents performing tasks in terminal environments, Google said. Google is positioning Neon between Gemini 4 Carbon, designed for demanding projects, and Gemini 4 Hydrogen, which prioritizes faster execution. The company has set Neon's API pricing at $3 per million input tokens and $15 per million output tokens. Cached inputs cost $0.15 per million tokens, while the model supports a context window of up to one million tokens. Google said Neon delivered a 32% lower cost per task than Gemini 4 Carbon at the default high reasoning setting in Artificial Analysis Intelligence Index evaluations. It also reported savings of roughly 50% to 80% against leading competing models on the Vals Index and Agent Arena benchmarks. Neon offers four reasoning levels, allowing developers to adjust computational effort according to workload requirements. The model is being made available through the Gemini API in Google AI Studio and through Gemini for Business, with access also expanding to Google's Antigravity development platform. Lower costs could shift enterprise model choices Production software development often requires longer context windows, which can push token consumption beyond initial estimates, said Anand Joshi, managing director of market intelligence firm JP Data. This,

## Arbor: How Search Policy Shapes Agent Behavior in System Optimization

DevFeed: [Arbor: How Search Policy Shapes Agent Behavior in System Optimization](<https://devfeed.tech/articles/arbor-how-search-policy-shapes-agent-behavior-in-system-optimization-142530.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2606.12563>)

Author: Neha Prakriya, Chaojun Hou, Zheng Gong, Huasha Zhao, Yanyuan Qin, Chris Cai, Xi Zhao, Zhenyu Gu, Emad Barsoum

Published: 2026-11-19T05:00:00Z

Content type: article

Language: en

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

Topics: [LLM optimization](<https://devfeed.tech/topics/llm-optimization.md>), [AI Agent](<https://devfeed.tech/topics/ai-agent.md>), [Multi Agent Systems](<https://devfeed.tech/topics/multi-agent-systems.md>), [Agent Harness](<https://devfeed.tech/topics/agent-harness.md>), [Post-training optimization](<https://devfeed.tech/topics/post-training-optimization.md>)

Tags: [agent](<https://devfeed.tech/tags/agent.md>), [behavior](<https://devfeed.tech/tags/behavior.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [optimization](<https://devfeed.tech/tags/optimization.md>), [policy](<https://devfeed.tech/tags/policy.md>), [search](<https://devfeed.tech/tags/search.md>), [system](<https://devfeed.tech/tags/system.md>)

### AI overview

Arbor organizes accelerator optimization as an explicit tree that agents can traverse, revisit, and deepen. Its shared harness provides containerized isolation, automatic rollback, and end-to-end validation; search options include scored bandit traversal, parallel swarms, and depth-first sweeps. The abstract reports gains of 40%-193% across six production inference models on two GPU generations, 42.8% for LLM training, and 41% for recommendation training. In controlled comparisons using the same agent, tree, and tools, bandit search gained 30.1% through targeted framework fixes, sweeps 26.4% through deep kernel rewrites, and swarms 33.4% by combining independent changes. A loop that chose its own targets gained 14% and wrote four times more code per percentage point of improvement than Arbor's structured policies. The paper also introduces an evaluation framework covering efficiency, grounding, robustness, and depth.

### Source excerpt

arXiv:2606.12563v2 Announce Type: replace Abstract: Achieving peak performance on modern accelerators requires coordinated optimization across kernels, operator fusion, KV-cache management, quantization, scheduling, and communication overlap, a process that demands weeks of expert effort per model and hardware platform. We present Arbor, a system that gives autonomous agents an explicit optimization tree to reason over, backtrack through, and deepen with experience, with pluggable search policies, scored bandit traversal, parallel agent swarms, and depth-first sweep, sharing a common harness of containerized isolation, automatic rollback, and end-to-end validation. Arbor generalizes across domains: +40% to +193% on six production inference models across two GPU generations, +42.8% on LLM training, and +41% on recommendation training, where agents autonomously wrote kernel-level and framework-level optimizations spanning thousands of lines of code. In controlled ablations where every search policy receives the same agent, tree, and tools, we find that search structure shapes both the magnitude and the nature of the optimizations. The bandit achieves +30.1% through targeted framework fixes, the sweep +26.4% through deep kernel rewrites, and the swarm +33.4% by compounding independent changes. An agent-driven loop that receives the same harness, tools, and information, but selects its own targets reaches +14%, writing 4x more code per percentage point of improvement than Arbor's structured search policies. We additionally introduce an evaluation framework for autonomous loop-based agents spanning efficiency, grounding, robustness, and depth, designed to characterize agent search behavior across long-running optimization campaigns.

