arXiv:2607. 21518v1 Announce Type: new Abstract: Even a current high-capability LLM can appear safer when shown a dangerous objective directly than when other agents transform and relay its direction.
Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.
arXiv:2607. 07097v1 Announce Type: new Abstract: Safety evaluations of multi-agent LLM systems often compare a direct prompt with a planner-executor pipeline and report the difference as a single "pipeline effect.
arXiv:2609.27900v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly deployed in multi-agent systems where a principal agent decomposes tasks and delegates them to subordinat...
arXiv:2606. 00914v1 Announce Type: new Abstract: LLM agents increasingly act after consuming ranked external information streams such as social feeds, search results, retrieval contexts, and email queues, yet safety evaluations almost always test the model or the user prompt in isolation, never the upstream ranker that decides what the agent reads just before it acts.
arXiv:2609.39050v1 Announce Type: cross Abstract: As multi-agent systems enter high-stakes domains, the possibility that agents may circumvent safety boundaries is a growing concern. Prior work has e...
The paper introduces a new skill poisoning technique for large language model agents that decouples the pretext (rationale) from the actuation (operation). By separating these two risk‑realization factors, the authors create coordinated pretext‑actuation skill pairs that allow malicious actions to remain hidden within legitimate agent behavior. An automated framework is presented to discover execution dependencies, synthesize these skill pairs, and refine them through closed‑loop feedback, achieving high attack success in both single‑session and persistent scenarios.
arXiv:2606. 04035v1 Announce Type: cross Abstract: We present a systematic study of domain-dependent safety behavior in open-weight LLMs: 7 standardized experiments across 7 ethical domains, testing 5 models (12B--70B) in 4,200 interactions with dual-judge validation.