works on
cross-tokenizer 1language model distillation 1large language models 1on-policy learning 1reinforcement learning framework 1

From the 1 of 21 linked papers with an AI index.

activity
20242026
collaborators
Showing cs.AIShow all

1 paper · 1 filter

cs.AI2026

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

Zhepei Hong, Lin Wang, Liting Li +5

Long-horizon LLM agents produce safety evidence across long trajectories, where sparse, delayed, and compositional risk signals often escape local moderation. Existing turn-level o…