arXiv subjects

Zexiong Ma

Publications and source records attributed to Zexiong Ma.

9 recordsLinked to original sources

arXiv2025

An Empirical Study on LLM-based Agents for Automated Bug Fixing

Large language models (LLMs) and LLM-based Agents have been applied to fix bugs automatically, demonstrating the capability in addressing software defects by engaging in development environment interaction, iterative validation and code modification. However, systematic analysis of these agent systems remain limited, particularly regarding performance variations among top-performing ones. In this paper, we examine six repair systems on the SWE-bench Verified benchmark for automated bug fixing. We first assess each system's overall performance, noting the instances solvable by all or none of these systems, and explore the capabilities of different systems. We also compare fault localization accuracy at file and code symbol levels and evaluate bug reproduction capabilities. Through analysis, we concluded that further optimization is needed in both the LLM capability itself and the design of Agentic flow to improve the effectiveness of the Agent in bug fixing.

cs.SE↗

arXiv2025

Tool-integrated Reinforcement Learning for Repo Deep Search

Issue localization, the process of identifying code locations that need modification to resolve software issues, is a critical yet challenging task in software development. The semantic gap between natural language issue descriptions and faulty code requires complex multi-hop reasoning through code dependencies. Existing LLM-based agents attempt to address this by integrating repository retrieval tools. However, this transforms issue localization into a demanding task we call Repo Deep Search, which requires the LLM to effectively utilize various repository retrieval tools throughout a multi-step reasoning and navigation process. To tackle this challenge, we present ToolTrain, a two-stage tool-integrated training framework combining rejection-sampled supervised fine-tuning and tool-integrated reinforcement learning to enhance LLMs' ability to use retrieval tools for issue localization. Experimental results show that ToolTrain-trained models achieve state-of-the-art performance, with our 32B model even surpassing Claude-3.7 on function-level localization. The results also show that improved localization performance translates to better end-to-end issue resolution performance. This further demonstrates that training for issue localization is a viable and effective strategy for improving automated software development.

cs.SE↗

arXiv2025

Evaluating Generated Commit Messages with Large Language Models

Commit messages are essential in software development as they serve to document and explain code changes. Yet, their quality often falls short in practice, with studies showing significant proportions of empty or inadequate messages. While automated commit message generation has advanced significantly, particularly with Large Language Models (LLMs), the evaluation of generated messages remains challenging. Traditional reference-based automatic metrics like BLEU, ROUGE-L, and METEOR have notable limitations in assessing commit message quality, as they assume a one-to-one mapping between code changes and commit messages, leading researchers to rely on resource-intensive human evaluation. This study investigates the potential of LLMs as automated evaluators for commit message quality. Through systematic experimentation with various prompt strategies and state-of-the-art LLMs, we demonstrate that LLMs combining Chain-of-Thought reasoning with few-shot demonstrations achieve near human-level evaluation proficiency. Our LLM-based evaluator significantly outperforms traditional metrics while maintaining acceptable reproducibility, robustness, and fairness levels despite some inherent variability. This work conducts a comprehensive preliminary study on using LLMs for commit message evaluation, offering a scalable alternative to human assessment while maintaining high-quality evaluation.

cs.SE↗

arXiv2025

SoRFT: Issue Resolving with Subtask-oriented Reinforced Fine-Tuning

Mainstream issue-resolving frameworks predominantly rely on commercial models, leading to high costs and privacy concerns. Existing training approaches for issue resolving struggle with poor generalization and fail to fully leverage open-source development resources. We propose Subtask-oriented Reinforced Fine-Tuning (SoRFT), a novel training approach to enhance the issue resolving capability of LLMs. We decomposes issue resolving into structured subtasks: file localization, function localization, line localization, and code edit generation. SoRFT consists of two training stages: (1) rejection-sampled supervised fine-tuning, Chain of Thought (CoT) data is filtered using ground-truth before fine-tuning the LLM, and (2) rule-based reinforcement learning, which leverages PPO with ground-truth based rewards. We evaluate the SoRFT-trained model on SWE-Bench Verified and SWE-Bench Lite, achieving state-of-the-art (SOTA) performance among open-source models (e.g., resolve 21.4% issues on SWE-Bench Verified with SoRFT-Qwen-7B). The experimental results demonstrate that SoRFT significantly enhances issue-resolving performance, improves model generalization, and provides a cost-efficient alternative to commercial models.

cs.SE↗

arXiv2024

Repository Structure-Aware Training Makes SLMs Better Issue Resolver

Language models have been applied to various software development tasks, but the performance varies according to the scale of the models. Large Language Models (LLMs) outperform Small Language Models (SLMs) in complex tasks like repository-level issue resolving, but raise concerns about privacy and cost. In contrast, SLMs are more accessible but under-perform in complex tasks. In this paper, we introduce ReSAT (Repository Structure-Aware Training), construct training data based on a large number of issues and corresponding pull requests from open-source communities to enhance the model's understanding of repository structure and issue resolving ability. We construct two types of training data: (1) localization training data, a multi-level progressive localization data to improve code understanding and localization capability; (2) code edit training data, which improves context-based code editing capability. The evaluation results on SWE-Bench-verified and RepoQA demonstrate that ReSAT effectively enhances SLMs' issue-resolving and repository-level long-context understanding capabilities.

