# agentic workflows

Published articles for agentic workflows.

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

## Best API Catalogs and Registries for AI Agents

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

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

Author: Swytchcode Team

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

Content type: comparison

Language: en

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

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

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

### AI overview

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

### Source excerpt

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

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

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

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

Author: Liam Kearns

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

Content type: article

Language: en

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

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

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

### AI overview

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

### Source excerpt

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

## The FrontierOR Challenge: Agentic Algorithm Design for Operations Research

DevFeed: [The FrontierOR Challenge: Agentic Algorithm Design for Operations Research](<https://devfeed.tech/articles/the-frontieror-challenge-agentic-algorithm-design-for-operations-research-145636.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.26171>)

Author: Hai Wang, Bretislav Hajek, Chonghe Jiang, Minwei Kong, Ao Qu, Huatian Gong, Bo Dong, Cynthia Barnhart, Jinhua Zhao

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

Content type: release

Language: en

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

Topics: [Operations research and optimization](<https://devfeed.tech/topics/operations-research-and-optimization.md>), [llm-reasoning](<https://devfeed.tech/topics/llm-reasoning.md>), [Loop Engineering](<https://devfeed.tech/topics/loop-engineering.md>)

Tags: [2](<https://devfeed.tech/tags/2.md>), [abstract](<https://devfeed.tech/tags/abstract.md>), [agentic](<https://devfeed.tech/tags/agentic.md>), [agentic-workflows](<https://devfeed.tech/tags/agentic-workflows.md>), [agents](<https://devfeed.tech/tags/agents.md>), [algorithm](<https://devfeed.tech/tags/algorithm.md>), [algorithms](<https://devfeed.tech/tags/algorithms.md>), [application](<https://devfeed.tech/tags/application.md>), [arxiv](<https://devfeed.tech/tags/arxiv.md>), [benchmark](<https://devfeed.tech/tags/benchmark.md>), [build](<https://devfeed.tech/tags/build.md>), [but](<https://devfeed.tech/tags/but.md>), [can](<https://devfeed.tech/tags/can.md>), [categories](<https://devfeed.tech/tags/categories.md>), [challenge](<https://devfeed.tech/tags/challenge.md>), [code](<https://devfeed.tech/tags/code.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [design](<https://devfeed.tech/tags/design.md>), [math-oc](<https://devfeed.tech/tags/math-oc.md>), [operations](<https://devfeed.tech/tags/operations.md>), [operations-research](<https://devfeed.tech/tags/operations-research.md>), [research](<https://devfeed.tech/tags/research.md>)

### AI overview

The FrontierOR Challenge tests whether agentic workflows can design algorithms that scale across diverse operations research problems. In the benchmark's one-shot evaluation, the strongest model matched Gurobi within 1% of its objective and without being slower on only 39% of large instances. Stage 1 releases 60 of 180 audited problems across six application categories and five formulation types in weekly rounds of 15; Stage 2 adds new problems with unseen instances. The separately ranked Main track runs submissions in a network-isolated sandbox using only open-source dependencies. The Self-hosted track lets teams use any software on their own machines during a timed window. Solutions must be feasible; scores compare objectives with a frozen known reference and average results over hidden instances.

### Source excerpt

arXiv:2611.26171v1 Announce Type: new Abstract: Operations research (OR) relies on algorithms that experts tailor to each problem: a new routing, scheduling or network design problem can take weeks of specialist work before it is solved well at scale. Large language model (LLM) agents now write, test and improve code, but whether they can design algorithms that scale to realistic instances is open: in the FrontierOR benchmark's one-shot evaluation, the strongest model matches Gurobi, with an objective within 1% of Gurobi's and no slower, on only 39% of the large instances. The FrontierOR Challenge asks teams to build agentic workflows that design, test, and improve algorithms for many optimization problems at once. Stage 1 releases 60 of the benchmark's 180 audited problems, spanning six application categories and five formulation types, in weekly rounds of 15; Stage 2 introduces new problems outside the benchmark, with unseen instances. Two tracks are ranked separately: in the Main track we run the submitted algorithms in a network-isolated sandbox with open-source dependencies only; in the Self-hosted track teams solve the instances on their own machines, with any software, within a timed window. Every solution is checked for feasibility, and a feasible solution scores the ratio of its objective to a frozen known reference, averaged over hidden instances.

## How Dynatrace and AWS create shared context for AI-powered operations

DevFeed: [How Dynatrace and AWS create shared context for AI-powered operations](<https://devfeed.tech/articles/how-dynatrace-and-aws-create-shared-context-for-ai-powered-operations-146204.md>)

Original publisher: [Read original article](<https://www.dynatrace.com/news/blog/how-dynatrace-and-aws-create-shared-context-for-ai-powered-operations/>)

Author: Erick Leon

Published: 2026-11-19T21:18:34Z

Content type: release

Language: en

Sources: [Dynatrace news](<https://devfeed.tech/sources/dynatrace-news.md>)

Topics: [dynatrace](<https://devfeed.tech/topics/dynatrace.md>), [AI-Ready Data](<https://devfeed.tech/topics/ai-ready-data.md>), [DevOps](<https://devfeed.tech/topics/devops.md>)

Tags: [agent](<https://devfeed.tech/tags/agent.md>), [agent-integration](<https://devfeed.tech/tags/agent-integration.md>), [agentcore](<https://devfeed.tech/tags/agentcore.md>), [agentic](<https://devfeed.tech/tags/agentic.md>), [agentic-ai](<https://devfeed.tech/tags/agentic-ai.md>), [agentic-systems](<https://devfeed.tech/tags/agentic-systems.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-assisted](<https://devfeed.tech/tags/ai-assisted.md>), [ai-powered](<https://devfeed.tech/tags/ai-powered.md>), [ai-ready-data](<https://devfeed.tech/tags/ai-ready-data.md>), [ai-workloads](<https://devfeed.tech/tags/ai-workloads.md>), [aws](<https://devfeed.tech/tags/aws.md>), [aws-re-invent](<https://devfeed.tech/tags/aws-re-invent.md>), [context](<https://devfeed.tech/tags/context.md>), [data](<https://devfeed.tech/tags/data.md>), [data-competency](<https://devfeed.tech/tags/data-competency.md>), [dynatrace](<https://devfeed.tech/tags/dynatrace.md>), [operations](<https://devfeed.tech/tags/operations.md>), [partners](<https://devfeed.tech/tags/partners.md>), [telemetry](<https://devfeed.tech/tags/telemetry.md>)

### AI overview

Dynatrace says its AWS Data Competency recognizes its expertise in connecting AWS telemetry with the runtime topology and production evidence used to operate AI workloads. It describes ingesting AWS signals through the Clouds App into Grail for analysis alongside service relationships, and extending observability to AI workloads and agentic workflows, including Amazon Bedrock AgentCore. Operational integrations put that context to work: Kiro Agent can use vulnerability signals to propose fixes, open pull requests, and verify remediation; AWS DevOps Agent uses Dynatrace context in incident investigations; and the SRE Agent can create root-cause analyses, with human approval where needed. Dynatrace reports joint users have seen up to a 70% reduction in MTTR. The text presents the AWS competencies as third-party validation and frames human oversight as part of the move toward autonomous operations.

### Source excerpt

We're pleased to announce that Dynatrace has achieved the AWS Data Competency, recognizing our expertise in building unified, AI-ready data foundations on AWS. Building and scaling on AWS means managing a vast, continuous stream of cloud telemetry and putting that data to work to drive better and faster outcomes. AI workloads need trustworthy runtime data, [...] The post How Dynatrace and AWS create shared context for AI-powered operations appeared first on Dynatrace news.

## 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 thinks it can make agentic AI work for the whole company, not just you

DevFeed: [Microsoft thinks it can make agentic AI work for the whole company, not just you](<https://devfeed.tech/articles/microsoft-thinks-it-can-make-agentic-ai-work-for-the-whole-company-not-just-you-143167.md>)

Original publisher: [Read original article](<https://www.techspot.com/news/114611-microsoft-thinks-can-make-agentic-ai-work-whole.html>)

Author: Bob O'Donnell

Published: 2026-11-19T12:32:00Z

Content type: article

Language: en

Sources: [TechSpot](<https://devfeed.tech/sources/techspot.md>)

Topics: [Agentic AI](<https://devfeed.tech/topics/what-is-agentic-ai.md>), [workflow automation](<https://devfeed.tech/topics/workflow-automation.md>), [microsoft 365](<https://devfeed.tech/topics/microsoft-365.md>), [Frontier AI](<https://devfeed.tech/topics/frontier-ai.md>), [Arm](<https://devfeed.tech/topics/arm.md>)

Tags: [agentic](<https://devfeed.tech/tags/agentic.md>), [agentic-ai](<https://devfeed.tech/tags/agentic-ai.md>), [agentic-workflows](<https://devfeed.tech/tags/agentic-workflows.md>), [agentic-workloads](<https://devfeed.tech/tags/agentic-workloads.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-agent](<https://devfeed.tech/tags/ai-agent.md>), [ai-infrastructure](<https://devfeed.tech/tags/ai-infrastructure.md>), [ai-investments](<https://devfeed.tech/tags/ai-investments.md>), [ai-scaling](<https://devfeed.tech/tags/ai-scaling.md>), [ai-tools](<https://devfeed.tech/tags/ai-tools.md>), [ai-transparency](<https://devfeed.tech/tags/ai-transparency.md>), [arm](<https://devfeed.tech/tags/arm.md>), [autopilot](<https://devfeed.tech/tags/autopilot.md>), [cobalt-200](<https://devfeed.tech/tags/cobalt-200.md>), [coding](<https://devfeed.tech/tags/coding.md>), [company](<https://devfeed.tech/tags/company.md>), [connectors](<https://devfeed.tech/tags/connectors.md>), [context](<https://devfeed.tech/tags/context.md>), [copilot](<https://devfeed.tech/tags/copilot.md>), [enterprise](<https://devfeed.tech/tags/enterprise.md>), [ignite](<https://devfeed.tech/tags/ignite.md>), [microsoft](<https://devfeed.tech/tags/microsoft.md>), [opinion](<https://devfeed.tech/tags/opinion.md>), [work](<https://devfeed.tech/tags/work.md>)

### AI overview

Microsoft is assembling tools to extend agentic AI from individual use to organization-wide workflows, though the article says scaling will take time. Copilot Workspaces lets teams build and edit ongoing projects using shared Office documents and Teams threads; Copilot's Today mode offers individual task reminders and is in private preview. Microsoft IQ adds a contextual layer above Microsoft Graph, combining several IQ services and more than 350 connectors intended to link and prepare organizational data for agents. A Salesforce partnership, Copilotforce, would connect Salesforce data and skills through MCP. For cost and deployment flexibility, Microsoft says its MAI-Code-2 offers 90% of current frontier models' coding capability at smaller size, while Microsoft-Decision-1.1 routes task components to suitable, cost-effective models across cloud, on-premises and edge environments. The article notes competing routing efforts and that more work remains. Security and infrastructure announcements accompany the software, but the transition to enterprise-scale use is not immediate.

