PhoenixRepair: Rethinking Repair Strategy Exploration in Software Agents

• URL: http://arxiv.org/abs/2607.18859v1
• Date: Tue, 21 Jul 2026 08:49:30 GMT
• Title: PhoenixRepair: Rethinking Repair Strategy Exploration in Software Agents
• Abstract summary: We present PhoenixRepair, a multi-agent framework that explores multiple candidate edit locations and generates better patches.<n>PhoenixRepair achieves the largest relative improvement of 7.8% over SWE-agent under DeepSeek-V3.1, and attains the highest resolved rate of 76.0% Pass@1 under MiniMax-M2.5.
• Score: 62.36339598951133
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: While Large Language Models have greatly advanced automated issue resolution, existing agent-based methods exhibit a fundamental limitation in their insufficient exploration of repair strategies. This insufficiency manifests in two key aspects. First, the exploration of multiple potential edit locations is limited. Second, the exploration of repair attempts at each location is also insufficient. To address these challenges, we present PhoenixRepair, a multi-agent framework that systematically explores multiple candidate edit locations and performs iterative reflection and refinement on patch generation, thereby expanding the search space of repair strategies. Our framework begins with multi-location sampling, optionally augmented with graph-based localization information for difficult tasks, followed by iterative reflection and refinement to generate better patches, culminating in final-round generation guided by distilled insights from all historical attempts. Experiments on SWE-bench-Verified demonstrate that PhoenixRepair achieves the largest relative improvement of 7.8\% over SWE-agent under DeepSeek-V3.1, and attains the highest resolved rate of 76.0\% Pass@1 under MiniMax-M2.5. Meanwhile, it achieves higher fault localization accuracy than existing approaches. Our code is available at https://github.com/DeepSoftwareAnalytics/PhoenixRepair.

