arXiv AI June 8, 2026 By Vijitha Mittapalli, Shreyaa Jayant Dani, Satya Srujana Pilli, Snigdha Ansu, Mohammadreza Teymoorianfard, Franck Dernoncourt, Hongjie Chen, Yu Wang, Ryan A. Rossi, Nesreen K. Ahmed

TRACE: Trajectory Reasoning through Adaptive Cross-Step Evidence Aggregation for LLM Agents

Read the original on arXiv AI →

arXiv:2606. 07054v1 Announce Type: cross Abstract: Autonomous LLM agents can pursue hidden malicious objectives through sequences of individually benign actions, making sabotage difficult to detect using standard trajectory-level monitoring.

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.

arXiv Machine Learning

Sep 22

TRACES: Proactive Safety Auditing for Multi-Turn LLM Agents via Trajectory-State Modeling

arXiv:2605.27690v2 Announce Type: replace-cross Abstract: LLM agents increasingly operate through multi-turn tool use and environment interaction, where safety risks often emerge from intermediate st...

By Jiaqian Li, Yanshu Li, Boxuan Zhang, Ruixiang Tang, Kuan-Hao Huang

llms agents benchmarks safety

arXiv AI

Jun 2

Constitutional Black-Box Monitoring for Scheming in LLM Agents

arXiv:2603. 00829v2 Announce Type: replace-cross Abstract: Safe deployment of Large Language Model (LLM) agents in autonomous settings requires reliable oversight mechanisms.

By Simon Storf, Rich Barton-Cooper, James Peters-Gill, Marius Hobbhahn

llms agents

arXiv AI

Jun 24

SAFARI: Scaling Long Horizon Agentic Fault Attribution via Active Investigation

arXiv:2606. 24626v1 Announce Type: new Abstract: As autonomous agents tackle increasingly complex multi-step, multi-agent tasks, their execution trajectories have scaled beyond the constraints of even the largest context windows.

By Chenyang Zhu, Jiayu Yao, Kushal Chawla, Youbing Yin, Nathan Wolfe, Pengshan Cai, Jingyu Wu, Spencer Hong, Sangwoo Cho, Shi-Xiong Zhang, Daben Liu, Sambit Sahu, Erin Babinsky

llms agents benchmarks

arXiv AI

Aug 26

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

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

llms agents safety

arXiv AI

Jun 2

FALAT: Tracing Failures in LLM Agent Trajectories via Dependency-Guided Search

arXiv:2606. 00765v1 Announce Type: new Abstract: LLM-based agents increasingly solve complex tasks through long trajectories involving reasoning steps, tool calls, and inter-agent communication.

By Md Nakhla Rafi, Md Ahasanuzzaman, Dong Jae Kim, Zhijie Wang, Tse-Hsun Chen

llms agents benchmarks

arXiv AI

Jun 2

TRACE: Trajectory Risk-Aware Compression for Long-Horizon Agent Safety

arXiv:2606. 00611v1 Announce Type: new Abstract: Long-horizon LLM agents produce safety evidence across long trajectories, where sparse, delayed, and compositional risk signals often escape local moderation.

By Zhepei Hong, Lin Wang, Liting Li, Haokai Ma, Junfeng Fang, Fei Shen, Dan Zhang, Xiang Wang

llms agents safety

One email a morning, machine-written

Related stories

TRACES: Proactive Safety Auditing for Multi-Turn LLM Agents via Trajectory-State Modeling

Constitutional Black-Box Monitoring for Scheming in LLM Agents

SAFARI: Scaling Long Horizon Agentic Fault Attribution via Active Investigation

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

FALAT: Tracing Failures in LLM Agent Trajectories via Dependency-Guided Search

TRACE: Trajectory Risk-Aware Compression for Long-Horizon Agent Safety