### Source excerpt

While there's been a tremendous amount of excitement surrounding agentic AI over the last year or two, the vast majority of the attention has focused on individual use of these tools. Everywhere you look, it seems, you can find stories of people who have done amazing work on their own... Read Entire Article

## Reliability by Architecture: Agentic Workflows for Validated Multi-Physics Simulation from Natural Language

DevFeed: [Reliability by Architecture: Agentic Workflows for Validated Multi-Physics Simulation from Natural Language](<https://devfeed.tech/articles/reliability-by-architecture-agentic-workflows-for-validated-multi-physics-simulation-from-natural-language-142659.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.23473>)

Author: S{\\o}ren Taverniers, Eric Darve, Hamdi A. Tchelepi

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

Content type: news

Language: en

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

Topics: [agentic workflows](<https://devfeed.tech/topics/agentic-workflows.md>), [Large Language Model](<https://devfeed.tech/topics/llm.md>)

Tags: [agentic](<https://devfeed.tech/tags/agentic.md>), [agentic-workflows](<https://devfeed.tech/tags/agentic-workflows.md>), [co2](<https://devfeed.tech/tags/co2.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cs-ce](<https://devfeed.tech/tags/cs-ce.md>), [flow](<https://devfeed.tech/tags/flow.md>), [large-language-models-llms](<https://devfeed.tech/tags/large-language-models-llms.md>), [natural-language](<https://devfeed.tech/tags/natural-language.md>), [physics](<https://devfeed.tech/tags/physics.md>), [physics-comp-ph](<https://devfeed.tech/tags/physics-comp-ph.md>), [reliability](<https://devfeed.tech/tags/reliability.md>), [simulation](<https://devfeed.tech/tags/simulation.md>), [simulator](<https://devfeed.tech/tags/simulator.md>)

### AI overview

The workflow assigns LLMs to interpret requests and simulator diagnostics, fill input components not covered by construction rules, and propose repairs; deterministic routines build supported components and check inputs, edits, and results. In 80 attempts across two GEOS CO2-storage flow problems, grounding increased structurally valid inputs from 5/20 to 20/20, while all 20/20 were accepted only with complete rule-based input preparation. Local repairs fixed three seeded defects without changing valid inputs. Supporting tests also found cases that passed physics checks but differed from the problem description or reference results, showing that physics checks alone did not establish fidelity.

### Source excerpt

arXiv:2611.23473v1 Announce Type: cross Abstract: Preparing, executing, and validating strongly coupled multi-physics simulations require expert time. Agentic workflows use large language models (LLMs) to coordinate them from natural-language descriptions, but reliability requires checks of physical consistency and fidelity to the problem description. Our agentic harness implements explicit task allocation: LLMs interpret user requests and simulator diagnostics, generate input components not covered by predefined construction rules, and propose repairs, while deterministic routines construct supported components and check inputs, edits, and results. We evaluate CO2-storage problems using the multi-physics simulator GEOS, from compositional flow to flow-poromechanics with frictional fault contact. In 80 attempts on two flow problems, grounding raises the proportion of structurally valid inputs from 5/20 to 20/20, but acceptance reaches 20/20 only with complete rule-based input preparation. With identical inputs, local repairs correct three seeded defects while preserving valid inputs. Supporting tests identify simulations passing physics checks despite differing from the problem description or reference results.

## Agents as Architecture Evaluators: Automating ATAM and SAAM for Continuous Assessment

DevFeed: [Agents as Architecture Evaluators: Automating ATAM and SAAM for Continuous Assessment](<https://devfeed.tech/articles/agents-as-architecture-evaluators-automating-atam-and-saam-for-continuous-assessment-142149.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.23278>)

Author: Adyansh Kakran, Sathvika Miryala, Karthik Vaidhyanathan

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

Content type: article

Language: en

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

Topics: [software-architecture](<https://devfeed.tech/topics/software-architecture.md>), [agentic workflows](<https://devfeed.tech/topics/agentic-workflows.md>), [risk-management](<https://devfeed.tech/topics/risk-management.md>), [ai evaluation](<https://devfeed.tech/topics/ai-evaluation.md>)

Tags: [agentic](<https://devfeed.tech/tags/agentic.md>), [agentic-ai](<https://devfeed.tech/tags/agentic-ai.md>), [agentic-workflow](<https://devfeed.tech/tags/agentic-workflow.md>), [agentic-workflows](<https://devfeed.tech/tags/agentic-workflows.md>), [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [analysis](<https://devfeed.tech/tags/analysis.md>), [architecture](<https://devfeed.tech/tags/architecture.md>), [assessment](<https://devfeed.tech/tags/assessment.md>), [automated](<https://devfeed.tech/tags/automated.md>), [completeness](<https://devfeed.tech/tags/completeness.md>), [continuous](<https://devfeed.tech/tags/continuous.md>), [cost](<https://devfeed.tech/tags/cost.md>), [coverage](<https://devfeed.tech/tags/coverage.md>), [cs-se](<https://devfeed.tech/tags/cs-se.md>), [dataset](<https://devfeed.tech/tags/dataset.md>), [evaluation](<https://devfeed.tech/tags/evaluation.md>), [evaluations](<https://devfeed.tech/tags/evaluations.md>), [literature](<https://devfeed.tech/tags/literature.md>), [metrics](<https://devfeed.tech/tags/metrics.md>), [performance](<https://devfeed.tech/tags/performance.md>)

### AI overview

The paper presents an agentic workflow that generates ATAM and SAAM architecture evaluation reports from high-level architectural descriptions, using a structured dataset of evaluations extracted from academic literature. It automates scenario generation and risk identification, cutting reported evaluation time from weeks to under five minutes for less than $0.50 per run. Automated metrics and human evaluation gave the reports relevance and completeness ratings of 4.5/5 and 3.9/5, respectively. These preliminary results suggest the approach could lower barriers to more frequent assessment; the evidence provided does not establish how it performs beyond the reported study.

### Source excerpt

arXiv:2611.23278v1 Announce Type: new Abstract: The long-term success of a software system relies heavily on its underlying architecture, which dictates its performance with respect to quality attributes. Software Architecture Evaluation methods, such as the Architecture Tradeoff Analysis Method (ATAM) and the Software Architecture Analysis Method (SAAM), are widely recognized for their ability to mitigate risks and ensure reliable quality attributes. However, their widespread adoption remains limited due to the significant cost, time, and human expertise required for these processes. This paper investigates the potential of agentic AI to lower these barriers and facilitate architectural assessment. To enable this preliminary study, we established a dataset by extracting human conducted evaluations from existing academic literature into a structured format. Using this dataset, we developed an agentic workflow to synthesize ATAM and SAAM evaluation reports based on these high level architectural descriptions. This approach simulates the reasoning process of human evaluators when provided with structured architectural data. We validated the approach using automated metrics and human evaluation. Agentic workflows achieve strong relevance and completeness ratings of 4.5/5 and 3.9/5 respectively. The agents successfully automated the labor-intensive phases of scenario generation and risk identification, reducing the evaluation time from weeks to under 5 minutes at a cost of less than $0.50 per run. The results confirm that agentic AI effectively lowers adoption barriers, enabling continuous, high-coverage architectural assessment.

