Zexiong Ma

13 papers A* 1A 1Journal 9Unranked 2
YearRankTypeTitle / Venue / Authors
2025 J jnl
Evaluating Generated Commit Messages with Large Language Models.
CoRR
Qunhong Zeng, Yuxia Zhang, Zexiong Ma, Bo Jiang, Ningyuan Sun, Klaas-Jan Stol, Xingyu Mou, Hui Liu
2025 — conf
SoRFT: Issue Resolving with Subtask-oriented Reinforced Fine-Tuning.
ACL (1)
Zexiong Ma, Chao Peng, Pengfei Gao, Xiangxin Meng, Yanzhen Zou, Bing Xie
2025 J jnl
SoRFT: Issue Resolving with Subtask-oriented Reinforced Fine-Tuning.
CoRR
Zexiong Ma, Chao Peng, Pengfei Gao, Xiangxin Meng, Yanzhen Zou, Bing Xie
2025 J jnl
Tool-integrated Reinforcement Learning for Repo Deep Search.
CoRR
Zexiong Ma, Chao Peng, Qunhong Zeng, Pengfei Gao, Yanzhen Zou, Bing Xie
2024 J jnl
An Empirical Study on LLM-based Agents for Automated Bug Fixing.
CoRR
Xiangxin Meng, Zexiong Ma, Pengfei Gao, Chao Peng
2024 — conf
Can LLMs Learn From Mistakes? An Empirical Study on Reasoning Tasks.
EMNLP (Findings)
Shengnan An, Zexiong Ma, Siqi Cai, Zeqi Lin, Nanning Zheng, Jian-Guang Lou, Weizhu Chen
2024 A conf
Compositional API Recommendation for Library-Oriented Code Generation.
ICPC
Zexiong Ma, Shengnan An, Bing Xie, Zeqi Lin
2024 J jnl
Compositional API Recommendation for Library-Oriented Code Generation.
CoRR
Zexiong Ma, Shengnan An, Bing Xie, Zeqi Lin
2024 J jnl
Dehallucinating Parallel Context Extension for Retrieval-Augmented Generation.
CoRR
Zexiong Ma, Shengnan An, Zeqi Lin, Yanzhen Zou, Jian-Guang Lou, Bing Xie
2024 A* conf
Make Your LLM Fully Utilize the Context.
NeurIPS
Shengnan An, Zexiong Ma, Zeqi Lin, Nanning Zheng, Jian-Guang Lou, Weizhu Chen
2024 J jnl
Make Your LLM Fully Utilize the Context.
CoRR
Shengnan An, Zexiong Ma, Zeqi Lin, Nanning Zheng, Jian-Guang Lou
2024 J jnl
Repository Structure-Aware Training Makes SLMs Better Issue Resolver.
CoRR
Zexiong Ma, Shengnan An, Zeqi Lin, Yanzhen Zou, Bing Xie
2023 J jnl
Learning From Mistakes Makes LLM Better Reasoner.
CoRR
Shengnan An, Zexiong Ma, Zeqi Lin, Nanning Zheng, Jian-Guang Lou, Weizhu Chen