Latest Agentic AI, AI Agents & Agent Governance News – 29 October 2026
🤖 Top Agentic AI, AI Agents & Governance Articles
Your twice-weekly roundup of the latest in Agentic AI, AI agents, and agent access, permission, governance & audit — covering agent frameworks, MCP/tool-use, agent identity, non-human access control, AI governance and agent security.
OpenAI and ServiceNow expand partnership across enterprise workflows
Source : OpenAI NewsOpenAI and ServiceNow expand their partnership to bring OpenAI models and agents into ServiceNow and ServiceNow workflows into ChatGPT and Codex.
Legora is building the agentic operating system for legal work
Source : OpenAI NewsSee how Legora uses OpenAI models, ChatGPT, and Codex to accelerate legal workflows, expand contract analysis, and free lawyers to focus on higher-value work.
Retell uses OpenAI models to help power 100M monthly calls
Source : OpenAI NewsGPT-6 Astra tops Retell’s voice agent benchmark, while Codex helps it reach a $1.6M annual revenue run rate per employee.
Turning Database Grading into RL Rewards: Post-Training Agents with ThinkingBox
Source : Hugging FaceThe focus on AI safety disasters ignores everyday harms
Source : MIT Technology Review AIConsider what passes for success in technology policy. An AI company promises that its chatbot will not encourage suicide. A social media platform makes it more difficult for children to buy fentanyl. These are important protections, and they should have existed all along. But companies can clear these low bars while continuing to make products…
The Foundations of Scalable AI
Source : MIT Technology Review AIA scalable AI system requires a strong foundation. Data, engineering, platforms, operating models, and governance must converge to work as one. This session from MIT Technology Review’s EmTech Future conference explores what it takes to build that foundation in a highly regulated environment and how a responsible, trustworthy implementation can turn emerging capabilities, including agentic…
Attacker Relentlessly Scans for Credentials by Impersonating AI Bots
Source : Dark ReadingThe threat actor lurked behind bots posing as agents from OpenAI, Anthropic, Meta, and others to find exposed data.
SCOPE: Source Credibility and Outlet Profiling Engine
Source : arXiv Multi-Agent SystemsarXiv:2610.35929v1 Announce Type: new Abstract: We present SCOPE, a multi-agent system for profiling news media outlets with respect to bias, factuality, and credibility. Given an outlet URL, SCOPE coordinates specialized agents for article acquisition, content analysis, external evidence search, scoring, and report generation. The system follows an MBFC-style methodology while making intermediate evidence and agent outputs inspectable through a structured demonstration interface. On a benchmark of 200 media outlets, SCOPE outperforms LLM-only, article-only, search-only, and media-background-check baselines on most metrics, achieving the lowest bias and factuality MAE, perfect failed-fact-check detection, and the lowest factual error rate. These results suggest that decomposed, evidence-grounded agent workflows can support more transparent and reliable media profiling. Our code is available at https://github.com/mbaisbay/SCOPE, and a live demonstration at https://scope-demo.streamlit.
