3 papers
cs.CL2026
CP-Agent: A Calibrated Risk-Controlled Agent for Feedback-Driven Competitive Programming
Peisong Wang, Bowen Liu, Zehua Li +4
Large language models still struggle with contest-level programming, while many agentic remedies rely on massive inference-time sampling or expensive multi-stage post-training. We…
cs.LG2025
Chain of Execution Supervision Promotes General Reasoning in Large Language Models
Nuo Chen, Zehua Li, Keqin Bao +2
Building robust and general reasoning ability is a central goal in the development of large language models (LLMs). Recent efforts increasingly turn to code as a rich training sour…
cs.LG2025
Toward Reproducible Cross-Backend Compatibility for Deep Learning: A Configuration-First Framework with Three-Tier Verification
Zehua Li
This paper presents a configuration-first framework for evaluating cross-backend compatibility in deep learning systems deployed on CPU, GPU, and compiled runtimes. The framework d…