arXiv AI June 16, 2026 By Andoni Rodr\'iguez, Alberto Pozanco, Daniel Borrajo

Is Your Agent Playing Dead? Deployed LLM Agents Exhibit Constraint-Evasive Fabrication and Thanatosis

arXiv:2606. 14831v1 Announce Type: cross Abstract: This paper presents and characterizes a spectrum of previously unreported behaviours we term Constraint-Evasive Fabrication (CEF): when an LLM agent operates under irreconcilable constraints (where no response can simultaneously satisfy all active rules) it spontaneously fabricates plausible external obstacles and presents them as a fact.

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

arXiv AI

Jul 14

Heterogeneous Agent Cohorts for Safe Open-Ended Exploration with Runtime Constraint Memory

arXiv:2607. 11226v1 Announce Type: new Abstract: LLM agents today are caught in an awkward bind.

By Tengjiao Liu

llms agents safety

arXiv AI

Jul 23

Guardrails as Scapegoats: Auditing Unfaithful Safety Refusals in Tool-Augmented LLM Agents

arXiv:2607. 19449v1 Announce Type: cross Abstract: Evaluation frameworks for tool-augmented LLM agents focus overwhelmingly on capability metrics or explicit tool crashes, leaving silent infrastructure failures and HTTP 200 responses with empty, null, or malformed payloads largely unaudited.

By Aarushi Singh

llms agents benchmarks safety

arXiv AI

Jun 30

Governance Decay: How Context Compaction Silently Erases Safety Constraints in Long-Horizon LLM Agents

arXiv:2606. 22528v2 Announce Type: replace Abstract: Modern LLM agents increasingly rely on context compaction, summarization, or eviction to keep long-running sessions within a token budget.

By Shiyang Chen

llms agents nlp benchmarks safety

arXiv AI

Jul 14

AgentCheck: A Reproduce-Intervene-Mitigate Workbench for LLM Agents over MCP

arXiv:2607. 11098v1 Announce Type: cross Abstract: Tool-using LLM agents are mostly evaluated assuming all tools work.

By Aritra Mazumder, Nusrat jahan Lia

llms agents

arXiv AI

Jun 9

Where Instruction Hierarchy Breaks: Diagnosing and Repairing Failures in Reasoning Language Models

arXiv:2606. 07808v1 Announce Type: new Abstract: Reasoning language models deployed in agentic workflows must follow an instruction hierarchy: when instructions from different sources conflict, the model should obey the highest-privilege applicable instruction.

By Sanjay Kariyappa, G. Edward Suh

llms agents benchmarks

arXiv AI

Jul 3

A Unified Framework for the Evaluation of LLM Agentic Capabilities

arXiv:2605. 27898v2 Announce Type: replace Abstract: As LLMs are increasingly deployed as agents, reliable assessment of their agentic capabilities has become essential.

By Pengyu Zhu, Lijun Li, Yaxing Lyu, Qianxin Luo, Jingyi Yang, Yi Liu, Tingfeng Hui, Xinyu Yuan, Li Sun, Sen Su, Jing Shao

llms agents benchmarks safety

Related stories

Heterogeneous Agent Cohorts for Safe Open-Ended Exploration with Runtime Constraint Memory

Guardrails as Scapegoats: Auditing Unfaithful Safety Refusals in Tool-Augmented LLM Agents

Governance Decay: How Context Compaction Silently Erases Safety Constraints in Long-Horizon LLM Agents

AgentCheck: A Reproduce-Intervene-Mitigate Workbench for LLM Agents over MCP

Where Instruction Hierarchy Breaks: Diagnosing and Repairing Failures in Reasoning Language Models

A Unified Framework for the Evaluation of LLM Agentic Capabilities