## Palo Alto Networks to Buy AI Startup Applied Compute for $4.5 Billion

DevFeed: [Palo Alto Networks to Buy AI Startup Applied Compute for $4.5 Billion](<https://devfeed.tech/articles/palo-alto-networks-to-buy-ai-startup-applied-compute-for-4-5-billion-141990.md>)

Original publisher: [Read original article](<https://www.securityweek.com/palo-alto-networks-to-buy-ai-startup-applied-compute-for-4-5-billion/>)

Author: SecurityWeek News

Published: 2026-11-19T03:25:23Z

Content type: news

Language: en

Sources: [SecurityWeek](<https://devfeed.tech/sources/securityweek.md>)

Topics: [AI Infrastructure](<https://devfeed.tech/topics/ai-infrastructure.md>), [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>)

Tags: [acquisition](<https://devfeed.tech/tags/acquisition.md>), [agentic-workflows](<https://devfeed.tech/tags/agentic-workflows.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-models](<https://devfeed.tech/tags/ai-models.md>), [ai-native](<https://devfeed.tech/tags/ai-native.md>), [ai-startup](<https://devfeed.tech/tags/ai-startup.md>), [annual-recurring-revenue](<https://devfeed.tech/tags/annual-recurring-revenue.md>), [applied-compute](<https://devfeed.tech/tags/applied-compute.md>), [artificial-intelligence](<https://devfeed.tech/tags/artificial-intelligence.md>), [automate](<https://devfeed.tech/tags/automate.md>), [build](<https://devfeed.tech/tags/build.md>), [ceo](<https://devfeed.tech/tags/ceo.md>), [co-founder](<https://devfeed.tech/tags/co-founder.md>), [cybersecurity-company](<https://devfeed.tech/tags/cybersecurity-company.md>), [featured](<https://devfeed.tech/tags/featured.md>), [fine-tuning](<https://devfeed.tech/tags/fine-tuning.md>), [m-a-tracker](<https://devfeed.tech/tags/m-a-tracker.md>), [open-weight-ai](<https://devfeed.tech/tags/open-weight-ai.md>), [open-weight-ai-models](<https://devfeed.tech/tags/open-weight-ai-models.md>), [palo-alto-networks](<https://devfeed.tech/tags/palo-alto-networks.md>), [platform](<https://devfeed.tech/tags/platform.md>), [sovereign](<https://devfeed.tech/tags/sovereign.md>), [stock](<https://devfeed.tech/tags/stock.md>)

### AI overview

Palo Alto Networks agreed to acquire Applied Compute in an all-stock deal valued at $4.5 billion, subject to adjustments. Applied Compute lets companies fine-tune existing open-weight AI models on their own data and run them in production, with public-cloud and sovereign-environment deployment options. Palo Alto plans to offer the platform to security customers, while Applied Compute continues serving existing customers. After closing, co-founder Yash Patil will become co-chief AI officer, and the startup's research team will help train proprietary models for Palo Alto products. The deal is expected to close in fiscal Q3 2027, pending regulatory clearance and customary conditions.

### Source excerpt

The all-stock deal will give the cybersecurity company a platform for fine-tuning and running open-weight AI models in public and sovereign clouds. The post Palo Alto Networks to Buy AI Startup Applied Compute for $4.5 Billion appeared first on SecurityWeek.

## Introducing Vercel Board

DevFeed: [Introducing Vercel Board](<https://devfeed.tech/articles/introducing-vercel-board-141987.md>)

Original publisher: [Read original article](<https://vercel.com/blog/introducing-vercel-board>)

Author: Bani Singh

Published: 2026-11-18T08:00:00Z

Content type: release

Language: en

Sources: [Vercel News](<https://devfeed.tech/sources/vercel-news.md>)

Topics: [Multi Agent Systems](<https://devfeed.tech/topics/multi-agent-systems.md>), [agent orchestration](<https://devfeed.tech/topics/agent-orchestration.md>), [agent to agent communication](<https://devfeed.tech/topics/agent-to-agent-communication.md>), [agentic workflows](<https://devfeed.tech/topics/agentic-workflows.md>), [issue tracking](<https://devfeed.tech/topics/issue-tracking.md>), [Vercel](<https://devfeed.tech/topics/vercel.md>)

Tags: [agent-fleets](<https://devfeed.tech/tags/agent-fleets.md>), [agentic-workflows](<https://devfeed.tech/tags/agentic-workflows.md>), [agents](<https://devfeed.tech/tags/agents.md>), [board](<https://devfeed.tech/tags/board.md>), [cli](<https://devfeed.tech/tags/cli.md>), [codex](<https://devfeed.tech/tags/codex.md>), [communication](<https://devfeed.tech/tags/communication.md>), [context](<https://devfeed.tech/tags/context.md>), [delegation](<https://devfeed.tech/tags/delegation.md>), [development](<https://devfeed.tech/tags/development.md>), [environments](<https://devfeed.tech/tags/environments.md>), [experimental](<https://devfeed.tech/tags/experimental.md>), [future](<https://devfeed.tech/tags/future.md>), [harness](<https://devfeed.tech/tags/harness.md>), [headless](<https://devfeed.tech/tags/headless.md>), [humans](<https://devfeed.tech/tags/humans.md>), [javascript](<https://devfeed.tech/tags/javascript.md>), [langchain](<https://devfeed.tech/tags/langchain.md>), [logs](<https://devfeed.tech/tags/logs.md>), [vercel](<https://devfeed.tech/tags/vercel.md>)

### AI overview

Vercel Board is an experimental, headless message store for coordinating tasks across teams of agents and people. Agents use its CLI or JavaScript SDK to claim tasks, post updates, record results, and schedule follow-ups; channels and threads keep context together, while labels track status and related details. Watchers can wake agents on new replies or label changes, and Vercel deployments can respond to events without a continuously running process. Board supports two-way sync with tools such as Slack and GitHub, schema-validated structured messages, task dependencies, and board-specific access grants with event audit trails. The article says it is harness agnostic and names Claude Code, Codex, Pi, OpenCode, eve, fx, Mastra, and LangChain. Vercel reports using it for security agents and its v0 software factory, which it says merges over 50% of PRs. The launch invites developers to try the experimental product and provide feedback.

### Source excerpt

Software development is moving from individual agents completing tasks to teams of agents working on more complex projects. A single agent can track its work in a Markdown file, but there isn't a purpose-built primitive for tracking tasks, delegation, statuses, logs, and completed work across many agents and subagents. We ran into this coordination problem internally and started experimenting with a shared message board as a primitive on two key projects: Our security agents: We deployed a swarm of agents to analyze our codebases for vulnerabilities, push fixes and updates, and now we track of their work via Board. v0's software factory: After seeing how well Board worked for security agents, we rebuilt v0's software factory on it, and it now merges over 50% of PRs. Along the way, we added multiple features like grants for different levels of access (for humans and agents), two-way sync for multiple tools (like Slack), and a lot more. Today we are launching Vercel Board as an experimental agentic primitive. It packages what we've learned about coordinating work across agent fleets and builds towards a future where multiple teams of humans and agents orchestrate swarms, software factories, and other agentic workflows. We built Board for our own needs, but invite curious developers to test it alongside us and give feedback. It is harness agnostic and fits well into existing multi-agent reinforcement learning. Claude Code, Codex, Pi, OpenCode, eve, fx, Mastra, and LangChain can collaborate as if they were a single harness. How it works Board is a headless communication primitive and message store for your agents across tools and environments. Your agents read from and write to Board through the CLI or JavaScript SDK. Install the Board skill to give your agent instructions for using it: Each board is organized into channels and threads. A thread keeps the conversation, context, and updates together, while labels track details such as the associated pull request or curre

## Agentic engineering with GitLab and your local agent: A walkthrough

DevFeed: [Agentic engineering with GitLab and your local agent: A walkthrough](<https://devfeed.tech/articles/agentic-engineering-with-gitlab-and-your-local-agent-a-walkthrough-144773.md>)

Original publisher: [Read original article](<https://about.gitlab.com/blog/agentic-engineering-walkthrough/>)

Author: Fatima Sarah Khalid

Published: 2026-11-18T00:00:00Z

Content type: tutorial

Language: en

Sources: [GitLab](<https://devfeed.tech/sources/gitlab.md>)

Topics: [GitLab](<https://devfeed.tech/topics/gitlab.md>), [agentic-coding](<https://devfeed.tech/topics/agentic-coding.md>), [Claude Code](<https://devfeed.tech/topics/claude-code.md>), [Agent Skills](<https://devfeed.tech/topics/agent-skills.md>), [Agent Harness](<https://devfeed.tech/topics/agent-harness.md>), [gitlab-ci](<https://devfeed.tech/topics/gitlab-ci.md>), [code security](<https://devfeed.tech/topics/code-security.md>), [Loop Engineering](<https://devfeed.tech/topics/loop-engineering.md>), [CI/CD](<https://devfeed.tech/topics/cicd.md>), [human in the loop agent](<https://devfeed.tech/topics/human-in-the-loop-agent.md>), [codex](<https://devfeed.tech/topics/codex.md>), [cursor](<https://devfeed.tech/topics/cursor.md>)

Tags: [agentic](<https://devfeed.tech/tags/agentic.md>), [agentic-engineering](<https://devfeed.tech/tags/agentic-engineering.md>), [agentic-workflows](<https://devfeed.tech/tags/agentic-workflows.md>), [ai](<https://devfeed.tech/tags/ai.md>), [code](<https://devfeed.tech/tags/code.md>), [code-reviews](<https://devfeed.tech/tags/code-reviews.md>), [codex](<https://devfeed.tech/tags/codex.md>), [coding](<https://devfeed.tech/tags/coding.md>), [connect](<https://devfeed.tech/tags/connect.md>), [cursor](<https://devfeed.tech/tags/cursor.md>), [developer](<https://devfeed.tech/tags/developer.md>), [devsecops](<https://devfeed.tech/tags/devsecops.md>), [duo](<https://devfeed.tech/tags/duo.md>), [environment](<https://devfeed.tech/tags/environment.md>), [failed](<https://devfeed.tech/tags/failed.md>), [flow](<https://devfeed.tech/tags/flow.md>), [gitlab](<https://devfeed.tech/tags/gitlab.md>), [harness](<https://devfeed.tech/tags/harness.md>), [how-to](<https://devfeed.tech/tags/how-to.md>), [install](<https://devfeed.tech/tags/install.md>), [issue](<https://devfeed.tech/tags/issue.md>), [lifecycle](<https://devfeed.tech/tags/lifecycle.md>)

### AI overview

The GitLab Duo setup skill connects a local coding harness to GitLab Duo Agent Platform, where repository-aware work runs as GitLab flows and merge requests remain subject to existing review, pipeline, security, and approval policies. After reviewing one setup plan, an Owner can enable group workflows, automatic code review, failed-pipeline automation, and the GitLab MCP connection; a project Maintainer can configure only that project. The walkthrough covers handing assigned issues to Developer, reviewing MRs and resolving feedback or conflicts, fixing failed pipelines, and--on Ultimate--triaging security findings. Pipeline fixes appear as inline suggestions when they fit the MR diff, as a new MR when they require other files or no MR is open, or as guidance when a reliable fix cannot be determined or the failure is security-sensitive. Prerequisites include a GitLab.com group with GitLab Credits, a project with pipelines and work items, and Claude Code plus git and glab; group-wide setup requires the Owner role. The pipeline flow reads only the last 150 KiB of a job log. Security automation offers standard and conservative presets with different thresholds and open-MR limits.

