Yuanhao Li — accepted AI-conference papers

2026

BOOSTAPR: Boosting Automated Program Repair via Execution-Grounded Reinforcement Learning with Dual Reward Models

Yuanhao Li, Hongbo Wang, Xiaotang Shang, Xunzhu Tang, Yiming Cao, Xuhong Chen

ICML 2026poster

Reinforcement learning for program repair is hindered by sparse execution feedback and coarse sequence-level rewards that obscure which edits actually fix bugs. We present BoostAPR, a three-stage framework: (1) supervised fine-tuning on execution-verified demonstrations with reasoning traces, (2) tr…

Cited by 0 Source ↗Scholar ↗

2026

DRAFT-RL: Multi-Agent Chain-of-Draft Reasoning for Reinforcement Learning-Enhanced LLMs

Yuanhao Li, Mingshan Liu, Hongbo Wang, Yiding Zhang, Yifei Ma, Wei Tan

AAAI 2026technical

Large Language Models (LLMs) have shown impressive capabilities in multi-step reasoning and problem-solving. Recent works introduce multi-agent reflection frameworks where multiple LLM agents critique and refine each other’s outputs using reinforcement learning (RL). However, these approaches often

Cited by 0 Source ↗PDF ↗Scholar ↗