arXiv AI By Yihan Xia, Taotao Wang

When Should Agent Trust Be Conditional? Characterizing and Attacking Skill-Conditional Reputation in Agent Swarms

Read the original on arXiv AI →

arXiv:2606. 14200v1 Announce Type: new Abstract: Open platforms increasingly route tasks among heterogeneous LLM agents--differing in base model, scaffold, and tool stack--whose competence varies sharply by skill: an agent excellent at one skill may be useless at another.

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

arXiv AI
Aug 7

When Self-Evolution Backfires: Pre-Commit Gating against Skill Contamination in LLM Agents

arXiv:2608. 05810v1 Announce Type: new Abstract: Self-evolving agents accumulate capability by distilling reusable skills from their execution trajectories, but we find this process is not monotonic: past a critical pool size, newly added skills degrade performance instead of improving it.

By Linfang Shang, Ming Xu, Yiding Sun, Tianle Xia, Lingxiang Hu, Lan Xu, Ning Zheng
arXiv AI
Jun 30

Pessimism's Paradox: Conservative Offline Training Amplifies Reward Hacking During Online Adaptation in Reasoning Models

arXiv:2606. 30627v1 Announce Type: cross Abstract: Conservative offline training is widely advocated as a safe foundation for subsequent online adaptation: if a policy stays close to well-supported behaviour, the argument goes, it is less likely to exploit imperfections in a learned reward model.

By Subramanyam Sahoo, Aman Chadha, Vinija Jain, Divya Chaudhary
arXiv AI
1d ago

CompoSkill: Compositional Skill Chain Attacks from Individually Scanner-Passing LLM Agent Skills

arXiv:2608. 16246v1 Announce Type: cross Abstract: Autonomous AI agents tackling Long Horizon Tasks depend on marketplace skills that are certified one at a time: a scanner returns a safety verdict for each skill and declares the ecosystem safe if every package passes.

By Mingxiao Liu, Zhoumian Jiang, Jianan Ma, Jian Zhang, Jialuo Chen, Xinhao Deng, Zhen Wang