AIBullisharXiv – CS AI · 6h ago7/10
🧠
TRACE: Trajectory Risk-Aware Compression for Long-Horizon Agent Safety
Researchers introduce TRACE, a novel safety detection system for long-horizon LLM agents that compresses extended trajectories into compact evidence states to better identify distributed risk signals. The method achieves up to 12.6 percentage points improvement over baselines across multiple safety benchmarks while maintaining performance stability as context length increases.