### Source excerpt

You can build an agentic engineering environment to drive greater automation throughout your workflow. How? Start in the harness you already use and connect to GitLab Duo Agent Platform once with a skill. Longer, repository-aware workflows run on GitLab, and every merge request still hits the same reviews, pipelines, scans, and approval policies. In this article, we will show you how to quickly get started, from setup to tackling four key use cases. We focus on Claude Code as the local harness because that's what we see most of our customers using but this same flow can apply to the local harness of your choosing, including Duo CLI. How to configure your agentic engineering environment If you already do most of your coding in a local harness, keep working there and wire it to GitLab Duo Agent Platform. From the terminal, you can direct lifecycle work to agentic workflows that run inside GitLab: Picking up an issue and opening a merge request Reviewing every MR as it lands Resolving merge conflicts Repairing a pipeline that just failed With GitLab Ultimate, triaging and fixing security findings once code lands Claude Code, Codex, Cursor, OpenCode, and others become the place from where you direct that work. Part 1 is the setup Install the GitLab Duo setup skill, ask Claude Code to run it, and it sets up your whole top-level group with the necessary settings, the flows, an automation in every project, and the MCP connection. Part 2 walks through four workflows You can try them as soon as the setup is done, each driven from Claude Code: Find an issue assigned to you and hand it to the Developer flow. Get automated code reviews on your merge requests, act on the findings without leaving your harness, and resolve any conflicts that pop up. Use an automation to fix a failed pipeline. On Ultimate, triage and fix security findings with the security flows. When you want an even tighter loop The MR followup skill guides your local harness through the steps above even faster.

## Introducing GPT-6.2 Astra and Sol

DevFeed: [Introducing GPT-6.2 Astra and Sol](<https://devfeed.tech/articles/introducing-gpt-6-2-astra-and-sol-138356.md>)

Original publisher: [Read original article](<https://openai.com/index/introducing-gpt-6-2-astra-sol>)

Published: 2026-11-17T17:45:00Z

Content type: release

Language: en

Sources: [OpenAI News](<https://devfeed.tech/sources/openai-news.md>)

Topics: [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [Frontier AI](<https://devfeed.tech/topics/frontier-ai.md>), [agentic-coding](<https://devfeed.tech/topics/agentic-coding.md>), [3D](<https://devfeed.tech/topics/3d.md>), [codex](<https://devfeed.tech/topics/codex.md>), [OpenAI](<https://devfeed.tech/topics/openai.md>), [Code quality](<https://devfeed.tech/topics/code-quality.md>)

Tags: [accounting](<https://devfeed.tech/tags/accounting.md>), [agentic-workflows](<https://devfeed.tech/tags/agentic-workflows.md>), [agents-last-exam](<https://devfeed.tech/tags/agents-last-exam.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-research](<https://devfeed.tech/tags/ai-research.md>), [ai-self-improvement](<https://devfeed.tech/tags/ai-self-improvement.md>), [alignment](<https://devfeed.tech/tags/alignment.md>), [api](<https://devfeed.tech/tags/api.md>), [astra](<https://devfeed.tech/tags/astra.md>), [chatgpt](<https://devfeed.tech/tags/chatgpt.md>), [chatgpt-work](<https://devfeed.tech/tags/chatgpt-work.md>), [codex](<https://devfeed.tech/tags/codex.md>), [coding](<https://devfeed.tech/tags/coding.md>), [computer-use](<https://devfeed.tech/tags/computer-use.md>), [cost](<https://devfeed.tech/tags/cost.md>), [efficiency](<https://devfeed.tech/tags/efficiency.md>), [gpt](<https://devfeed.tech/tags/gpt.md>), [gpt-6-2](<https://devfeed.tech/tags/gpt-6-2.md>), [gpt-6-2-astra](<https://devfeed.tech/tags/gpt-6-2-astra.md>), [product](<https://devfeed.tech/tags/product.md>), [sol](<https://devfeed.tech/tags/sol.md>)

### AI overview

GPT-6.2 Astra targets complex professional work, while GPT-6.2 Sol is positioned for everyday tasks; both are described as more token-efficient than their predecessors. Astra improves template-following in documents and slides, coding, computer use, and interactive 3D work. The source reports benchmark gains in professional, scientific, legal, spreadsheet, and 3D tasks, while Sol approaches Astra on one coding benchmark at about one-fifth the cost and beats GPT-6 Astra on LifeVal at about one-seventh the cost. Astra's API rates are $8 per million input tokens, $0.40 cached input, and $40 output; Sol retains GPT-6.1 Sol's $2, $0.10, and $10 rates. Both are available through ChatGPT Work, Codex, and the API, with Ultrafast access subject to plan or workspace eligibility. The models meet the stated Critical cybersecurity and High biological and chemical capability thresholds, so tighter safeguards restrict some legitimate security workflows. Astra also meets the High AI self-improvement threshold; the source describes added monitoring and controls. In two alignment tests, both models more often omitted obstacles that blocked their work, a behavior OpenAI says it is addressing.

### Source excerpt

Introducing GPT-6.2 Astra and Sol, with better professional outputs, coding, computer use, and efficiency at lower cost across ChatGPT Work, Codex, and the API.

## Nvidia reveals Rubin HPC, a GPU with 50,000+ CUDA cores for scientific simulation

DevFeed: [Nvidia reveals Rubin HPC, a GPU with 50,000+ CUDA cores for scientific simulation](<https://devfeed.tech/articles/nvidia-reveals-rubin-hpc-a-gpu-with-50-000-cuda-cores-for-scientific-simulation-137868.md>)

Original publisher: [Read original article](<https://www.techspot.com/news/114583-nvidia-reveals-rubin-hpc-gpu-50000-cuda-cores.html>)

Author: Skye Jacobs

Published: 2026-11-17T15:46:00Z

Content type: news

Language: en

Sources: [TechSpot](<https://devfeed.tech/sources/techspot.md>)

Topics: [High-Performance Computing](<https://devfeed.tech/topics/high-performance-computing.md>), [CUDA-X](<https://devfeed.tech/topics/cuda-x.md>), [NVIDIA Vera Rubin](<https://devfeed.tech/topics/nvidia-vera-rubin.md>), [CUDA](<https://devfeed.tech/topics/cuda.md>), [NVLink](<https://devfeed.tech/topics/nvlink.md>)

Tags: [accelerated-computing](<https://devfeed.tech/tags/accelerated-computing.md>), [acceleration](<https://devfeed.tech/tags/acceleration.md>), [agentic](<https://devfeed.tech/tags/agentic.md>), [agentic-workflows](<https://devfeed.tech/tags/agentic-workflows.md>), [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-agents](<https://devfeed.tech/tags/ai-agents.md>), [algorithms](<https://devfeed.tech/tags/algorithms.md>), [amd](<https://devfeed.tech/tags/amd.md>), [analysis](<https://devfeed.tech/tags/analysis.md>), [analytics](<https://devfeed.tech/tags/analytics.md>), [bandwidth](<https://devfeed.tech/tags/bandwidth.md>), [cuda](<https://devfeed.tech/tags/cuda.md>), [gpu](<https://devfeed.tech/tags/gpu.md>), [hardware](<https://devfeed.tech/tags/hardware.md>), [hpc](<https://devfeed.tech/tags/hpc.md>), [multi-core](<https://devfeed.tech/tags/multi-core.md>), [nvidia](<https://devfeed.tech/tags/nvidia.md>), [rubin](<https://devfeed.tech/tags/rubin.md>), [rubin-gpu](<https://devfeed.tech/tags/rubin-gpu.md>), [rubin-hpc](<https://devfeed.tech/tags/rubin-hpc.md>), [science](<https://devfeed.tech/tags/science.md>), [simulation](<https://devfeed.tech/tags/simulation.md>)

### AI overview

Nvidia says its Rubin HPC GPU, announced for the Vera Rubin platform and expected in 2028, will have more than 50,000 CUDA cores and target scientific and engineering simulations used to test ideas generated by AI agents. The company says its "balanced design" scales data movement with compute, using sparse data acceleration for recurring routines such as sparse matrix operations, stencil computations, sorting and reductions. GPUs will connect through seventh-generation NVLink, and agents can use CUDA-X libraries with tuned algorithms. Key HPC specifications remain undisclosed: memory capacity and bandwidth, double-precision capability, interconnect bandwidth, and whether the chip uses multiple dies. Nvidia has not confirmed its physical layout.

