2 papers
cs.AI2026
One Readout, Many Repairs: Diffusion-Guided Hierarchical Search for Tool-Agent Repair
Xiang Xia, Cheng Yan, Fan Xu +4
Tool agents use large language models to act through external tools, yet successfully executed calls can still leave user requests unfulfilled. Tool-agent repair seeks alternative…
cs.AI2026
UPAIR: Diagnosing Reasoning States via Uncertainty-Progress Alignment for Selective Intervention
Cheng Yan, Zhijun Fan, Guangyang Ye +4
While test-time scaling improves the problem-solving ability of large reasoning models (LRMs) through additional inference-time computation, it can also exacerbate overthinking and…