Related papers

• Dream-RSI: Recursive Self-Improvement through Evolving Worlds [61.888486670260306]
  textscDream-RSI is a framework for scalable self-improving exploration.<n>A lightweight orchestration layer makes exploration explicit and programmable.<n>By performing dreaming in the replay simulator constructed from historical discovery trees, textscDream-RSI secures immediate, low-cost off-policy feedback.
  arXiv  Detail & Related papers  (2026-09-14T00:10:47Z)
• Repair or Resample? Rethinking Failure Debugging in LLM Multi-Agent Systems [15.825635807363499]
  We introduce SymTrace, a controlled evaluation framework that records the MAS execution trajectory and establishes intervention anchors.<n>During replay, it effectively reconstructs the execution before the anchor using recorded logs and only regenerates the downstream trajectory.<n>Our findings reveal that existing unguided rerun methods are highly unreliable, exhibiting low failure reproduction and repair rates.
  arXiv  Detail & Related papers  (2026-08-26T15:33:47Z)
• MT-Web2Code: Benchmarking Coding Agents on Multi-Turn Regional Reconstruction and Localized Modification [26.741669879220684]
  MT-Web2Code is the first multimodal coding benchmark for multi-turn Macro-Level Regional Reconstruction and Micro-Level Localized Modification.<n>We develop a scalable Reverse-Corruption Trajectory Engine that iteratively injects structural and stylistic defects into golden pages.<n> Experiments on 13 coding agents reveal that current agents struggle to faithfully target regions while preserving unaffected content, lack fine-grained visual-code alignment for localized edits, and suffer from error snowballing over multiple turns.
  arXiv  Detail & Related papers  (2026-08-04T11:14:00Z)
• TerraRepair: A Tool-Grounded LLM Agent for Infrastructure-as-Code Repair [4.223176941421543]
  Large Language Model (LLM)-based repair approaches can repair some findings, but may hallucinate unsupported constructs or suppress warnings without fixing the issue.<n>We present a prototype of a tool-grounded LLM agent for Terraform repair with structured escalation.<n>We evaluate our tool on two vulnerable-by-design Terraform repositories using two IaC security scanners, Checkov and Trivy, across AWS, Azure, and GCP.
  arXiv  Detail & Related papers  (2026-07-13T10:54:38Z)
• Knowledge-Enhanced Agentic Vulnerability Repair [20.715227299482947]
  KeaRepair is a novel agentic approach that grounds patch generation in verified program facts and high-level vulnerability knowledge.<n>It significantly outperforms existing approaches on 55 C/C++ vulnerabilities.<n>When paired with Gemini-3.1-Pro, KeaRepair successfully repairs 46 vulnerabilities, achieving a repair rate of 83.64%.
  arXiv  Detail & Related papers  (2026-07-01T11:42:25Z)
• Root-Cause-Driven Automated Vulnerability Repair [22.901308199259443]
  Kumushi is a root-cause-driven patching agent that focuses on the code most relevant to the defect.<n>It produces more root-cause fixes and fewer superficial patches, and is preferred in the majority of decisive pairwise comparisons.
  arXiv  Detail & Related papers  (2026-05-05T19:34:49Z)
• DocSeeker: Structured Visual Reasoning with Evidence Grounding for Long Document Understanding [63.257540233507626]
  We propose a paradigm that requires the model to execute a structured Analysis, Localization and Reasoning workflow.<n>We show it robustly generalizes from short-page training to ultra-long documents and is naturally synergistic with visual Retrieval-Augmented Generation systems.
  arXiv  Detail & Related papers  (2026-04-14T14:39:26Z)
• FailureMem: A Failure-Aware Multimodal Framework for Autonomous Software Repair [45.42550492783294]
  Multimodal Automated Program Repair (MAPR) extends traditional program repair by requiring models to jointly reason over source code, textual issue descriptions, and visual artifacts such as GUI screenshots.<n>We propose FailureMem, a multimodal repair framework that integrates three key mechanisms: a hybrid workflow-agent architecture that balances structured localization with flexible reasoning, active perception tools that enable region-level visual grounding, and a Failure Memory Bank that converts past repair attempts into reusable guidance.
  arXiv  Detail & Related papers  (2026-03-18T15:24:22Z)
• BeyondSWE: Can Current Code Agent Survive Beyond Single-Repo Bug Fixing? [61.247730037229815]
  We introduce BeyondSWE, a comprehensive benchmark that broadens existing evaluations along two axes - resolution scope and knowledge scope.<n>To investigate the role of external knowledge, we develop SearchSWE, a framework that integrates deep search with coding abilities.<n>This work offers both a realistic, challenging evaluation benchmark and a flexible framework to advance research toward more capable code agents.
  arXiv  Detail & Related papers  (2026-03-03T17:52:01Z)
• SWE-Adept: An LLM-Based Agentic Framework for Deep Codebase Analysis and Structured Issue Resolution [9.339988760379915]
  Large language models (LLMs) exhibit strong performance on self-contained tasks.<n>SWE-Adept is a framework where a localization agent identifies issue-relevant code locations and a resolution agent implements the corresponding fixes.<n> Experiments on SWE-Bench Lite and SWE-Bench Pro demonstrate that SWE-Adept consistently outperforms prior approaches in both issue localization and resolution.
  arXiv  Detail & Related papers  (2026-03-01T23:52:30Z)
• DoVer: Intervention-Driven Auto Debugging for LLM Multi-Agent Systems [48.971606069204825]
  DoVer is an intervention-driven debug framework for large language model (LLM)-based multi-agent systems.<n>It augments hypothesis generation with active verification through targeted interventions.<n>DoVer flips 18-28% of failed trials into successes, achieves up to 16% milestone progress, and validates or refutes 30-60% of failure hypotheses.
  arXiv  Detail & Related papers  (2025-12-07T09:23:48Z)
• FINEREASON: Evaluating and Improving LLMs' Deliberate Reasoning through Reflective Puzzle Solving [90.88021670297664]
  FINEREASON is a logic-puzzle benchmark for evaluation of large language models' reasoning capabilities.<n>We introduce two tasks: state checking, and state transition, for a comprehensive evaluation of how models assess the current situation and plan the next move.<n>We show that models trained on our state checking and transition data demonstrate gains in math reasoning by up to 5.1% on GSM8K.
  arXiv  Detail & Related papers  (2025-02-27T16:23:25Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.