## OpenKAGE: Open-Ended Lifelong Learning in the Open World via Knowledge-Sharing Agent-Group Evolution

DevFeed: [OpenKAGE: Open-Ended Lifelong Learning in the Open World via Knowledge-Sharing Agent-Group Evolution](<https://devfeed.tech/articles/openkage-open-ended-lifelong-learning-in-the-open-world-via-knowledge-sharing-agent-group-evolution-142775.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.24302>)

Author: Wenhao Yuan, Longhui Yuan, Zexi Jia, Ningzhe Shi, Jingwei Li, Shipeng Cen, Pengcheng Luo, Jie Zhou, Jinchao Zhang

Published: 2026-11-19T05:00:00Z

Content type: article

Language: en

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

Topics: [Multi Agent Systems](<https://devfeed.tech/topics/multi-agent-systems.md>), [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [knowledge-management](<https://devfeed.tech/topics/knowledge-management.md>), [knowledge-engineering](<https://devfeed.tech/topics/knowledge-engineering.md>)

Tags: [advanced](<https://devfeed.tech/tags/advanced.md>), [agent](<https://devfeed.tech/tags/agent.md>), [agents](<https://devfeed.tech/tags/agents.md>), [artificial-intelligence](<https://devfeed.tech/tags/artificial-intelligence.md>), [autonomous](<https://devfeed.tech/tags/autonomous.md>), [autonomous-agents](<https://devfeed.tech/tags/autonomous-agents.md>), [capabilities](<https://devfeed.tech/tags/capabilities.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cs-ma](<https://devfeed.tech/tags/cs-ma.md>), [evolution](<https://devfeed.tech/tags/evolution.md>), [experience](<https://devfeed.tech/tags/experience.md>), [exploration](<https://devfeed.tech/tags/exploration.md>), [framework](<https://devfeed.tech/tags/framework.md>), [graph](<https://devfeed.tech/tags/graph.md>), [groups](<https://devfeed.tech/tags/groups.md>), [improvement](<https://devfeed.tech/tags/improvement.md>), [knowledge](<https://devfeed.tech/tags/knowledge.md>), [knowledge-sharing](<https://devfeed.tech/tags/knowledge-sharing.md>), [learning](<https://devfeed.tech/tags/learning.md>), [open](<https://devfeed.tech/tags/open.md>), [sharing](<https://devfeed.tech/tags/sharing.md>), [world](<https://devfeed.tech/tags/world.md>)

### AI overview

OpenKAGE enables groups of agents to keep exploring open worlds and build on one another's experience. It separates situated memories from transferable experiences and skills, retaining conditions for when those skills apply. Textual experiences are consolidated into a shared knowledge graph, while executable skills are shared verbatim. In Minecraft, the framework reportedly sustained group exploration and supported advanced technological milestones. Its accumulated knowledge also improved survival and exploration when transferred to a newly initialized group using a different backbone model.

### Source excerpt

arXiv:2611.24302v1 Announce Type: new Abstract: Building autonomous agents that continually explore open worlds and acquire new capabilities through experience is a long-standing aspiration in artificial intelligence. Existing research often pursues lifelong learning within predefined tasks, curricula, or objectives, with self-improvement largely confined to individual agents. We introduce OpenKAGE, an agent-group evolution framework for open-ended lifelong learning. Within this framework, agents autonomously explore open worlds and continually acquire new capabilities by accumulating and reusing knowledge from their own interactions and the experience of others. OpenKAGE builds on two key mechanisms: (1) a two-layer knowledge representation, with a memory layer for situated memories and an experience layer for transferable experience and skills that retains the applicability conditions needed for reuse; and (2) a knowledge-sharing mechanism that semantically consolidates textual experience into a continuously evolving shared knowledge graph, while executable skills are shared verbatim. In Minecraft, OpenKAGE supports open-ended lifelong learning, enabling agent groups to sustain exploration and reach advanced technological milestones. Furthermore, the accumulated knowledge can be transferred to a newly initialized agent group on a different backbone model, improving its survival and exploration progress.

