Empowering RepoQA-Agent based on Reinforcement Learning Driven by Monte-carlo Tree Search

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Li, Guochang, Liu, Yuchen, Qin, Zhen, Wang, Yunkun, Zhong, Jianping, Zhi, Chen, Li, Binhua, Huang, Fei, Li, Yongbin, Deng, Shuiguang
Format:	Preprint
Published:	2025
Subjects:	Software Engineering
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

InspectCoder: Dynamic Analysis-Enabled Self Repair through interactive LLM-Debugger Collaboration
by: Wang, Yunkun, et al.
Published: (2025)

ExploraCoder: Advancing code generation for multiple unseen APIs via planning and chained exploration
by: Wang, Yunkun, et al.
Published: (2024)

RepoQA: Evaluating Long Context Code Understanding
by: Liu, Jiawei, et al.
Published: (2024)

Exploring Parameter-Efficient Fine-Tuning of Large Language Model on Automated Program Repair
by: Li, Guochang, et al.
Published: (2024)

Can Vision-Language Models Handle Long-Context Code? An Empirical Study on Visual Compression
by: Zhong, Jianping, et al.
Published: (2026)

Do Code LLMs Understand Design Patterns?
by: Pan, Zhenyu, et al.
Published: (2025)

CodeGlance: Understanding Code Reasoning Challenges in LLMs through Multi-Dimensional Feature Analysis
by: Wang, Yunkun, et al.
Published: (2026)

Alibaba LingmaAgent: Improving Automated Issue Resolution via Comprehensive Repository Exploration
by: Ma, Yingwei, et al.
Published: (2024)

CodeAgent: Enhancing Code Generation with Tool-Integrated Agent Systems for Real-World Repo-level Coding Challenges
by: Zhang, Kechi, et al.
Published: (2024)

GrepRAG: An Empirical Study and Optimization of Grep-Like Retrieval for Code Completion
by: Wang, Baoyi, et al.
Published: (2026)

Thinking Longer, Not Larger: Enhancing Software Engineering Agents via Scaling Test-Time Compute
by: Ma, Yingwei, et al.
Published: (2025)

Tool-integrated Reinforcement Learning for Repo Deep Search
by: Ma, Zexiong, et al.
Published: (2025)

EvoCodeBench: An Evolving Code Generation Benchmark with Domain-Specific Evaluations
by: Li, Jia, et al.
Published: (2024)

GraphCodeAgent: Dual Graph-Guided LLM Agent for Retrieval-Augmented Repo-Level Code Generation
by: Li, Jia, et al.
Published: (2025)

LLMs as Continuous Learners: Improving the Reproduction of Defective Code in Software Issues
by: Lin, Yalan, et al.
Published: (2024)

CodeRL+: Improving Code Generation via Reinforcement with Execution Semantics Alignment
by: Jiang, Xue, et al.
Published: (2025)

Lingma SWE-GPT: An Open Development-Process-Centric Language Model for Automated Software Improvement
by: Ma, Yingwei, et al.
Published: (2024)

From I/O to Code with Discovery Agent
by: Dong, Yihong, et al.
Published: (2026)

Codev-Bench: How Do LLMs Understand Developer-Centric Code Completion?
by: Pan, Zhenyu, et al.
Published: (2024)

CompileAgent: Automated Real-World Repo-Level Compilation with Tool-Integrated LLM-based Agent System
by: Hu, Li, et al.
Published: (2025)

CodeRepoQA: A Large-scale Benchmark for Software Engineering Question Answering
by: Hu, Ruida, et al.
Published: (2024)

To Diff or Not to Diff? Structure-Aware and Adaptive Output Formats for Efficient LLM-based Code Editing
by: Cheng, Wei, et al.
Published: (2026)

RepoMirage: Probing Repository Context Reasoning in Code Agents with Perturbations
by: Li, Hanyu, et al.
Published: (2026)

RealBench: A Repo-Level Code Generation Benchmark Aligned with Real-World Software Development Practices
by: Li, Jia, et al.
Published: (2026)

Neurosymbolic Repo-level Code Localization
by: Xu, Xiufeng, et al.
Published: (2026)

Large Language Model Unlearning for Source Code
by: Jiang, Xue, et al.
Published: (2025)

RepoRepair: Leveraging Code Documentation for Repository-Level Automated Program Repair
by: Pan, Zhongqiang, et al.
Published: (2026)

CoReQA: Uncovering Potentials of Language Models in Code Repository Question Answering
by: Chen, Jialiang, et al.
Published: (2025)

Think Anywhere in Code Generation
by: Jiang, Xue, et al.
Published: (2026)

RepoTransAgent: Multi-Agent LLM Framework for Repository-Aware Code Translation
by: Guan, Ziqi, et al.
Published: (2025)

RepoSummary: Feature-Oriented Summarization and Documentation Generation for Code Repositories
by: Zhu, Yifeng, et al.
Published: (2025)

CodeScope: An Execution-based Multilingual Multitask Multidimensional Benchmark for Evaluating LLMs on Code Understanding and Generation
by: Yan, Weixiang, et al.
Published: (2023)

BeyondSWE: Can Current Code Agent Survive Beyond Single-Repo Bug Fixing?
by: Chen, Guoxin, et al.
Published: (2026)

Revisiting Vulnerability Patch Localization: An Empirical Study and LLM-Based Solution
by: Xu, Haoran, et al.
Published: (2025)

ChatUniTest: A Framework for LLM-Based Test Generation
by: Chen, Yinghao, et al.
Published: (2023)

Saber: An Efficient Sampling with Adaptive Acceleration and Backtracking Enhanced Remasking for Diffusion Language Model
by: Dong, Yihong, et al.
Published: (2025)

RepoScope: Leveraging Call Chain-Aware Multi-View Context for Repository-Level Code Generation
by: Liu, Yang, et al.
Published: (2025)

RepoHyper: Search-Expand-Refine on Semantic Graphs for Repository-Level Code Completion
by: Phan, Huy N., et al.
Published: (2024)

RepoDoc: A Knowledge Graph-Based Framework to Automatic Documentation Generation and Incremental Updates
by: Xu, Dong, et al.
Published: (2026)

RepoZero: Can LLMs Generate a Code Repository from Scratch?
by: Zhang, Zhaoxi, et al.
Published: (2026)