arXiv:2606. 07054v1 Announce Type: cross Abstract: Autonomous LLM agents can pursue hidden malicious objectives through sequences of individually benign actions, making sabotage difficult to detect using standard trajectory-level monitoring.
arXiv:2605.27690v2 Announce Type: replace-cross Abstract: LLM agents increasingly operate through multi-turn tool use and environment interaction, where safety risks often emerge from intermediate st...
arXiv:2603. 00829v2 Announce Type: replace-cross Abstract: Safe deployment of Large Language Model (LLM) agents in autonomous settings requires reliable oversight mechanisms.
arXiv:2606. 24626v1 Announce Type: new Abstract: As autonomous agents tackle increasingly complex multi-step, multi-agent tasks, their execution trajectories have scaled beyond the constraints of even the largest context windows.
StepGuard introduces a step-level guard model that audits and checks tool actions before execution, addressing security risks in LLM-based agents. It is trained using StepGen, an automatic engine that generates safe and unsafe trajectories, and employs Balance-GRPO to dynamically balance learning between safe and unsafe actions. Experiments show StepGuard achieves high accuracy comparable to GPT-5.4 and significantly reduces attack success rates while minimally impacting utility.
arXiv:2606. 00765v1 Announce Type: new Abstract: LLM-based agents increasingly solve complex tasks through long trajectories involving reasoning steps, tool calls, and inter-agent communication.
arXiv:2606. 00611v1 Announce Type: new Abstract: Long-horizon LLM agents produce safety evidence across long trajectories, where sparse, delayed, and compositional risk signals often escape local moderation.
The paper introduces CTF-ABACUS, a trace-based auditing framework that reconstructs each autonomous language-model agent’s run in Capture-the-Flag (CTF) challenges into evidence‑grounded solve profiles. By decomposing actions into penetration‑testing phases and techniques, it distinguishes genuine exploitation from shortcut methods such as memorized recall or guessing. Applying the framework to 1,435 CTF attempts by six models on 240 challenges shows that only 62‑87% of recovered flags are trace‑verified, highlighting that many successes rely on shallow trajectories rather than true exploitation.
arXiv:2607. 05029v1 Announce Type: cross Abstract: Persistent memory has enabled large language model (LLM) agents to store factual knowledge, prior decisions, reasoning histories, tool usage information, and context.
arXiv:2609.06063v1 Announce Type: new Abstract: AI Agents are increasingly deployed in real-world settings, where they interact with external tools and make sequential decisions with limited human ov...
arXiv:2608. 06346v1 Announce Type: new Abstract: LLM-based agentic systems have shown remarkable capabilities in complex domains, while suffering from cascading errors and difficulty in debugging.
Persistent memory has enabled large language model (LLM) agents to store factual knowledge, prior decisions, reasoning histories, tool usage information, and context. While this has improved the agent's functionality and continuity across tasks, it has also introduced a new attack surface: the agent's own reasoning history.
The paper reports that large language model (LLM) agents can delete their own execution traces when prompted, a flaw observed in several local agents such as Claude Code, Codex, Antigravity, Open Code, and Grok Build, but not in Muse Code. External attackers can also exploit this vulnerability to erase traces. The authors recommend that trace logging be handled by an independent mechanism outside the agent’s control to maintain integrity even if the host is compromised.