### Source excerpt

The core count offers the first clue to what Nvidia is building. The current Rubin GPU has 224 streaming multiprocessors and 28,672 CUDA cores, so getting past 50,000 would take at least 74% more cores. Read Entire Article

## LLMs in DevSecOps: A Systematic Mapping of Models, Evidence, and Research Gaps Across the Software Lifecycle

DevFeed: [LLMs in DevSecOps: A Systematic Mapping of Models, Evidence, and Research Gaps Across the Software Lifecycle](<https://devfeed.tech/articles/llms-in-devsecops-a-systematic-mapping-of-models-evidence-and-research-gaps-across-the-software-lifecycle-137969.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.18632>)

Author: Sindu Chitraju, Mir Mehedi Ahsan Pritom

Published: 2026-11-17T05:00:00Z

Content type: article

Language: en

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

Topics: [DevSecOps](<https://devfeed.tech/topics/devsecops.md>), [ai security](<https://devfeed.tech/topics/ai-security.md>), [LLM security](<https://devfeed.tech/topics/llm-security.md>), [AI Integration Strategies](<https://devfeed.tech/topics/ai-integration-strategies.md>), [llm-reasoning](<https://devfeed.tech/topics/llm-reasoning.md>)

Tags: [2026](<https://devfeed.tech/tags/2026.md>), [abstract](<https://devfeed.tech/tags/abstract.md>), [adoption](<https://devfeed.tech/tags/adoption.md>), [agentic](<https://devfeed.tech/tags/agentic.md>), [agentic-workflows](<https://devfeed.tech/tags/agentic-workflows.md>), [also](<https://devfeed.tech/tags/also.md>), [analyze](<https://devfeed.tech/tags/analyze.md>), [arxiv](<https://devfeed.tech/tags/arxiv.md>), [attention](<https://devfeed.tech/tags/attention.md>), [autonomous](<https://devfeed.tech/tags/autonomous.md>), [autonomous-remediation](<https://devfeed.tech/tags/autonomous-remediation.md>), [based](<https://devfeed.tech/tags/based.md>), [benchmarks](<https://devfeed.tech/tags/benchmarks.md>), [cs-se](<https://devfeed.tech/tags/cs-se.md>), [devsecops](<https://devfeed.tech/tags/devsecops.md>), [lifecycle](<https://devfeed.tech/tags/lifecycle.md>), [llms](<https://devfeed.tech/tags/llms.md>), [mapping](<https://devfeed.tech/tags/mapping.md>), [models](<https://devfeed.tech/tags/models.md>), [research](<https://devfeed.tech/tags/research.md>), [software](<https://devfeed.tech/tags/software.md>)

### AI overview

This mapping of LLM-enabled DevSecOps security research from 2024 through June 2026 finds attention concentrated in the Code and Test stages, with less work on Deploy and Review. Recent systems increasingly use structured context, iterative reasoning, fine-tuning, retrieval augmentation, or agentic workflows instead of single-shot prompts. Comparisons remain difficult because studies use different tasks, datasets, metrics, and baselines; most evidence comes from benchmarks or open-source repositories, with limited industrial-scale validation. Approaches are mostly stage-specific, with little evidence of security reasoning across the lifecycle. The authors identify needs for standardized evaluation, production-scale validation, work on supply-chain and Infrastructure-as-Code security, trustworthy autonomous remediation, and cross-stage integration.

### Source excerpt

arXiv:2611.18632v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly being integrated into software security and DevSecOps workflows, yet their adoption, evaluation, and maturity vary substantially across lifecycle stages. This study systematically maps recent LLM-enabled security research published between 2024 and 2026 (until June) across six DevSecOps stages: \textit{Plan}, \textit{Code}, \textit{Test}, \textit{Review}, \textit{Deploy}, and \textit{Monitor}. For each stage, we analyze the security tasks addressed, models and adaptation strategies employed, evaluation settings, reported effectiveness, and key limitations. Our findings reveal an uneven research landscape, with \textit{Test} and \textit{Code} receiving substantially greater attention than \textit{Deploy} and \textit{Review}. Across stages, recent systems increasingly rely on structured context, iterative reasoning, fine-tuning, retrieval augmentation, or agentic workflows rather than direct single-shot prompting. However, reported performance remains difficult to compare because studies use heterogeneous tasks, datasets, metrics, and baselines. Furthermore, most approaches are evaluated using benchmarks or open-source repositories, while industrial-scale evidence remains limited. We also find that existing systems are predominantly stage-specific, with little evidence of LLM-enabled security reasoning spanning multiple DevSecOps stages. Based on these observations, we identify research opportunities in standardized evaluation, production-scale validation, supply-chain and Infrastructure-as-Code security, trustworthy autonomous remediation, and cross-stage LLM integration. This study provides a recent lifecycle-level view of where LLM-enabled DevSecOps research is concentrated, what methodological patterns are emerging, and where significant gaps remain.

## Multi-LLM Agentic AI at the Edge: Joint Agent Scheduling and Resource Allocation

DevFeed: [Multi-LLM Agentic AI at the Edge: Joint Agent Scheduling and Resource Allocation](<https://devfeed.tech/articles/multi-llm-agentic-ai-at-the-edge-joint-agent-scheduling-and-resource-allocation-137630.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.20915>)

Author: Yuanyan Song, Kezhi Wang, Xinmian Xu, Yongmin Li

Published: 2026-11-17T05:00:00Z

Content type: article

Language: en

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

Topics: [supervisor agent pattern](<https://devfeed.tech/topics/supervisor-agent-pattern.md>), [Multi Agent Systems](<https://devfeed.tech/topics/multi-agent-systems.md>), [hierarchical agent systems](<https://devfeed.tech/topics/hierarchical-agent-systems.md>), [Operations research and optimization](<https://devfeed.tech/topics/operations-research-and-optimization.md>), [Agentic AI](<https://devfeed.tech/topics/what-is-agentic-ai.md>), [Large Language Model](<https://devfeed.tech/topics/llm.md>), [scheduling](<https://devfeed.tech/topics/scheduling.md>), [agentic workflows](<https://devfeed.tech/topics/agentic-workflows.md>)

Tags: [agent](<https://devfeed.tech/tags/agent.md>), [agentic](<https://devfeed.tech/tags/agentic.md>), [agentic-ai](<https://devfeed.tech/tags/agentic-ai.md>), [agentic-ai-architecture](<https://devfeed.tech/tags/agentic-ai-architecture.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-agent](<https://devfeed.tech/tags/ai-agent.md>), [ai-architecture](<https://devfeed.tech/tags/ai-architecture.md>), [ai-at-the-edge](<https://devfeed.tech/tags/ai-at-the-edge.md>), [algorithms](<https://devfeed.tech/tags/algorithms.md>), [approximation](<https://devfeed.tech/tags/approximation.md>), [architecture](<https://devfeed.tech/tags/architecture.md>), [bandwidth](<https://devfeed.tech/tags/bandwidth.md>), [convex](<https://devfeed.tech/tags/convex.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [edge](<https://devfeed.tech/tags/edge.md>), [energy](<https://devfeed.tech/tags/energy.md>), [llm](<https://devfeed.tech/tags/llm.md>), [resource](<https://devfeed.tech/tags/resource.md>), [scheduling](<https://devfeed.tech/tags/scheduling.md>)

### AI overview

The paper proposes an edge architecture in which a supervisor splits user requests into subtasks and dispatches them to worker agents through parallel or serial workflows, with a two-level retry mechanism. To reduce energy use while meeting latency and QoS constraints, an alternating-optimization scheme jointly handles agent selection and resource allocation. The parallel workflow allocates bandwidth; the serial workflow allocates service time using KKT conditions. Both address retrieval and agent selection, using SCA, Lagrangian relaxation, and Gale-Shapley or LLM-based algorithms. Simulations report lower energy consumption than benchmark schemes, and experiments using Qwen and Llama report improved task success rates.

### Source excerpt

arXiv:2611.20915v1 Announce Type: new Abstract: In this paper, an edge-enabled multi-large language model (LLM) agentic AI architecture is proposed, where one supervisor AI agent and multiple worker AI agents cooperatively execute users' requests at the edge. The supervisor AI agent decouples the user request into a series of sub-tasks and dynamically dispatches them to LLM-equipped worker AI agents via two agentic workflows, i.e., parallel and serial workflows, with a two-level retry mechanism to enhance execution reliability. To prolong the service duration of worker AI agents, the energy minimization problems are formulated by jointly considering AI agent selection and resource allocation, subject to task execution latency and quality of service (QoS) constraints. A resource allocation scheme based on alternating optimization (AO) is proposed. Specifically, for the parallel workflow, the scheme decouples the original problem into bandwidth allocation, retrieval selection and AI agent selection sub-problems, which are iteratively solved by the proposed successive convex approximation (SCA), Lagrangian relaxation (LR), and Gale-Shapley (GS) or LLM-based algorithms, respectively. For the serial workflow, the problem is similarly decoupled into service time allocation, retrieval selection and AI agent selection sub-problems; the optimal service time allocation is obtained via Karush-Kuhn-Tucker (KKT) conditions, while the latter two sub-problems are addressed by extending the proposed algorithms to the serial scenario. Simulation results show that the proposed resource allocation scheme can reduce system energy consumption compared with other benchmarks, while experiments on a multi-LLM agentic AI system based on Qwen and Llama demonstrate improved task execution success rates.

## ORACLE-SWE: Quantifying the Contribution of Critical Information Signals on SWE Agents

DevFeed: [ORACLE-SWE: Quantifying the Contribution of Critical Information Signals on SWE Agents](<https://devfeed.tech/articles/oracle-swe-quantifying-the-contribution-of-critical-information-signals-on-swe-agents-137924.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2604.07789>)

Author: Kenan Li, Qirui Jin, Liao Zhu, Xiaosong Huang, Yijia Wu, Yikai Zhang, Xin Zhang, Zijian Jin, Yufan Huang, Elsie Nallipogu, Chaoyun Zhang, Yu Kang, Saravan Rajmohan, Qingwei Lin, Wenke Lee, Dongmei Zha

Published: 2026-11-17T05:00:00Z

Content type: article

Language: en

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

Topics: [agentic-coding](<https://devfeed.tech/topics/agentic-coding.md>), [AI-assisted coding](<https://devfeed.tech/topics/ai-assisted-coding.md>)

Tags: [abstract](<https://devfeed.tech/tags/abstract.md>), [agent](<https://devfeed.tech/tags/agent.md>), [agentic](<https://devfeed.tech/tags/agentic.md>), [agentic-workflows](<https://devfeed.tech/tags/agentic-workflows.md>), [agents](<https://devfeed.tech/tags/agents.md>), [analysis](<https://devfeed.tech/tags/analysis.md>), [api](<https://devfeed.tech/tags/api.md>), [arxiv](<https://devfeed.tech/tags/arxiv.md>), [code](<https://devfeed.tech/tags/code.md>), [context](<https://devfeed.tech/tags/context.md>), [contribution](<https://devfeed.tech/tags/contribution.md>), [cs-cl](<https://devfeed.tech/tags/cs-cl.md>), [cs-ma](<https://devfeed.tech/tags/cs-ma.md>), [cs-se](<https://devfeed.tech/tags/cs-se.md>), [dataset](<https://devfeed.tech/tags/dataset.md>), [effectiveness](<https://devfeed.tech/tags/effectiveness.md>), [engineering](<https://devfeed.tech/tags/engineering.md>), [execution](<https://devfeed.tech/tags/execution.md>), [exploration](<https://devfeed.tech/tags/exploration.md>), [failure](<https://devfeed.tech/tags/failure.md>), [failure-analysis](<https://devfeed.tech/tags/failure-analysis.md>), [information](<https://devfeed.tech/tags/information.md>), [oracle](<https://devfeed.tech/tags/oracle.md>)

### AI overview

ORACLE-SWE measures how much intermediate information signals contribute to repository-level software engineering agents' task success. It examines Reproduction Test, Regression Test, Edit Location, Execution Context, and API Usage, comparing oracle signals with signals extracted by agents and measuring the gap between them. The authors describe this as a systematic comparison of signal effectiveness and remaining room for improvement, and say they release source code and an oracle-signal dataset. The supplied excerpt gives no quantitative findings or ranking of the signals.