## Learning to Interact in Multi-Agent Self-Play for Controllable Autonomous Driving Scenario Generation

DevFeed: [Learning to Interact in Multi-Agent Self-Play for Controllable Autonomous Driving Scenario Generation](<https://devfeed.tech/articles/learning-to-interact-in-multi-agent-self-play-for-controllable-autonomous-driving-scenario-generation-143574.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.24876>)

Author: Beyazit Yalcinkaya, Ethan Pronovost, Maximilian Naumann, Marcell Vazquez-Chanlatte

Published: 2026-11-19T05:00:00Z

Content type: article

Language: en

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

Topics: [Multi Agent Systems](<https://devfeed.tech/topics/multi-agent-systems.md>), [autonomous vehicles](<https://devfeed.tech/topics/autonomous-vehicles.md>)

Tags: [abstract](<https://devfeed.tech/tags/abstract.md>), [adversarial](<https://devfeed.tech/tags/adversarial.md>), [agent](<https://devfeed.tech/tags/agent.md>), [approach](<https://devfeed.tech/tags/approach.md>), [arxiv](<https://devfeed.tech/tags/arxiv.md>), [autonomous](<https://devfeed.tech/tags/autonomous.md>), [autonomous-driving](<https://devfeed.tech/tags/autonomous-driving.md>), [autonomous-vehicle](<https://devfeed.tech/tags/autonomous-vehicle.md>), [av](<https://devfeed.tech/tags/av.md>), [behaviors](<https://devfeed.tech/tags/behaviors.md>), [but](<https://devfeed.tech/tags/but.md>), [cases](<https://devfeed.tech/tags/cases.md>), [challenge](<https://devfeed.tech/tags/challenge.md>), [complex](<https://devfeed.tech/tags/complex.md>), [critical](<https://devfeed.tech/tags/critical.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [cs-ro](<https://devfeed.tech/tags/cs-ro.md>), [driving](<https://devfeed.tech/tags/driving.md>), [generation](<https://devfeed.tech/tags/generation.md>), [learning](<https://devfeed.tech/tags/learning.md>), [multi-agent](<https://devfeed.tech/tags/multi-agent.md>), [play](<https://devfeed.tech/tags/play.md>)

### AI overview

The framework targets safety-critical driving scenarios that static map-location goals in existing goal-conditioned self-play do not reliably produce, including aggressive tailgating and adversarial cut-offs. It adds agent-relative dynamic goals and conditions policies on them to enable targeted scenario synthesis. The abstract reports that this approach generates interactive behaviors static-goal baselines cannot simulate, offering a tool for long-tail autonomous vehicle testing.

### Source excerpt

arXiv:2611.24876v1 Announce Type: cross Abstract: Large-scale, multi-agent self-play trains robust driving policies effectively in simulation, but controlling these models to generate specific, safety-critical edge cases remains a key challenge. Existing goal-conditioned self-play frameworks rely primarily on static map-location goals and fail to reliably produce complex agent interactions such as aggressive tailgating or adversarial cut-offs. These agent interactions are necessary for rigorous autonomous vehicle (AV) testing. To address this, we present an extended multi-agent self-play framework that introduces agent-relative dynamic goals. By conditioning policies on this extended goal representation, our framework enables targeted, controllable scenario synthesis. We demonstrate that our approach successfully generates interactive driving behaviors that static-goal baselines cannot simulate, providing a flexible tool for long-tail scenario generation in AV testing.

