让长时序智能体安全检测更准，通过压缩轨迹证据提升风险识别能力。
TRACE: Trajectory Risk-Aware Compression for Long-Horizon Agent Safety
- 用压缩-阅读架构将全程轨迹转为紧凑证据状态
- 在多个数据集上比现有方法最高提升12.6个百分点准确率
- 适合需要长期安全监控的复杂智能体系统
长时序大模型智能体在长时间轨迹中产生安全证据，但稀疏、延迟且组合性的风险信号常被局部审查忽略。现有逐轮或短上下文检测器难以可靠保留并聚合此类证据。我们提出轨迹级证据压缩框架TRACE，采用压缩器-阅读器设计：压缩器在轨迹级监督下将完整轨迹编码为紧凑的潜在证据状态，阅读器以该状态为安全参考判断原始轨迹。此设计有助于聚合分散的风险线索并减少早期证据丢失。在ASSEBench、Pre-Ex-Bench和R-Judge上，TRACE在所有评估骨干模型中均取得最佳准确率，相比强基线最高提升12.6个百分点；在LongSafety上，其性能随上下文长度增长下降更小。注意力可视化与案例分析表明，压缩后的参考帮助阅读器聚焦风险关键段并恢复跨步证据。代码已开源：https://github.com/Peregrine123/TRACE_official。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。