cs.SE↗

arXiv2024

Dehallucinating Parallel Context Extension for Retrieval-Augmented Generation

Large language models (LLMs) are susceptible to generating hallucinated information, despite the integration of retrieval-augmented generation (RAG). Parallel context extension (PCE) is a line of research attempting to effectively integrating parallel (unordered) contexts, while it still suffers from hallucinations when adapted to RAG scenarios. In this paper, we propose DePaC (Dehallucinating Parallel Context Extension), which alleviates the hallucination problem with context-aware negative training and information-calibrated aggregation. DePaC is designed to alleviate two types of in-context hallucination: fact fabrication (i.e., LLMs present claims that are not supported by the contexts) and fact omission (i.e., LLMs fail to present claims that can be supported by the contexts). Specifically, (1) for fact fabrication, we apply the context-aware negative training that fine-tunes the LLMs with negative supervisions, thus explicitly guiding the LLMs to refuse to answer when contexts are not related to questions; (2) for fact omission, we propose the information-calibrated aggregation which prioritizes context windows with higher information increment from their contexts. The experimental results on nine RAG tasks demonstrate that DePaC significantly alleviates the two types of hallucination and consistently achieves better performances on these tasks.

cs.CL↗

arXiv2024

Make Your LLM Fully Utilize the Context

While many contemporary large language models (LLMs) can process lengthy input, they still struggle to fully utilize information within the long context, known as the lost-in-the-middle challenge. We hypothesize that it stems from insufficient explicit supervision during the long-context training, which fails to emphasize that any position in a long context can hold crucial information. Based on this intuition, our study presents information-intensive (IN2) training, a purely data-driven solution to overcome lost-in-the-middle. Specifically, IN2 training leverages a synthesized long-context question-answer dataset, where the answer requires (1) fine-grained information awareness on a short segment (~128 tokens) within a synthesized long context (4K-32K tokens), and (2) the integration and reasoning of information from two or more short segments. Through applying this information-intensive training on Mistral-7B, we present FILM-7B (FILl-in-the-Middle). To thoroughly assess the ability of FILM-7B for utilizing long contexts, we design three probing tasks that encompass various context styles (document, code, and structured-data context) and information retrieval patterns (forward, backward, and bi-directional retrieval). The probing results demonstrate that FILM-7B can robustly retrieve information from different positions in its 32K context window. Beyond these probing tasks, FILM-7B significantly improves the performance on real-world long-context tasks (e.g., 23.5->26.9 F1 score on NarrativeQA), while maintaining a comparable performance on short-context tasks (e.g., 59.3->59.2 accuracy on MMLU). Github Link: https://github.com/microsoft/FILM.

cs.CL↗

arXiv2024

Learning From Mistakes Makes LLM Better Reasoner

Large language models (LLMs) recently exhibited remarkable reasoning capabilities on solving math problems. To further improve their reasoning capabilities, this work explores whether LLMs can LEarn from MistAkes (LEMA), akin to the human learning process. Consider a human student who failed to solve a math problem, he will learn from what mistake he has made and how to correct it. Mimicking this error-driven learning process, LEMA incorporates mistake-correction data pairs during fine-tuning LLMs. Specifically, we first collect inaccurate reasoning paths from various LLMs, and then employ GPT-4 as a ''corrector'' to identify the mistake step, explain the reason for the mistake, correct the mistake and generate the final answer. In addition, we apply a correction-centric evolution strategy that effectively expands the question set for generating correction data. Experiments across various LLMs and reasoning tasks show that LEMA effectively improves CoT-alone fine-tuning. Our further ablations shed light on the non-homogeneous effectiveness between CoT data and correction data. These results suggest a significant potential for LLMs to improve through learning from their mistakes. Our code, models and prompts are publicly available at https://github.com/microsoft/LEMA.

cs.CL↗

arXiv2024

Compositional API Recommendation for Library-Oriented Code Generation

Large language models (LLMs) have achieved exceptional performance in code generation. However, the performance remains unsatisfactory in generating library-oriented code, especially for the libraries not present in the training data of LLMs. Previous work utilizes API recommendation technology to help LLMs use libraries: it retrieves APIs related to the user requirements, then leverages them as context to prompt LLMs. However, developmental requirements can be coarse-grained, requiring a combination of multiple fine-grained APIs. This granularity inconsistency makes API recommendation a challenging task. To address this, we propose CAPIR (Compositional API Recommendation), which adopts a "divide-and-conquer" strategy to recommend APIs for coarse-grained requirements. Specifically, CAPIR employs an LLM-based Decomposer to break down a coarse-grained task description into several detailed subtasks. Then, CAPIR applies an embedding-based Retriever to identify relevant APIs corresponding to each subtask. Moreover, CAPIR leverages an LLM-based Reranker to filter out redundant APIs and provides the final recommendation. To facilitate the evaluation of API recommendation methods on coarse-grained requirements, we present two challenging benchmarks, RAPID (Recommend APIs based on Documentation) and LOCG (Library-Oriented Code Generation). Experimental results on these benchmarks, demonstrate the effectiveness of CAPIR in comparison to existing baselines. Specifically, on RAPID's Torchdata-AR dataset, compared to the state-of-the-art API recommendation approach, CAPIR improves recall@5 from 18.7% to 43.2% and precision@5 from 15.5% to 37.1%. On LOCG's Torchdata-Code dataset, compared to code generation without API recommendation, CAPIR improves pass@100 from 16.0% to 28.0%.

cs.SE↗