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.
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.
Related stories
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.
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.
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.
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.
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.
arXiv AI
Jul 3
Safety Testing LLM Agents at Scale: From Risk Discovery to Evidence-Grounded Verification
arXiv:2607. 01793v1 Announce Type: new Abstract: LLM agents increasingly perform autonomous actions through external tools, leading to complex and evolving safety risks.
arXiv AI
Jul 14
AgentAbstain: Do LLM Agents Know When Not to Act?
arXiv:2607. 10059v1 Announce Type: new Abstract: Agent systems based on large language models (LLMs) are increasingly deployed for autonomous tasks, yet existing evaluations mostly focus on task success rather than whether agents know when to abstain.
arXiv AI
Jun 18
SafeClawBench: Separating Semantic, Audit-Evidence, and Sandbox Harm in Tool-Using LLM Agents
arXiv:2606. 18356v1 Announce Type: cross Abstract: Tool-using language-model agents introduce security failures that go beyond unsafe text: they can disclose protected objects, write persistent memory, send messages, modify databases, or trigger harmful code and tool effects.
arXiv AI
Aug 5
Designing for Doubt: The Case for Informed Abstention in Autonomous Agents
arXiv:2606. 02965v2 Announce Type: replace Abstract: As large language models gain tool access and are deployed as autonomous agents capable of editing records, executing transactions, and modifying infrastructure, we still evaluate them based on the sole metric of task completion.
arXiv AI
Aug 5
Injection-Execution Dissociation: A Mechanistic Evaluation of Persistent Memory Attacks and Defenses in Stateful LLM Agents
arXiv:2605. 08442v5 Announce Type: replace-cross Abstract: We discover that prompt-injection success and tool-execution success are separable safety properties: defenses that block injection do not necessarily block execution, and vice versa.
arXiv AI
Jul 14
Agent Hacks Agent: Autoresearch for Production-Agent Red-Teaming
arXiv:2607. 11698v1 Announce Type: cross Abstract: Production LLM agents such as Claude Code and Codex operate over untrusted content, files, commands, and workspace state, making safety failures directly actionable.