Showing cs.AIShow all
3 papers · 1 filter
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…
cs.AI2026
REFLEX: Rethinking MoE Inference as Refinement-Aware Compute Allocation in Diffusion Language Models
Xiang Xia, Cheng Yan, Yiming Zhang +3
Mixture-of-experts (MoE) models increase parameter capacity by activating only a small subset of experts for each token. This conditional-computation paradigm has enabled autoregre…