2 papers
cs.AI2026
Rubric-to-Code Credit Assignment for Reinforcement Learning
Rui Jin, Jikai Chen, Yihan Chen +6
Interactive web application generation requires models to produce usable HTML, CSS, and JavaScript applications from natural language requests. Unlike conventional code generation,…
cs.LG2026
Last Step Matters: Early Uncertainty Cannot Predict Failure in Long-Horizon Agents
Zongyue Li, Chengyue Yu, Lei Zang +3
Early failure prediction is important for long-horizon agents, as it enables timely intervention and can reduce inference and tool-use costs. Uncertainty quantification, such as ve…