Who Convinced Whom? Tracing How LLMs Change Their Minds in Multi-Agent Systems
Source : arXiv Multi-Agent SystemsarXiv:2610.35930v1 Announce Type: new Abstract: Multi-agent debate (MAD) aims to improve language-model decisions through the exchange of arguments, yet agreement after debate need not reflect independent corroboration. We investigate how peer communication influences individual decisions and collective outcomes through behavioral and internal interventions. We introduce MAD Bench, a 2,400-question benchmark spanning knowledge and reasoning, values and moral judgment, and safety and refusal, and evaluate three open-weight models using a round-matched independent-reflection control. Among answer-changing responses, a forced-choice readout before rationale generation matches the eventual answer more often in debate than in reflection (65.4% versus 22.3% on Qwen3.5-9B). Message ablations reveal model-dependent effects of peer answers and reasoning, while attributing identical text to the receiver rather than another agent substantially changes its influence. For the tested source descrip
PASS Is a Claim, Not an Observation: Mechanical Re-verification of 10 Self-Asserted Fix Claims in a Live Multi-Agent Audit Layer
Source : arXiv Multi-Agent SystemsarXiv:2610.35950v1 Announce Type: new Abstract: When agents claim to have fixed their own defects, how do we know the fix is real? We mechanically re-verified 10 self-asserted code-level fix claims from a privileged coordination agent (azone_god) operating in AITRAP, a live multi-agent knowledge-tree platform. These 10 claims were extracted from a corpus of 179 coordination broadcasts (28 containing structured fix assertions, 31 unique fix-ID/message pairs, 18 distinct fix identifiers). Fix claims use mixed English/Chinese formats (PASS, checkmarks, and "verification passed" declarations). Each code-level claim was checked against three criteria: (1) file modification timestamp (mtime) consistency -- 70% pass; (2) presence of the claimed defensive pattern at the specified identifier and call site -- 60% pass in the claimed file (80% anywhere in the codebase); (3) deterministic rule-based re-verification from the broadcast announcement alone -- 80% pass. The critical finding: among cla
The Trinity:Capability-Driven Recursive Self-Improvement for Multimodal Agents
Source : arXiv Artificial IntelligencearXiv:2610.36077v1 Announce Type: new Abstract: Multimodal intelligence can be viewed as human-guided co-evolution between worlds and agents through interaction. However, scaling this process faces two bottlenecks: constructing heterogeneous, verifiable environments is costly, and manual Harness iteration cannot keep pace with growing task diversity and complexity. A key insight is that tasks with different modalities and surface forms can share the same underlying capability requirements. We therefore introduce The Trinity, a recursive self-improvement framework coupling world generation with Harness evolution through three roles: Creator, Explorer, and Evolver. Drawing on verified execution trajectories, Evolver shifts the basis of task organization from surface categories to shared requirements, reorganizing the original task tree into a hierarchical capability tree. We introduce Capability-Driven Real2Sim2Real: for heterogeneous tasks at the same node, Creator abstracts their comm
CohortFlow: A Steerable Clinical Cohort Curation Agent with Localized Semantic Correction
Source : arXiv Artificial IntelligencearXiv:2610.36100v1 Announce Type: new Abstract: Language model agents for clinical cohort curation should accommodate evolving eligibility criteria without repeatedly processing unchanged requirements. We introduce CohortFlow, a steerable agent that represents natural language corrections as localized updates to a structured cohort specification and reconciles them with a persistent execution graph. Explicitly recorded semantic dependencies enable affected computations to be selectively invalidated while preserving valid prior results. On 100 scenarios derived from clinical-trial eligibility criteria, comprising 126 correction turns, localized steering achieves 77.0% requirement micro-F1 versus 76.4% for full regeneration using the same 8B model, a small numerical advantage that is not statistically significant ($p=0.493$). It reduces mean correction latency by 64.8% after completion and 44.3% during execution, with 38.1% fewer model calls. In a separate proof-of-concept evaluation ov
Skill Dreaming: Evolving Repository Skills through Pull Request Streams
Source : arXiv Artificial IntelligencearXiv:2610.36188v1 Announce Type: new Abstract: Large language model (LLM) agents increasingly rely on reusable skills for complex software engineering tasks, making skill libraries essential for repository development and maintenance. However, repository-specific skills must evolve with changing code structures, implementation conventions, and maintenance requirements. Pull requests (PRs) provide a natural source of such knowledge by recording how repositories evolve through implementation and review. Meanwhile, new PRs must follow repository-specific implementation patterns, modify related components consistently, and ensure that existing tests continue to pass while adding coverage for new functionality. This creates a mutually reinforcing cycle: PRs provide knowledge for updating skills, while these skills improve future PRs, maintain repositories, and support further skill evolution. To enable this co-evolution of PRs, repositories, and skills, we propose Skill Dreaming, a framew
