arXiv:2606. 02965v1 Announce Type: new Abstract: Benchmarks for autonomous agents measure whether agents complete tasks, yet this framing is systematically blind to whether an agent should have proceeded at all.
By Victor Ojewale, Suresh Venkatasubramanian
arXiv:2606. 09890v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly deployed as autonomous agents capable of executing multi-step action trajectories toward a given objective.
By Hainiu Xu, Italo Luis da Silva, Jiangnan Ye, Yuhao Wang, Wei Liu, Linyi Yang, Jonathan Richard Schwarz, Nicola Paoletti, Yulan He, Hanqi Yan
HINTBench is a new benchmark for evaluating agents’ intrinsic risk, comprising 596 trajectories (400 synthetic risky, 136 synthetic safe, 30 real risky, 30 real safe) with an average length of 24 steps. It supports three tasks—risk detection, risk-step localization, and intrinsic failure-type identification—using a unified five-constraint taxonomy. Experiments show a large performance gap: while large language models can detect risky trajectories, they score below 37 on strict-F1 for risk-step localization, and existing guard models transfer poorly to this setting.
By Jiacheng Wang, Jinchang Hou, Fabian Wang, Ping Jian, Chenfu Bao, Zhonghou Lv
arXiv:2606. 05805v1 Announce Type: new Abstract: LLM-based guardrails typically safeguard agents by evaluating proposed actions or inputs before execution, producing safety signals such as binary allow/deny decisions, risk categories, and/or explanatory rationales about potential policy violations.
By Yuhao Sun, Jiacheng Zhang, Shaanan Cohney, Zhexin Zhang, Feng Liu, Xingliang Yuan
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.
By Zhijie Zheng, Yu Li, Chen Qian, Yuqian Fu, Yanwei Fu, Lu Sheng, Jing Shao, Dongrui Liu
arXiv:2609.39107v1 Announce Type: new
Abstract: Large Language Models (LLMs) have been applied in various fields. However, ensuring compliance and safety of LLMs, such as avoiding discrimination and...
By Yan Zhang, Chuming Wei, Ruien Li, Yaoyao Peng, Wusheng Zhang, Guangwen Yang