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

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. 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 pr