arXiv AI July 23, 2026 By Thamilvendhan Munirathinam

Will the Agent Recuse, and Will It Stop? Measuring LLM-Agent Compliance with In-Band Governance Signals at the Access Door and Mid-Flight

arXiv:2606. 06460v3 Announce Type: replace-cross Abstract: Autonomous LLM agents increasingly hold real credentials and operate infrastructure with no human in the loop, yet operators have no standard way to tell an agent a resource is off-limits, or to ask a running agent to stand down: access controls either admit it or hard-fail it.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv AI.

arXiv AI

Jun 6

Will the Agent Recuse Itself? Measuring LLM-Agent Compliance with In-Band Access-Deny Signals

arXiv:2606. 06460v1 Announce Type: cross Abstract: As autonomous LLM agents increasingly hold real credentials and operate infrastructure without a human in the loop, operators have no standard way to tell an agent that a resource is off-limits.

By Thamilvendhan Munirathinam

llms agents robotics

arXiv AI

Jun 19

Trustworthy Multi-Agent Systems: Mitigating Semantic Drift with the Argent Signaling Protocol

arXiv:2606. 19356v1 Announce Type: cross Abstract: When multi-agent LLM systems produce bad answers, not all failures are equal: some answers are grounded in the right material but incomplete, while others are simply ungrounded and should be stopped.

By Anantha Sharma

llms agents benchmarks

arXiv AI

Jul 9

Reason Less, Verify More: Deterministic Gates Recover a Silent Policy-Violation Failure Mode in Tool-Using LLM Agents

arXiv:2607. 07405v1 Announce Type: new Abstract: Tool-using LLM agents can violate the very policies they are deployed to enforce while appearing to complete the task successfully.

By Vikas Reddy, Sumanth Reddy Challaram, Abhishek Basu

llms agents benchmarks

arXiv AI

Jul 17

Falsifiable Release Gates for Self-Improving Systems

arXiv:2607. 13070v1 Announce Type: cross Abstract: Safety claims on self-improving agent runtimes are almost always self-graded: a policy file, a guardrail, or a README commitment.

By Deepak Soni

agents safety

arXiv Machine Learning

Jul 31

Safety-Gated Agentic Supervisory Control on a Coupled Distillation Benchmark: Regime Map, Auditable Gate, and Co-Design Findings

arXiv:2607. 27849v1 Announce Type: cross Abstract: An open-weight LLM can write composition setpoints every five minutes.

By Christian Rosenthal

llms agents efficiency benchmarks safety

arXiv AI

Jul 14

Temporary Authority, Permanent Effects: Commit-Time Authorization for LLM Agents

arXiv:2607. 10487v1 Announce Type: cross Abstract: LLM agents can commit durable effects from authority evidence that was valid earlier in execution: a DOM snapshot, approval epoch, version witness, branch token, or worker result.

By Igor Santos-Grueiro

llms agents

Related stories

Will the Agent Recuse Itself? Measuring LLM-Agent Compliance with In-Band Access-Deny Signals

Trustworthy Multi-Agent Systems: Mitigating Semantic Drift with the Argent Signaling Protocol

Reason Less, Verify More: Deterministic Gates Recover a Silent Policy-Violation Failure Mode in Tool-Using LLM Agents

Falsifiable Release Gates for Self-Improving Systems

Safety-Gated Agentic Supervisory Control on a Coupled Distillation Benchmark: Regime Map, Auditable Gate, and Co-Design Findings

Temporary Authority, Permanent Effects: Commit-Time Authorization for LLM Agents