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
PASTABench introduces a benchmark of 1,139 multi-turn trajectories to evaluate proactive safety monitoring in large language models. It formalizes three dimensions of intervention—whether, when, and what risk—to address gaps in step-level isolation and post-hoc trajectory assessment. The study finds that proactive intervention is largely unsolved, with the best model achieving only 40.74% optimal-timing interventions, and reveals that smaller models’ safety scores are often driven by lexical overfitting rather than true risk comprehension.
By Jiapeng Sun, Yujin Zhou, Han Zhu, Pengcheng Wen, Jiayi Zhou, Sirui Han, Yike Guo
SafeEvolve is an experience-driven framework that co‑evolves a harness and policy to align large‑language‑model agents with safety goals. It uses completed on‑policy trajectories to update safety prompts and hierarchical skills, then applies a two‑stage SFT‑RL training loop that bootstraps the policy with the evolved harness and refines it through verifier‑augmented rewards. Experiments on agentic safety benchmarks show that SafeEvolve improves the safety‑utility tradeoff, achieving a three‑fold reduction in ASR on AgentDojo for Qwen3.5‑4B while increasing benign utility from 59.79% to 61.86%.
By Qinghua Mao, Wanying Qu, Dadi Guo, Leitao Yuan, Qingyu Liu, Yu Li, Guanxu Chen, Yanwei Fu, Xi Lin, Xia Hu, Dongrui Liu
The paper introduces SCOPE, a method that post‑trains computer‑use agents to balance task completion with safety by conditioning actions on environmental risk. It combines supervised fine‑tuning on three trajectory types—capability demonstrations, safe continuations, and explicit refusals—followed by reinforcement learning to improve performance. Experiments starting from Qwen3.5‑9B show that SCOPE‑RL achieves high task success and attack‑avoidance rates, outperforming other agents on OSWorld and OS‑BLIND benchmarks.
By Zeyu Kang, Zhenyun Yin, Yang Zhang, Shan He, Shanzhe Lei, Yanjiu Zhong, Xinquan Chen, Yuhong Wang
The paper introduces MENTOR, a multi‑agent framework that provides on‑policy pedagogical intervention to address zero‑reward collapse in reinforcement learning from verifiable rewards. MENTOR diagnoses failures in real time and generates targeted prompts to guide the learning agent, integrating seamlessly with existing policy optimization pipelines such as GRPO. Experiments on math and code generation tasks show that MENTOR significantly reduces collapse, achieving up to 78.3% relative gains on Llama‑3.2‑3B‑Instruct.
By Guanlan Yue, Hang Yu, Xiaoyong Huang, Ruipeng Li, Wei Zhang, Bingchang Liu, Rui Wang
SafeEvolve is an experience-driven framework that co‑evolves a harness and policy to improve safety alignment for LLM‑based agents. It uses on‑policy trajectory safety evidence to update safety prompts and hierarchical skills, producing auditable harness artifacts. The policy is trained via a two‑stage SFT‑RL pipeline that bootstraps with the evolved harness and then refines behavior through verifier‑decomposed rewards, yielding a better safety‑utility tradeoff on benchmarks such as AgentDojo.