← Back to all news
arXiv AI By Zhijie Zheng, Yu Li, Chen Qian, Yuqian Fu, Yanwei Fu, Lu Sheng, Jing Shao, Dongrui Liu

StepGuard: Learning Step-Level Guardrails with Scalable Supervision and Safety-Utility Balancing

Read the original on arXiv AI →

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.

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.

Related stories

arXiv AI
Oct 9

Safe Actions Alone Do Not Ensure Safe Agents: Identifying Unfulfilled Obligations with Guard Models

Guard models are used to prevent LLM agents from performing forbidden actions, but this alone does not guarantee safety. The paper shows that many agent trajectories contain unfulfilled safety‑critical obligations—actions that should have been performed—highlighting a new source of risk. To address this, the authors introduce ObligationBench, a benchmark of 240 expert‑validated trajectories, and develop ObligationGuard, a model that improves obligation detection recall and exact‑match rates over existing models.

By Youwei Feng, Yitong Zhang, Yuetong Liu, Jia Li
llmsagentsbenchmarkssafety
More like this →