Cover Image

Boosting Open-Source LLMs for Program Repair via Reasoning Transfer and LLM-Guided Reinforcement Learning

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Tang, Xunzhu, Klein, Jacques, Bissyandé, Tegawendé F.
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

Reinforcement Learning-Guided Chain-of-Draft for Token-Efficient Code Generation
by: Tang, Xunzhu, et al.
Published: (2025)

Measuring LLM Code Generation Stability via Structural Entropy
by: Song, Yewei, et al.
Published: (2025)

Patch-CLIP: A Patch-Text Pre-Trained Model
by: Tang, Xunzhu, et al.
Published: (2023)

MalLoc: Toward Fine-grained Android Malicious Payload Localization via LLMs
by: Sun, Tiezhu, et al.
Published: (2025)

CREF: An LLM-based Conversational Software Repair Framework for Programming Tutors
by: Yang, Boyang, et al.
Published: (2024)

Test smells in LLM-Generated Unit Tests
by: Ouédraogo, Wendkûuni C., et al.
Published: (2024)

AndroLibZoo: A Reliable Dataset of Libraries Based on Software Dependency Analysis
by: Samhi, Jordan, et al.
Published: (2023)

MORepair: Teaching LLMs to Repair Code via Multi-Objective Fine-tuning
by: Yang, Boyang, et al.
Published: (2024)

Programming Language Confusion: When Code LLMs Can't Keep their Languages Straight
by: Moumoula, Micheline Bénédicte, et al.
Published: (2025)

MT4DP: Data Poisoning Attack Detection for DL-based Code Search Models via Metamorphic Testing
by: Chen, Gong, et al.
Published: (2025)

Unlocking LLM Repair Capabilities Through Cross-Language Translation and Multi-Agent Refinement
by: Luo, Wenqiang, et al.
Published: (2025)

CallNavi, A Challenge and Empirical Study on LLM Function Calling and Routing
by: Song, Yewei, et al.
Published: (2025)

BoostAPR: Boosting Automated Program Repair via Execution-Grounded Reinforcement Learning with Dual Reward Models
by: Li, Yuanhao, et al.
Published: (2026)

Learned or Memorized ? Quantifying Memorization Advantage in Code LLMs
by: Euraste, Djiré Albérick, et al.
Published: (2026)

CodeAgent: Autonomous Communicative Agents for Code Review
by: Tang, Xunzhu, et al.
Published: (2024)

Enhancing Text-to-SQL Translation for Financial System Design
by: Song, Yewei, et al.
Published: (2023)

When Fine-Tuning LLMs Meets Data Privacy: An Empirical Study of Federated Learning in LLM-Based Program Repair
by: Luo, Wenqiang, et al.
Published: (2024)

In-Context Code-Text Learning for Bimodal Software Engineering
by: Tang, Xunzhu, et al.
Published: (2024)

Evaluating Large Language Models in detecting Secrets in Android Apps
by: Alecci, Marco, et al.
Published: (2025)

The Code Barrier: What LLMs Actually Understand?
by: Nikiema, Serge Lionel, et al.
Published: (2025)

The Struggles of LLMs in Cross-lingual Code Clone Detection
by: Moumoula, Micheline Bénédicte, et al.
Published: (2024)

How Secure is Secure Code Generation? Adversarial Prompts Put LLM Defenses to the Test
by: Tessa, Melissa, et al.
Published: (2026)

A Survey of LLM-based Automated Program Repair: Taxonomies, Design Paradigms, and Applications
by: Yang, Boyang, et al.
Published: (2025)

Software Security in Software-Defined Networking: A Systematic Literature Review
by: Diouf, Moustapha Awwalou, et al.
Published: (2025)

Call Graph Soundness in Android Static Analysis
by: Samhi, Jordan, et al.
Published: (2024)

Revisiting Code Similarity Evaluation with Abstract Syntax Tree Edit Distance
by: Song, Yewei, et al.
Published: (2024)

Open-Source AI-based SE Tools: Opportunities and Challenges of Collaborative Software Learning
by: Lin, Zhihao, et al.
Published: (2024)

Large-scale, Independent and Comprehensive study of the power of LLMs for test case generation
by: Ouédraogo, Wendkûuni C., et al.
Published: (2024)

Beyond Surface Similarity: Evaluating LLM-Based Test Refactorings with Structural and Semantic Awareness
by: Ouédraogo, Wendkûuni C., et al.
Published: (2025)

LLM for Mobile: An Initial Roadmap
by: Chen, Daihang, et al.
Published: (2024)

DetectBERT: Towards Full App-Level Representation Learning to Detect Android Malware
by: Sun, Tiezhu, et al.
Published: (2024)

Enriching Automatic Test Case Generation by Extracting Relevant Test Inputs from Bug Reports
by: Ouédraogo, Wendkûuni C., et al.
Published: (2023)

Correctness isnt Efficiency: Runtime Memory Divergence in LLM-Generated Code
by: Rajput, Prateek, et al.
Published: (2026)

Beyond Language Barriers: Multi-Agent Coordination for Multi-Language Code Generation
by: Moumoula, Micheline Bénédicte, et al.
Published: (2025)

From Rookie to Expert: Manipulating LLMs for Automated Vulnerability Exploitation in Enterprise Software
by: Diouf, Moustapha Awwalou, et al.
Published: (2025)

ContractTrace: Retracing Smart Contract Versions for Security Analyses
by: Mbodji, Fatou Ndiaye, et al.
Published: (2024)

SIEVE: Towards Verifiable Certification for Code-datasets
by: Mbodji, Fatou Ndiaye, et al.
Published: (2025)

Rethinking Cognitive Complexity for Unit Tests: Toward a Readability-Aware Metric Grounded in Developer Perception
by: Ouédraogo, Wendkûuni C., et al.
Published: (2025)

Characterizing Build Compromises Through Vulnerability Disclosure Analysis
by: Diao, Maimouna Tamah, et al.
Published: (2025)

Human-Aligned Code Readability Assessment with Large Language Models
by: Ouédraogo, Wendkûuni C., et al.
Published: (2025)