Aug 2026· International journal of computer information systems and industrial management applications· 0 citations
TL;DR
Comparisons of AgentCodeReview against single-agent and non-agentic baselines indicate that role specialization and explicit verification improve review accuracy, repair effectiveness and the transparency of the generated rationales, offering a reproducible pathway toward trustworthy autonomous software maintenance.
Abstract
Modern software development depends heavily on code review and timely bug fixing, yet manual review is slow, inconsistent and hard to scale, while single-model automated approaches based on Large Language Models (LLMs) frequently produce opaque suggestions and rarely close the loop between detecting a defect and repairing it. This paper proposes AgentCodeReview, a multi-agent framework that decomposes explainable code review and automated bug repair into cooperating specialized agents — Retrieval, Review, Explanation, Repair and Verification — coordinated by an Orchestrator over a shared retrieval-augmented context store, with a verification-driven feedback loop that iteratively refines candidate patches until they pass their tests. We describe the architecture, the inter-agent communication protocol and an evaluation design over widely used code-review and program-repair benchmarks, comparing the framework against single-agent and non-agentic baselines using precision, recall, F1, repair success rate and a human-aligned explanation-quality score. The results indicate that role specialization and explicit verification improve review accuracy, repair effectiveness and the transparency of the generated rationales, offering a reproducible pathway toward trustworthy autonomous software maintenance.
The AgentCodeReview system is presented, a multi-agent system that is able to conduct explainable code review and automated bug repair by leveraging software engineering agents with different code review tasks and its utility and extensibility to the field of explainable AI in software quality assurance are demonstrated.
B. N, T. L. Manasa· International journal of com...· 0 citations
This work proposes BiVCoder, a diagnosis-driven multi-agent framework featuring a novel bidirectional code-test diagnosis mechanism, and introduces BiVCoder-SFT, a role-specific instruction fine-tuning scheme.
Xiaoyang Li, Jin-Hao Dong, Wenhang Shi et al.· Proceedings of the 32nd ACM...· 0 citations
This work introduces REFINE (Refactoring with Evidence-aware Flow for Integrated ageNtic Execution), a tool-agnostic, evidence-aware multi-agent approach for generating Java file-level refactoring candidates that achieves a higher median code-smell reduction with smaller edits and fewer public-method removals.
Muhammad Waseem, Aakash Ahmad, Pekka Abrahamsson· 0 citations
Automated Program Repair (APR) has benefited greatly from Large Language Models (LLMs), but existing LLM-based APR methods still struggle with multi-hunk bugs that require coordinated changes across multiple locations. These bugs demand repository-level context understanding, repair-order scheduling, and effective hunk-level patch generation and selection. To address these challenges, we propose MultiFixer, a novel Coordinator-Proposer based multi-agent framework for multi-hunk repair. MultiFixer performs tool-augmented bug analysis, constructs fine-grained repair context, iteratively generates patches through a Coordinator-Proposer architecture, and applies two-stage patch refinement for syntactic and semantic correctness. We evaluate MultiFixer on 835 bugs from Defects4J and three vulnerability benchmarks. On Defects4J, MultiFixer fixes 326 bugs, including 62 multi-method and 27 multi-file bugs, and outperforms prior APR baselines in the reported comparisons with the same base model. Moreover, MultiFixer also fixes 46 multi-hunk bugs among 95 unique fixes. When combined with Claude-3.5-Sonnet, MultiFixer repairs 420 bugs, establishing a new state of the art on Defects4J. On VUL4J, MultiFixer repairs 24 real-world vulnerabilities, including 5 multi-hunk cases. On the multi-hunk subsets of SEC-bench and PatchEval, MultiFixer fixes 11 and 19 vulnerabilities, respectively, outperforming all compared baselines under GPT-3.5. These results demonstrate the effectiveness of MultiFixer for multi-hunk repair.
Haichuan Hu, Chunrong Fang, Ye Shang et al.· arXiv.org· 0 citations
An automated approach that explicitly targets Java best-practice violations across real-world projects is proposed, intended to make automated refactoring more controlled than naïve single-step LLM rewriting by introducing explicit applicability assessment, rule-specific transformation guidance, and post-hoc verification.
Automated program repair (APR) has emerged as a promising technique for improving software reliability by automatically fixing bugs. Recent advances in large language models (LLMs), particularly LLM‐based agents, have further enhanced repair capabilities by enabling flexible patch generation and iterative reasoning. However, existing LLM‐based agent frameworks still suffer from several limitations, including unstructured repair processes, unproductive trial‐and‐error loops and the lack of explicit coordination between reasoning and action, which lead to inefficient and unstable repair behaviours. In this paper, we propose SCAgent, an LLM‐based agent for APR with state‐aware coordination. SCAgent structures the repair process into coordinated stages, including bug understanding, information gathering and patch generation, and dynamically controls transitions between these stages based on the repair context. Experimental results on Defects4J show that SCAgent correctly repairs 173 bugs. We further conduct a preliminary evaluation on GitBug‐Java to assess its potential generalizability, with SCAgent correctly repairing 15 bugs in a sampled subset of 100 bugs.
Shaosheng Wang, Lu Lu, Shaojian Qiu· Expert systems· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