## Colosseum: Auditing Collusion in Cooperative Multi-Agent Systems

DevFeed: [Colosseum: Auditing Collusion in Cooperative Multi-Agent Systems](<https://devfeed.tech/articles/colosseum-auditing-collusion-in-cooperative-multi-agent-systems-142508.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2602.15198>)

Author: Mason Nakamura, Abhinav Kumar, Saswat Das, Sahar Abdelnabi, Saaduddin Mahmud, Ferdinando Fioretto, Shlomo Zilberstein, Eugene Bagdasarian

Published: 2026-11-19T05:00:00Z

Content type: article

Language: en

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

Topics: [Multi Agent Systems](<https://devfeed.tech/topics/multi-agent-systems.md>), [agent to agent communication](<https://devfeed.tech/topics/agent-to-agent-communication.md>), [LLM security](<https://devfeed.tech/topics/llm-security.md>)

Tags: [auditing](<https://devfeed.tech/tags/auditing.md>), [coalition](<https://devfeed.tech/tags/coalition.md>), [communication](<https://devfeed.tech/tags/communication.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cs-cl](<https://devfeed.tech/tags/cs-cl.md>), [cs-ma](<https://devfeed.tech/tags/cs-ma.md>), [decision-making](<https://devfeed.tech/tags/decision-making.md>), [framework](<https://devfeed.tech/tags/framework.md>), [llm-agents](<https://devfeed.tech/tags/llm-agents.md>), [multi-agent-systems](<https://devfeed.tech/tags/multi-agent-systems.md>), [network](<https://devfeed.tech/tags/network.md>), [plan](<https://devfeed.tech/tags/plan.md>), [safety](<https://devfeed.tech/tags/safety.md>), [secret](<https://devfeed.tech/tags/secret.md>), [strategies](<https://devfeed.tech/tags/strategies.md>), [tactics](<https://devfeed.tech/tags/tactics.md>), [tasks](<https://devfeed.tech/tags/tasks.md>)

### AI overview

Colosseum audits collusion among cooperative LLM agents by grounding cooperation in a formal multi-agent decision framework and measuring action-based behavior through regret against the cooperative optimum, alongside communication-based behavior. It supports audits across benign settings, coalition objectives, persuasion tactics, and network topologies. The abstract reports that secret communication channels reveal a propensity to collude in most out-of-the-box models, termed "emergent collusion"; it also finds "collusion on paper," where agents discuss plans to collude but often choose non-collusive actions. The supplied abstract says the framework studies factors affecting collusion and possible mitigation strategies, but does not specify those strategies.

### Source excerpt

arXiv:2602.15198v3 Announce Type: replace-cross Abstract: Multi-agent systems, where LLM agents communicate through free-form language, enable sophisticated coordination for solving complex cooperative tasks. This surfaces a unique safety problem when a group of agents forms a coalition and colludes to pursue secondary goals and degrade the joint objective. In this paper, we present Colosseum, a framework for auditing LLM agents' collusive behavior in multi-agent settings. We ground how agents cooperate through a formal multi-agent decision-making framework and measure action-based collusive behavior in actions via regret relative to the cooperative optimum and compare it with communication-based collusive behavior. Colosseum enables audits of LLM agents for collusion under benign settings, different coalition objectives, persuasion tactics, and network topologies. We then introduce a new behavioral probe by creating secret communication channels between agents, showing that most out-of-the-box models exhibit a propensity to collude under this probe, which we term emergent collusion. Furthermore, we discover ``collusion on paper'' when agents plan to collude in text but often pick non-collusive actions. Colosseum provides a new way to audit collusion in cooperative multi-agent systems while presenting observations about how collusion emerges, what affects collusion efficacy, and which strategies may mitigate it.

