2025
SoRFT: Issue Resolving with Subtask-oriented Reinforced Fine-Tuning.
CoRR, February, 2025

2024
Repository Structure-Aware Training Makes SLMs Better Issue Resolver.
CoRR, 2024

Dehallucinating Parallel Context Extension for Retrieval-Augmented Generation.
CoRR, 2024

An Empirical Study on LLM-based Agents for Automated Bug Fixing.
CoRR, 2024

Make Your LLM Fully Utilize the Context.
CoRR, 2024

Make Your LLM Fully Utilize the Context.
Proceedings of the Advances in Neural Information Processing Systems 38: Annual Conference on Neural Information Processing Systems 2024, 2024

Compositional API Recommendation for Library-Oriented Code Generation.
Proceedings of the 32nd IEEE/ACM International Conference on Program Comprehension, 2024

Can LLMs Learn From Mistakes? An Empirical Study on Reasoning Tasks.
Proceedings of the Findings of the Association for Computational Linguistics: EMNLP 2024, 2024

2023
Learning From Mistakes Makes LLM Better Reasoner.
CoRR, 2023