Image de couverture de livre

MCTS-Refined CoT: High-Quality Fine-Tuning Data for LLM-Based Repository Issue Resolution

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Wang, Yibo, Peng, Zhihao, Wang, Ying, Wei, Zhao, Yu, Hai, Zhu, Zhiliang
Format:	Preprint
Publié:	2025
Sujets:	Software Engineering
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Are They All Good? Evaluating the Quality of CoTs in LLM-based Code Generation
par: Zhang, Binquan, et autres
Publié: (2025)

Evaluating and Improving Automated Repository-Level Rust Issue Resolution with LLM-based Agents
par: Xiang, Jiahong, et autres
Publié: (2026)

Beyond Fixed Tests: Repository-Level Issue Resolution as Coevolution of Code and Behavioral Constraints
par: Li, Kefan, et autres
Publié: (2026)

Lingxi: Repository-Level Issue Resolution Framework Enhanced by Procedural Knowledge Guided Scaling
par: Yang, Xu, et autres
Publié: (2025)

RethinkMCTS: Refining Erroneous Thoughts in Monte Carlo Tree Search for Code Generation
par: Li, Qingyao, et autres
Publié: (2024)

Structural Anchors and Reasoning Fragility:Understanding CoT Robustness in LLM4Code
par: Liu, Yang, et autres
Publié: (2026)

CoReQA: Uncovering Potentials of Language Models in Code Repository Question Answering
par: Chen, Jialiang, et autres
Publié: (2025)

ThinkFL: Self-Refining Failure Localization for Microservice Systems via Reinforcement Fine-Tuning
par: Zhang, Lingzhe, et autres
Publié: (2025)

AdaptiveLLM: A Framework for Selecting Optimal Cost-Efficient LLM for Code-Generation Based on CoT Length
par: Cheng, Junhang, et autres
Publié: (2025)

Repository-Aware File Path Retrieval via Fine-Tuned LLMs
par: Yanuganti, Vasudha, et autres
Publié: (2025)

Skeleton-Guided-Translation: A Benchmarking Framework for Code Repository Translation with Fine-Grained Quality Evaluation
par: Zhang, Xing, et autres
Publié: (2025)

REAgent: Requirement-Driven LLM Agents for Software Issue Resolution
par: Kuang, Shiqi, et autres
Publié: (2026)

Combating Missed Recalls in E-commerce Search: A CoT-Prompting Testing Approach
par: Wu, Shengnan, et autres
Publié: (2024)

Atomizer: An LLM-based Collaborative Multi-Agent Framework for Intent-Driven Commit Untangling
par: Zhu, Kangchen, et autres
Publié: (2026)

Combining Fine-Tuning and LLM-based Agents for Intuitive Smart Contract Auditing with Justifications
par: Ma, Wei, et autres
Publié: (2024)

EXPEREPAIR: Dual-Memory Enhanced LLM-based Repository-Level Program Repair
par: Mu, Fangwen, et autres
Publié: (2025)

ReposVul: A Repository-Level High-Quality Vulnerability Dataset
par: Wang, Xinchen, et autres
Publié: (2024)

SWE-Mirror: Scaling Issue-Resolving Datasets by Mirroring Issues Across Repositories
par: Wang, Junhao, et autres
Publié: (2025)

Studying and Automating Issue Resolution for Software Quality
par: Saha, Antu
Publié: (2025)

STALL+: Boosting LLM-based Repository-level Code Completion with Static Analysis
par: Liu, Junwei, et autres
Publié: (2024)

RepoTransAgent: Multi-Agent LLM Framework for Repository-Aware Code Translation
par: Guan, Ziqi, et autres
Publié: (2025)

RepoSummary: Feature-Oriented Summarization and Documentation Generation for Code Repositories
par: Zhu, Yifeng, et autres
Publié: (2025)

Are Human Rules Necessary? Generating Reusable APIs with CoT Reasoning and In-Context Learning
par: Mai, Yubo, et autres
Publié: (2024)

Does Pass Rate Tell the Whole Story? Evaluating Design Constraint Compliance in LLM-based Issue Resolution
par: Yu, Kai, et autres
Publié: (2026)

RTLRepoCoder: Repository-Level RTL Code Completion through the Combination of Fine-Tuning and Retrieval Augmentation
par: Wu, Peiyang, et autres
Publié: (2025)

Alibaba LingmaAgent: Improving Automated Issue Resolution via Comprehensive Repository Exploration
par: Ma, Yingwei, et autres
Publié: (2024)

Tracing Errors, Constructing Fixes: Repository-Level Memory Error Repair via Typestate-Guided Context Retrieval
par: Cheng, Xiao, et autres
Publié: (2025)

Compressing Code Context for LLM-based Issue Resolution
par: Jia, Haoxiang, et autres
Publié: (2026)

When Fine-Tuning LLMs Meets Data Privacy: An Empirical Study of Federated Learning in LLM-Based Program Repair
par: Luo, Wenqiang, et autres
Publié: (2024)

Classifying Issues in Open-source GitHub Repositories
par: Raaj, Amir Hossain, et autres
Publié: (2025)

A Methodological Framework for LLM-Based Mining of Software Repositories
par: De Martino, Vincenzo, et autres
Publié: (2025)

RepoGenesis: Benchmarking End-to-End Microservice Generation from Readme to Repository
par: Peng, Zhiyuan, et autres
Publié: (2026)

VulnResolver: A Hybrid Agent Framework for LLM-Based Automated Vulnerability Issue Resolution
par: Zhang, Mingming, et autres
Publié: (2026)

MAGIS: LLM-Based Multi-Agent Framework for GitHub Issue Resolution
par: Tao, Wei, et autres
Publié: (2024)

Adversarial Robustness of Open-source Text Classification Models and Fine-Tuning Chains
par: Qin, Hao, et autres
Publié: (2024)

RustRepoTrans: Repository-level Code Translation Benchmark Targeting Rust
par: Ou, Guangsheng, et autres
Publié: (2024)

CodeCoT: Tackling Code Syntax Errors in CoT Reasoning for Code Generation
par: Huang, Dong, et autres
Publié: (2023)

FGIT: Fault-Guided Fine-Tuning for Code Generation
par: Fan, Lishui, et autres
Publié: (2025)

GraphCoder: Enhancing Repository-Level Code Completion via Code Context Graph-based Retrieval and Language Model
par: Liu, Wei, et autres
Publié: (2024)

A Preference-Driven Methodology for High-Quality Solidity Code Generation
par: Peng, Zhiyuan, et autres
Publié: (2025)