## Beyond Corpus-Driven Imitation: Evolving Musical Mindsets in the Agentic Orchestra via Quantum Reinforcement Learning

DevFeed: [Beyond Corpus-Driven Imitation: Evolving Musical Mindsets in the Agentic Orchestra via Quantum Reinforcement Learning](<https://devfeed.tech/articles/beyond-corpus-driven-imitation-evolving-musical-mindsets-in-the-agentic-orchestra-via-quantum-reinforcement-learning-142773.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.24290>)

Author: Eduardo Reck Miranda, Moein Fahmideh Vatandoost

Published: 2026-11-19T05:00:00Z

Content type: article

Language: en

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

Topics: [Reinforcement learning](<https://devfeed.tech/topics/reinforcement-learning.md>), [Quantum Computing](<https://devfeed.tech/topics/quantum-computing.md>), [Multi Agent Systems](<https://devfeed.tech/topics/multi-agent-systems.md>), [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [generalization in machine learning](<https://devfeed.tech/topics/generalization-in-machine-learning.md>)

Tags: [adaptive](<https://devfeed.tech/tags/adaptive.md>), [agent](<https://devfeed.tech/tags/agent.md>), [agentic](<https://devfeed.tech/tags/agentic.md>), [agents](<https://devfeed.tech/tags/agents.md>), [circuits](<https://devfeed.tech/tags/circuits.md>), [composition](<https://devfeed.tech/tags/composition.md>), [computing](<https://devfeed.tech/tags/computing.md>), [creativity](<https://devfeed.tech/tags/creativity.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [decision](<https://devfeed.tech/tags/decision.md>), [entanglement](<https://devfeed.tech/tags/entanglement.md>), [environment](<https://devfeed.tech/tags/environment.md>), [experiments](<https://devfeed.tech/tags/experiments.md>), [hardware](<https://devfeed.tech/tags/hardware.md>), [ibm-quantum](<https://devfeed.tech/tags/ibm-quantum.md>), [interaction](<https://devfeed.tech/tags/interaction.md>), [interactive](<https://devfeed.tech/tags/interactive.md>), [learning](<https://devfeed.tech/tags/learning.md>), [midi](<https://devfeed.tech/tags/midi.md>), [quant-ph](<https://devfeed.tech/tags/quant-ph.md>), [quantum](<https://devfeed.tech/tags/quantum.md>), [reinforcement-learning](<https://devfeed.tech/tags/reinforcement-learning.md>)

### AI overview

The agentic orchestra uses quantum reinforcement learning to develop musical agents through interaction with a musical environment rather than large-dataset imitation. Parameterised quantum circuits operate in a hybrid quantum-classical loop; atomistic agents process pitch and rhythm separately, while holistic agents treat pitch and duration as unified note events. Musically grounded reward functions can be combined and weighted to shape agents' distinct compositional mindsets. The abstract reports generalisation to unseen material in interactive and offline MIDI modes, and musically meaningful learning on IBM quantum hardware. It presents the agents as adaptive musical partners; quantum computers remain in development.

### Source excerpt

arXiv:2611.24290v1 Announce Type: new Abstract: This paper presents a framework for computer-aided music composition and performance based on quantum reinforcement learning and multi-agent interaction. We introduce the agentic orchestra, where musical agents evolve distinct mindsets through trial-and-error engagement with a musical environment, rather than through training on large datasets. The agents are implemented as parameterised quantum circuits. They evolve distinct compositional behaviours, referred to as mindsets. This enables the exploration of musical decision spaces using quantum superposition and entanglement within a hybrid quantum-classical loop. We present two complementary agent architectures: atomistic agents, which process pitch and rhythm independently, and holistic agents, which handle pitch and duration as unified note events. Mindsets are shaped through musically grounded reward functions, which can be combined and weighted to develop different mindsets across agents. The resulting system positions quantum computing agents less as autonomous composers and more as adaptive musical partners, each developing its own musical personality through interaction rather than imitation. Demonstrations show how agents generalise their learned behaviour to previously unseen material, operating in interactive and offline batch modes using MIDI-encoded music. While quantum computers are still in development, experiments conducted on IBM quantum hardware confirmed that musically meaningful learning is achievable with existing quantum computers. For composers and performers, the agentic orchestra opens new possibilities for emergent, process-oriented musical creativity, offering a scalable foundation for quantum computer-aided music composition as quantum computing technology continues to advance.

[Next page](<https://devfeed.tech/topics/multi-agent-systems.md?cursor=WyIyMDI2LTExLTE5VDA1OjAwOjAwKzAwOjAwIiwgImM4OGNjMjBmLTJhYTYtNGRlZC1hMTMyLTBkMWY4OGMwMTAyNCJd>)