Showing cs.AIShow all
3 papers · 1 filter
cs.AI2026
Mechanist: AI as a Scientific Instrument for Discovering the Mechanisms of Intelligence
Mengru Wang, Junfeng Fang, Shuofei Qiao +16
AI models have achieved remarkable success across diverse domains, yet the mechanisms underlying their capabilities and the risks they may pose remain poorly understood. As AI deve…
cs.AI2026
ReflectRL: Learning from Golden Negative Trajectories via Reflective-to-Direct Reasoning
Jinhe Bi, Chennan Zhou, Zengjie Jin +10
On-policy training has emerged as a powerful post-training paradigm for improving the reasoning capabilities of large language models, and is often enhanced by golden trajectories…
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…