Showing cs.AIShow all
2 papers · 1 filter
cs.AI2026
Harness-Delta Attribution: Dissecting Gains From Harness Evolution
Wenxuan Ding, Qin Lu, Changlong Yu +5
Harness evolution automatically optimizes the prompts, skills, tools, and orchestration code around a fixed-weight model, offering a way to improve agentic systems without updating…
cs.AI2026
TPO: Uncertainty-Guided Exploration Control for Stable Multi-Turn Agentic Reinforcement Learning
Haixin Wang, Hejie Cui, Chenwei Zhang +7
Recent progress in multi-turn reinforcement learning (RL) has significantly improved reasoning LLMs' performances on complex interactive tasks. Despite advances in stabilization te…