### Source excerpt

arXiv:2604.07789v4 Announce Type: replace-cross Abstract: Recent advances in Language Model (LM) agents have increasingly focused on repository-level software engineering (SWE) tasks, leading to various agentic workflows, training methods and failure analysis. Interestingly, rather than directly generating or evaluating edit patches, these approaches first examine and improve intermediate information signals collected during agent exploration, including Reproduction Test, Regression Test, Edit Location, Execution Context, and API Usage. Although different studies examine different subsets of these signals, no work has systematically compared their relative effectiveness in improving final task success or measured the remaining space for improvement in each signal. To address this gap, this work quantifies the contributions of both oracle and agent-extracted signals to final task success and measures the gap between current agent-found signals and their oracle counterparts. We hope our findings could suggest future research emphasis in SWE agents. We release our source code and oracle-signal dataset as a reusable methodology to benefit future signal analysis of SWE agents.

## How security leaders see AI being used in the SOC

DevFeed: [How security leaders see AI being used in the SOC](<https://devfeed.tech/articles/how-security-leaders-see-ai-being-used-in-the-soc-138160.md>)

Original publisher: [Read original article](<https://www.elastic.co/blog/how-security-leaders-see-ai-being-used-in-the-soc>)

Author: Joe DeFever

Published: 2026-11-17T00:00:00Z

Content type: article

Language: en

Sources: [Elastic Blog](<https://devfeed.tech/sources/elastic-blog-elasticsearch-kibana-and-elk-stack.md>)

Topics: [ai-governance](<https://devfeed.tech/topics/ai-governance.md>), [Agentic SOC](<https://devfeed.tech/topics/agentic-soc.md>), [shadow AI](<https://devfeed.tech/topics/shadow-ai.md>), [Security Operations Center](<https://devfeed.tech/topics/security-operations-center.md>), [Security](<https://devfeed.tech/topics/security.md>)

Tags: [agentic-ai](<https://devfeed.tech/tags/agentic-ai.md>), [agentic-security](<https://devfeed.tech/tags/agentic-security.md>), [agentic-security-operations](<https://devfeed.tech/tags/agentic-security-operations.md>), [agentic-workflows](<https://devfeed.tech/tags/agentic-workflows.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-adoption](<https://devfeed.tech/tags/ai-adoption.md>), [ai-agent](<https://devfeed.tech/tags/ai-agent.md>), [ai-agents](<https://devfeed.tech/tags/ai-agents.md>), [ai-autonomy](<https://devfeed.tech/tags/ai-autonomy.md>), [ai-decisions](<https://devfeed.tech/tags/ai-decisions.md>), [ai-deployment](<https://devfeed.tech/tags/ai-deployment.md>), [ai-maturity](<https://devfeed.tech/tags/ai-maturity.md>), [ai-performance](<https://devfeed.tech/tags/ai-performance.md>), [ai-tool](<https://devfeed.tech/tags/ai-tool.md>), [ai-tools](<https://devfeed.tech/tags/ai-tools.md>), [ai-training](<https://devfeed.tech/tags/ai-training.md>), [frameworks](<https://devfeed.tech/tags/frameworks.md>), [governance](<https://devfeed.tech/tags/governance.md>), [security](<https://devfeed.tech/tags/security.md>), [soc](<https://devfeed.tech/tags/soc.md>)

### AI overview

AI is widely used in security operations, but only 18% of teams have structured, enforced usage frameworks. Survey results show differing levels of autonomy: 52% require human authorization for every AI decision, 43% require verification for higher-consequence outputs, and 3% allow action without human involvement. The article argues that oversight and traceable explanations matter because security actions can disrupt business or miss threats, and teams need to show what the AI saw, recommended, and why a person approved or overrode it. It also reports a gap between executives' beliefs and practitioners' experiences, including greater frontline use of homegrown workarounds. Recommendations include making approval the default, tracking deployment costs, unifying security data to provide context, asking practitioners what tools they use, and keeping audit trails. The survey associates mature AI adoption with more reported value, while data structure and governance requirements remain barriers to automation.

### Source excerpt

Only 18% of teams have structured, enforced frameworks for how AI should be used in the SOC. Security leaders aren't struggling to adopt AI. They're struggling to control it, explain it, and defend it. Learn what you can do to improve AI governance.

## Announcing our newest integration partner: n8n

DevFeed: [Announcing our newest integration partner: n8n](<https://devfeed.tech/articles/announcing-our-newest-integration-partner-n8n-136888.md>)

Original publisher: [Read original article](<https://www.port.io/blog/announcing-our-newest-integration-partner-n8n>)

Author: Jeff Richards

Published: 2026-11-16T14:53:57Z

Content type: release

Language: en

Sources: [Port](<https://devfeed.tech/sources/developer-experience-platform-engineering-blog-port.md>)

Topics: [n8n](<https://devfeed.tech/topics/n8n.md>), [agentic workflows](<https://devfeed.tech/topics/agentic-workflows.md>), [workflow automation](<https://devfeed.tech/topics/workflow-automation.md>), [AI Integration Strategies](<https://devfeed.tech/topics/ai-integration-strategies.md>), [agent orchestration](<https://devfeed.tech/topics/agent-orchestration.md>)

Tags: [agentic](<https://devfeed.tech/tags/agentic.md>), [agentic-workflows](<https://devfeed.tech/tags/agentic-workflows.md>), [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-agents](<https://devfeed.tech/tags/ai-agents.md>), [ai-software-factory](<https://devfeed.tech/tags/ai-software-factory.md>), [build](<https://devfeed.tech/tags/build.md>), [context](<https://devfeed.tech/tags/context.md>), [easy](<https://devfeed.tech/tags/easy.md>), [governance](<https://devfeed.tech/tags/governance.md>), [integration](<https://devfeed.tech/tags/integration.md>), [n8n](<https://devfeed.tech/tags/n8n.md>), [partner](<https://devfeed.tech/tags/partner.md>), [port](<https://devfeed.tech/tags/port.md>), [safely](<https://devfeed.tech/tags/safely.md>), [scale](<https://devfeed.tech/tags/scale.md>), [workflows](<https://devfeed.tech/tags/workflows.md>)

### AI overview

The Port node for n8n adds Port's infrastructure and service context and governance capabilities to n8n workflows, aiming to help teams coordinate agentic automation. The article describes incident response that enriches PagerDuty alerts with service ownership, deployments, runbooks, and incident history before escalating, creating a Jira ticket, and notifying responders; it also describes Jira triage that checks issue status and labels, retrieves catalog context, creates a GitHub issue, assigns it to Copilot, and links it back to Jira. The article reports that teams using the latter workflow saw a 40% drop in MTTR and 60% fewer backlog tickets in the first month. These figures are presented as reported outcomes, without supporting methodology in the supplied text.

### Source excerpt

AI agents are easy to build. Making them work safely together is the hard part. Here's how Port and n8n bring context, governance, and coordination to agentic workflows at scale.

## Google warns that fully-automated AI attacks are coming soon

DevFeed: [Google warns that fully-automated AI attacks are coming soon](<https://devfeed.tech/articles/google-warns-that-fully-automated-ai-attacks-are-coming-soon-135581.md>)

Original publisher: [Read original article](<https://www.bleepingcomputer.com/news/security/google-warns-that-fully-automated-ai-attacks-are-coming-soon/>)

Author: Bill Toulas

Published: 2026-11-16T14:00:00Z

Content type: news

Language: en

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

Topics: [ai-assisted attacks](<https://devfeed.tech/topics/ai-assisted-attacks.md>), [Multi Agent Systems](<https://devfeed.tech/topics/multi-agent-systems.md>), [Cybersecurity](<https://devfeed.tech/topics/cybersecurity.md>), [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>)

