← authors · overview

• SelfAPR: Self-supervised Program Repair with Test Execution Diagnostics
  2022 · 75 citations
• MUFIN: Improving Neural Repair Models with Back-Translation
  2023 · 2 citations
• Automated Repair of Ambiguous Problem Descriptions for LLM-Based Code Generation
  2025 · 1 citations
• CodeTracer: Towards Traceable Agent States
  2026
• An Iterative Test-and-Repair Framework for Competitive Code Generation
  2026
• ExecVerify: White-Box RL with Verifiable Stepwise Rewards for Code Execution Reasoning
  2026
• HerAgent: Rethinking the Automated Environment Deployment via Hierarchical Test Pyramid
  2026
• JMigBench: A Benchmark for Evaluating LLMs on Source Code Migration (Java 8 to Java 11)
  2026
• Environment-in-the-Loop: Rethinking Code Migration with LLM-based Agents
  2026
• ContextBench: A Benchmark for Context Retrieval in Coding Agents
  2026
• Understanding Code Agent Behaviour: An Empirical Study of Success and Failure Trajectories
  2025
• CodeReasoner: Enhancing the Code Reasoning Ability with Reinforcement Learning
  2025
• Prometheus: Towards Long-Horizon Codebase Navigation for Repository-Level Problem Solving
  2025
• Adversarial Reasoning for Repair Based on Inferred Program Intent
  2025
• A Comprehensive Study of Automatic Program Repair on the QuixBugs Benchmark
  2018