← Back to all news
arXiv Machine Learning By Ding Jia, Wei Liu, Xianglong Du, Yingjie Li, Yingqing Yang, Huili Yu, Zhangsong Zhan, Chu Zhou

PROACT-Agent: Progressive Runtime Oversight and Active Circuit-breaking for Real-Time Safety

Read the original on arXiv Machine Learning →

PROACT-Agent is a framework designed to provide proactive runtime oversight for large language model agents, aiming to prevent irreversible environmental harm by enabling real‑time guardrails. It introduces three key components: Progressive Trajectory Unrolling, Reasoning‑Augmented Causal Rectification, and Culturally‑Aware Data Localization, which together address safety drift and enforce temporal consistency. The accompanying PROACT‑Bench, a bilingual safety benchmark with 155,780 labeled states, demonstrates the framework’s effectiveness, achieving high unsafe‑class F1 scores and significantly reducing attack success rates in AgentDojo.

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 Machine Learning.

Related stories

arXiv AI
Sep 24

PASTABench: Proactive Assessment of Sequential Trajectories for Agent Safety

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
llmsagentsbenchmarkssafety
More like this →
arXiv AI
Aug 7

DreamGuard: Efficient Runtime Guardrail for LLM Agents via Risk-Aware World Model

arXiv:2608. 05695v1 Announce Type: new Abstract: As large language model (LLM) agents increasingly invoke external tools and interact with real-world systems, unsafe actions may cause irreversible consequences on external states, user data, and downstream services.

By Wenhao Lin, Chenyu Yu, Xingwei Lin, Sicong Cao, Xiang Chen, Lei Xue, Le Yu, Letian Sha, Chunming Wu
llmsagentsbenchmarkssafety
More like this →
arXiv AI
Aug 11

SHE: Trajectory-driven Safety Harness Evolution for LLM Agents

arXiv:2608. 09885v1 Announce Type: new Abstract: The safety of large language model (LLM) agents depends not only on model weights but also on the agent harness that manages context, memory, tools, permissions, and runtime control.

By Wanying Qu, Qinghua Mao, Yu Li, Jiyao Liu, Xin Zhang, Dadi Guo, Yanxu Zhu, Qingyu Liu, Leitao Yuan, Xi Lin, Shanfeng Zhu, Yanwei Fu, Jing Shao, Xia Hu, Dongrui Liu
llmsagentsmultimodalbenchmarkssafety
More like this →
arXiv AI
Aug 26

RePolicy: Reinforcement Learning for Safety-Policy Invocation in Agent Safeguards

RePolicy is a reinforcement learning approach designed to invoke safety policies for language model agents by evaluating entire execution trajectories within context-dependent policy libraries. It generates policy-grounded rationales and safety judgments, and is initialized with the PolicyTraj-20K dataset before fine-tuning via GRPO with verifiable rewards and policy-context perturbation. Experiments on six safety benchmarks demonstrate strong safety-detection performance and robust policy invocation across varying contexts.

By Houcheng Jiang, Boxuan Zhang, Qiyong Zhong, Junfeng Fang, Xiang Wang, Xiangnan He
llmsagentsreinforcement-learningfine-tuningbenchmarkssafety
More like this →