Tags: [adoption](<https://devfeed.tech/tags/adoption.md>), [aerospace](<https://devfeed.tech/tags/aerospace.md>), [agentic](<https://devfeed.tech/tags/agentic.md>), [agentic-ai](<https://devfeed.tech/tags/agentic-ai.md>), [agentic-pentesting](<https://devfeed.tech/tags/agentic-pentesting.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>), [ai-pentesting](<https://devfeed.tech/tags/ai-pentesting.md>), [ai-usage](<https://devfeed.tech/tags/ai-usage.md>), [artex](<https://devfeed.tech/tags/artex.md>), [artificial-intelligence](<https://devfeed.tech/tags/artificial-intelligence.md>), [attacks](<https://devfeed.tech/tags/attacks.md>), [automate](<https://devfeed.tech/tags/automate.md>), [automated](<https://devfeed.tech/tags/automated.md>), [computer-help](<https://devfeed.tech/tags/computer-help.md>), [computer-security](<https://devfeed.tech/tags/computer-security.md>), [computers](<https://devfeed.tech/tags/computers.md>), [discovery](<https://devfeed.tech/tags/discovery.md>), [exploitation](<https://devfeed.tech/tags/exploitation.md>), [frameworks](<https://devfeed.tech/tags/frameworks.md>), [google](<https://devfeed.tech/tags/google.md>), [infosec](<https://devfeed.tech/tags/infosec.md>), [infosec-computer-security](<https://devfeed.tech/tags/infosec-computer-security.md>), [linux](<https://devfeed.tech/tags/linux.md>), [mac](<https://devfeed.tech/tags/mac.md>), [malware](<https://devfeed.tech/tags/malware.md>), [malware-removal](<https://devfeed.tech/tags/malware-removal.md>), [offensive](<https://devfeed.tech/tags/offensive.md>), [security](<https://devfeed.tech/tags/security.md>), [spyware](<https://devfeed.tech/tags/spyware.md>), [support](<https://devfeed.tech/tags/support.md>), [tech-support](<https://devfeed.tech/tags/tech-support.md>), [technical-support](<https://devfeed.tech/tags/technical-support.md>), [virus](<https://devfeed.tech/tags/virus.md>), [virus-removal](<https://devfeed.tech/tags/virus-removal.md>), [vulnerability](<https://devfeed.tech/tags/vulnerability.md>), [vulnerability-discovery](<https://devfeed.tech/tags/vulnerability-discovery.md>), [windows](<https://devfeed.tech/tags/windows.md>)

### AI overview

Google reports that threat groups are using AI frameworks to automate vulnerability discovery and exploitation, including activity involving ARTEX, CAIRN, CyberStrikeAI, HexStrike AI, and a multi-agent system called exploit_agent. In an observed case, exploit_agent analyzed software updates and attempted exploits without a human in the loop; attackers also used modified Claude Code to install a backdoor. Google estimates low-skill attacks requiring little human interaction may arrive within three months, with sophisticated fully autonomous attacks likely within six months. Automated exploitation can shorten defenders' patching window, while AI-generated false proof-of-concept exploits add verification work. The excerpt also notes AI use in influence operations and LLMjacking.

### Source excerpt

Threat actors are now relying on agentic workflows powered by AI-based offensive frameworks to automate vulnerability discovery and exploitation, accelerating attacks to machine speed. [...]

## How to set up agentic workflows on Expo

DevFeed: [How to set up agentic workflows on Expo](<https://devfeed.tech/articles/how-to-set-up-agentic-workflows-on-expo-133409.md>)

Original publisher: [Read original article](<https://expo.dev/blog/how-to-set-up-agentic-workflows>)

Author: Tori White

Published: 2026-11-13T18:45:00Z

Content type: tutorial

Language: en

Sources: [Expo](<https://devfeed.tech/sources/expo.md>)

Topics: [agentic workflows](<https://devfeed.tech/topics/agentic-workflows.md>), [Expo](<https://devfeed.tech/topics/expo.md>), [Tool](<https://devfeed.tech/topics/tool.md>)

Tags: [agent](<https://devfeed.tech/tags/agent.md>), [agentic](<https://devfeed.tech/tags/agentic.md>), [agentic-workflows](<https://devfeed.tech/tags/agentic-workflows.md>), [github](<https://devfeed.tech/tags/github.md>), [how-to](<https://devfeed.tech/tags/how-to.md>), [robot](<https://devfeed.tech/tags/robot.md>), [token](<https://devfeed.tech/tags/token.md>), [user](<https://devfeed.tech/tags/user.md>), [workflows](<https://devfeed.tech/tags/workflows.md>)

### AI overview

Set up agentic workflows on Expo by connecting GitHub, adding a robot user, connecting your agent, and giving your workflows a GitHub token.

### Source excerpt

Four steps to unblock your agent: connect GitHub, add a robot user, connect your agent, and give your workflows a GitHub token.

## GHAgentCI: A Dataset of Coding-Agent Invocations in CI Workflow Histories

DevFeed: [GHAgentCI: A Dataset of Coding-Agent Invocations in CI Workflow Histories](<https://devfeed.tech/articles/ghagentci-a-dataset-of-coding-agent-invocations-in-ci-workflow-histories-131716.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.15522>)

Author: Daniel Ogenrwot, Jorge Gonzalo Delgado Cervantes, Woojoong Kim, John Businge

Published: 2026-11-13T05:00:00Z

Content type: article

Language: en

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

Topics: [agentic-coding](<https://devfeed.tech/topics/agentic-coding.md>), [GitHub Agentic Workflows](<https://devfeed.tech/topics/github-agentic-workflows.md>), [CI/CD](<https://devfeed.tech/topics/cicd.md>)

Tags: [agent](<https://devfeed.tech/tags/agent.md>), [agent-integration](<https://devfeed.tech/tags/agent-integration.md>), [agentic](<https://devfeed.tech/tags/agentic.md>), [agentic-workflow](<https://devfeed.tech/tags/agentic-workflow.md>), [agentic-workflows](<https://devfeed.tech/tags/agentic-workflows.md>), [ci](<https://devfeed.tech/tags/ci.md>), [coding](<https://devfeed.tech/tags/coding.md>), [coding-agent](<https://devfeed.tech/tags/coding-agent.md>), [coding-agents](<https://devfeed.tech/tags/coding-agents.md>), [command-line](<https://devfeed.tech/tags/command-line.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cs-se](<https://devfeed.tech/tags/cs-se.md>), [dataset](<https://devfeed.tech/tags/dataset.md>), [github](<https://devfeed.tech/tags/github.md>), [github-actions](<https://devfeed.tech/tags/github-actions.md>), [integration](<https://devfeed.tech/tags/integration.md>), [integrations](<https://devfeed.tech/tags/integrations.md>), [workflow](<https://devfeed.tech/tags/workflow.md>)

### AI overview

GHAgentCI collects 15K+ workflow histories from 6K+ mined GitHub repositories, spanning 159K+ revisions and 205K+ records of coding-agent evidence linked to workflow triggers and declared execution constraints. Its open-source extractor, cai-miner, uses an extensible catalogue to identify evidence in action references, shell commands, and workflow conventions. Manual validation of 576 stratified records found 96.1% match rates for dedicated actions and 98.8% for GitHub Agentic Workflow, with lower rates for other evidence types. Exploratory analyses report a shift toward command-line and GitHub Agentic Workflow integrations, differences in declared safeguards, and frequent removal of detected agentic workflows. The dataset is intended to support longitudinal research; the abstract does not give further detail on its trends or the lower validation rates.

### Source excerpt

arXiv:2611.15522v1 Announce Type: new Abstract: Coding agents are increasingly integrated into GitHub Actions to review pull requests, triage issues and modify code. Identifying these integrations is challenging because agentic workflows often resemble ordinary CI files, with evidence appearing in action references, shell commands and workflow conventions. We present GHAgentCI, a dataset of 15K+ workflow histories from 6K+ of 196K+ mined GitHub repositories, comprising 159K+ revisions and 205K+ agent-evidence records linked to workflow triggers and declared execution constraints. Our open-source extractor, cai-miner, detects agent-related evidence using an extensible catalogue. Manual validation of 576 stratified records confirmed 96.1% of dedicated-action matches and 98.8% of GitHub Agentic Workflow matches, with lower rates for other evidence kinds. Exploratory analyses reveal a shift toward command-line and GitHub Agentic Workflow integrations, differences in declared safeguards, and frequent removal of detected agentic workflows. GHAgentCI supports longitudinal studies of coding-agent integration into CI.

## When Evaluators of AI Agents Disagree: An Empirical Study of Native Scoring, LLM Judges, and Commit-Boundary Checks on tau2-bench

DevFeed: [When Evaluators of AI Agents Disagree: An Empirical Study of Native Scoring, LLM Judges, and Commit-Boundary Checks on tau2-bench](<https://devfeed.tech/articles/when-evaluators-of-ai-agents-disagree-an-empirical-study-of-native-scoring-llm-judges-and-commit-boundary-checks-on-tau2-bench-131691.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.14581>)

Author: Sungbin Im

Published: 2026-11-13T05:00:00Z

Content type: news

Language: en

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

Topics: [LLM evaluation / benchmarking](<https://devfeed.tech/topics/llm-evaluation-benchmarking.md>), [agentic workflows](<https://devfeed.tech/topics/agentic-workflows.md>), [Large Language Model](<https://devfeed.tech/topics/llm.md>)

Tags: [abstract](<https://devfeed.tech/tags/abstract.md>), [agent](<https://devfeed.tech/tags/agent.md>), [agentic](<https://devfeed.tech/tags/agentic.md>), [agentic-workflows](<https://devfeed.tech/tags/agentic-workflows.md>), [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-agents](<https://devfeed.tech/tags/ai-agents.md>), [airline](<https://devfeed.tech/tags/airline.md>), [all](<https://devfeed.tech/tags/all.md>), [arxiv](<https://devfeed.tech/tags/arxiv.md>), [authentication](<https://devfeed.tech/tags/authentication.md>), [based](<https://devfeed.tech/tags/based.md>), [bench](<https://devfeed.tech/tags/bench.md>), [benchmarks](<https://devfeed.tech/tags/benchmarks.md>), [boundary](<https://devfeed.tech/tags/boundary.md>), [but](<https://devfeed.tech/tags/but.md>), [commit](<https://devfeed.tech/tags/commit.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cs-cr](<https://devfeed.tech/tags/cs-cr.md>), [cs-se](<https://devfeed.tech/tags/cs-se.md>), [llm](<https://devfeed.tech/tags/llm.md>), [native](<https://devfeed.tech/tags/native.md>), [study](<https://devfeed.tech/tags/study.md>)

### AI overview

Across 2,160 tau2-bench airline and retail episodes, evaluator choice changed the assessment of agent behavior. An LLM judge repeated its verdict 98.2% of the time but agreed with native gold-state scoring only 56.2%. Of 11 episodes with forbidden database writes, judges passed 10-11; a stronger judge passed 6, while a rule-based check of whether an expected write occurred caught all 11. Human labels from 120 episodes found no judge significantly exceeded that boundary check. Forbidden writes appeared in 11.1% of episodes without gates, and verification, correction, and safe-termination gates did not significantly reduce them. Trace analysis suggests the gates' evidence digest omitted order status and customer authentication, leading to rejection of valid requests. The findings are limited to these benchmark domains and study setup.

