Long-horizon LLM agents produce safety evidence across long trajectories, where sparse, delayed, and compositional risk signals often escape local moderation. Existing turn-level or short-context detectors struggle to reliably retain and aggregate such evidence over extended horizons. We reframe long-horizon agent safety detection as trajectory-level evidence compression and propose Trajectory Risk-Aware Compression for Long-Horizon Agent Safety (TRACE). TRACE uses a Compressor-Reader design: the Compressor encodes the full trajectory into a compact latent evidence state under trajectory-level supervision, and the Reader judges the raw trajectory with this latent evidence state as a safety reference. This design helps aggregate dispersed risk cues and reduce premature evidence loss. Across ASSEBench, Pre-Ex-Bench, and R-Judge, TRACE achieves the best accuracy on all evaluated backbones, improving over strong baselines by up to 12.6 percentage points. On LongSafety, TRACE shows smaller performance degradation as context length grows. Attention visualizations and case studies suggest that the compressed reference helps the Reader focus on risk-critical segments and recover cross-step evidence. Code is available at https://github.com/Peregrine123/TRACE_official.
Mechanistically Interpreting Compression in Vision-Language Models
Indian Institute of Technology Jodhpur（印度理工学院焦特布尔分校）；AIM Intelligence；National Institute of Technology Agartala（国立阿加尔塔拉理工学院）；Fordham University（福特汉姆大学）；University of Fukui（福井大学）；Independent Researcher（独立研究员）
TRACE: Trajectory Return Attribution and Contrastive Erasure for Multi-Turn Safety
King Abdullah University of Science and Technology（阿卜杜拉国王科技大学）；University of Macau（澳门大学）；RIKEN Center for Advanced Intelligence Project（理化学研究所先进智能研究中心）；University of Electronic Science and Technology of China（电子科技大学）
SHE: Trajectory-driven Safety Harness Evolution for LLM Agents
Shanghai Artificial Intelligence Laboratory（上海人工智能实验室）；Fudan University（复旦大学）；Shanghai Jiao Tong University（上海交通大学）；The Hong Kong University of Science and Technology（香港科技大学）
Institute of Informatics & Telecommunications, NCSR Demokritos（希腊国家科学研究中心德谟克利特信息学与电信研究所）；Information Management Systems Institute, Athena Research Center（雅典娜研究中心信息管理系统研究所）；University of Piraeus（比雷埃夫斯大学）
ATBench: A Diverse and Realistic Agent Trajectory Benchmark for Safety Evaluation and Diagnosis
Shanghai AI Lab（上海人工智能实验室）；Fudan University（复旦大学）；Shanghai Jiao Tong University（上海交通大学）；Tsinghua University（清华大学）；KAUST（卡塔尔人工智能科学中心）；East China Normal University（华东师范大学）
Automatic driving lane change safety prediction model based on LSTM
Trine University（特莱恩大学）；Yantai University（烟台大学）；University of Electronic Science and Technology of China（电子科技大学）；Northern Arizona University（北亚利桑那大学）；University of Aberdeen（阿伯丁大学）