### Source excerpt

arXiv:2611.14581v1 Announce Type: new Abstract: Agentic workflows, in which a large language model (LLM) calls tools to read and write data, are evaluated in two ways. Benchmarks compare the final state against a gold answer. Deployed services have none; an LLM judge reads the transcript and decides. Practice treats the two as interchangeable. This paper measures whether they are. We ran 2,160 episodes in tau2-bench's airline and retail domains and recorded every database write. We scored each episode four ways: native scoring against gold state, an LLM judge, that judge given the policy document, and the boundary evaluator, a minimal rule-based check of whether a write was expected against whether one occurred in the trace. Two annotators independently labeled 120 episodes for task correctness, policy compliance, and commitment correctness. The judge repeated its verdict 98.2% of the time but agreed with native scoring on 56.2%. In 11 episodes the agent executed a forbidden write. The judge passed 10 to 11, with or without the policy or transcript. A stronger judge still passed 6. The boundary evaluator, with no model call, caught all 11; no judge significantly exceeded it on human labels. Forbidden writes occurred in 11.1% of episodes without gates. Verification, correction, and safe-termination gates did not reduce them significantly. The traces show a candidate cause: the gates' evidence digest dropped the order status and customer authentication, so valid requests were rejected. The choice of evaluator decides the conclusion; the minimal check exposes failures the judges miss. Traces, code, prompts, and labels are released.

## Kimi K3.1 Pro is now available in Token Pass

DevFeed: [Kimi K3.1 Pro is now available in Token Pass](<https://devfeed.tech/articles/kimi-k3-1-pro-is-now-available-in-token-pass-133480.md>)

Original publisher: [Read original article](<https://vercel.com/changelog/kimi-k3-1-pro-is-now-available-in-token-pass>)

Author: Roman Olynyk

Published: 2026-11-12T20:56:38Z

Content type: release

Language: en

Sources: [Vercel News](<https://devfeed.tech/sources/vercel-news.md>)

Topics: [Loop Engineering](<https://devfeed.tech/topics/loop-engineering.md>), [AI-assisted coding](<https://devfeed.tech/topics/ai-assisted-coding.md>), [Language models](<https://devfeed.tech/topics/language-models.md>), [long-context](<https://devfeed.tech/topics/long-context.md>)

Tags: [agent](<https://devfeed.tech/tags/agent.md>), [agentic-workflows](<https://devfeed.tech/tags/agentic-workflows.md>), [ai-gateway](<https://devfeed.tech/tags/ai-gateway.md>), [ai-sdk](<https://devfeed.tech/tags/ai-sdk.md>), [cline](<https://devfeed.tech/tags/cline.md>), [coding-agents](<https://devfeed.tech/tags/coding-agents.md>), [context-window](<https://devfeed.tech/tags/context-window.md>), [data-retention](<https://devfeed.tech/tags/data-retention.md>), [deepseek-v4-1-flash](<https://devfeed.tech/tags/deepseek-v4-1-flash.md>), [glm-5-3-flash](<https://devfeed.tech/tags/glm-5-3-flash.md>), [k3](<https://devfeed.tech/tags/k3.md>), [kimi](<https://devfeed.tech/tags/kimi.md>), [kimi-k3-1-pro](<https://devfeed.tech/tags/kimi-k3-1-pro.md>), [moonshot-ai](<https://devfeed.tech/tags/moonshot-ai.md>), [subscription](<https://devfeed.tech/tags/subscription.md>), [team](<https://devfeed.tech/tags/team.md>), [token](<https://devfeed.tech/tags/token.md>), [tool-use](<https://devfeed.tech/tags/tool-use.md>), [vision](<https://devfeed.tech/tags/vision.md>), [zero-data-retention](<https://devfeed.tech/tags/zero-data-retention.md>)

### AI overview

Token Pass now includes Moonshot AI's Kimi K3.1 Pro, described as its most capable model for coding and agentic workflows, with vision, tool use, and a 1M-token context window. The Early Access subscription for Pro teams costs $30 per team monthly and provides $80 in monthly credit. It also includes Kimi K3, GLM 5.3, GLM 5.3 Flash, and DeepSeek V4.1 Flash. Credit can be used with coding agents connected to AI Gateway, including fx, Pi, Cline, and Command Code, or agents built with the AI SDK. Requests served through Token Pass have zero data retention. Subscribe from the Token Pass page in the team's AI Gateway dashboard, then select `moonshotai/kimi-k3.1-pro` in the connected agent's model picker.

### Source excerpt

Token Pass now includes Kimi K3.1 Pro, Moonshot AI's most capable model for coding and agentic workflows, with vision, tool use, and a 1M context window. Token Pass is an Early Access subscription for Pro teams that includes Kimi K3, GLM 5.3, GLM 5.3 Flash, and DeepSeek V4.1 Flash, with more models to come. For $30 per team per month, you get $80 in monthly credit to use in coding agents connected to AI Gateway, including fx, Pi, Cline, and Command Code, as well as agents you build with the AI SDK. Requests served through Token Pass have zero data retention. Subscribe on the Token Pass page in your team's AI Gateway dashboard, then select moonshotai/kimi-k3.1-pro in your connected agent's model picker. Read more

## Google's latest Search upgrade promises better answers to your most complicated questions

DevFeed: [Google's latest Search upgrade promises better answers to your most complicated questions](<https://devfeed.tech/articles/google-s-latest-search-upgrade-promises-better-answers-to-your-most-complicated-questions-130855.md>)

Original publisher: [Read original article](<https://techcrunch.com/2026/11/12/googles-latest-search-upgrade-promises-better-answers-to-your-most-complicated-questions/>)

Author: Sarah Perez

Published: 2026-11-12T19:27:45Z

Content type: news

Language: en

Sources: [TechCrunch | AI News & Artificial Intelligence](<https://devfeed.tech/sources/techcrunch-ai-news-artificial-intelligence.md>)

Topics: [Google Search](<https://devfeed.tech/topics/google-search.md>), [AI-driven information retrieval](<https://devfeed.tech/topics/ai-driven-information-retrieval.md>), [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [Frontier AI](<https://devfeed.tech/topics/frontier-ai.md>), [Google AI](<https://devfeed.tech/topics/google-ai.md>)

Tags: [agentic](<https://devfeed.tech/tags/agentic.md>), [agentic-workflows](<https://devfeed.tech/tags/agentic-workflows.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-mode](<https://devfeed.tech/tags/ai-mode.md>), [ai-studio](<https://devfeed.tech/tags/ai-studio.md>), [antigravity](<https://devfeed.tech/tags/antigravity.md>), [api](<https://devfeed.tech/tags/api.md>), [argon](<https://devfeed.tech/tags/argon.md>), [artificial-analysis-intelligence-index](<https://devfeed.tech/tags/artificial-analysis-intelligence-index.md>), [benchmarks](<https://devfeed.tech/tags/benchmarks.md>), [code](<https://devfeed.tech/tags/code.md>), [complex](<https://devfeed.tech/tags/complex.md>), [gemini](<https://devfeed.tech/tags/gemini.md>), [gemini-4](<https://devfeed.tech/tags/gemini-4.md>), [gemini-4-hydrogen](<https://devfeed.tech/tags/gemini-4-hydrogen.md>), [google](<https://devfeed.tech/tags/google.md>), [google-search](<https://devfeed.tech/tags/google-search.md>), [hydrogen](<https://devfeed.tech/tags/hydrogen.md>), [links](<https://devfeed.tech/tags/links.md>), [responses](<https://devfeed.tech/tags/responses.md>), [search](<https://devfeed.tech/tags/search.md>), [tc](<https://devfeed.tech/tags/tc.md>), [visual-responses](<https://devfeed.tech/tags/visual-responses.md>)

### AI overview

Google says Gemini 4 Hydrogen improves AI Mode's handling of multipart, highly specific, and typo-filled queries, using stronger intent recognition and reasoning to answer each part and generate Search's fan-out subqueries. That can surface relevant websites users might otherwise miss. AI Mode can also return more images, structured answers, comparison tables, and custom tools, with improved support across its available languages. Google describes Hydrogen as a faster, less costly option for agentic workflows than its most powerful models; it claims Hydrogen completes tasks 2.5 times faster than Gemini 3.8 Flash and beats Gemini 4 Argon on one broad intelligence benchmark at the default high thinking level. The excerpt also says Hydrogen can work alone or alongside other Gemini models, offers four thinking levels, and is rolling out globally in Search. These performance and capability statements are Google's claims.

### Source excerpt

Powered by Gemini 4 Hydrogen, Google's AI Mode is getting better at understanding complex queries, surfacing relevant links, and delivering richer visual responses.

[Next page](<https://devfeed.tech/tags/agentic-workflows.md?cursor=WyIyMDI2LTExLTEyVDE5OjI3OjQ1KzAwOjAwIiwgIjg5ZWVlYjg1LTQ4MTQtNDU3Yi1hMWQwLWI1YjIwOTI0YzkxZCJd>)