✨ Awesome Issue Resolution¶
✨ Awesome Issue Resolution
Advances and Frontiers of LLM-based Issue Resolution in Software Engineering A Comprehensive Survey
📖 Abstract¶
Based on a systematic review of 281 papers and online resources, this survey establishes a holistic theoretical framework for Issue Resolution in software engineering. We examine how Large Language Models (LLMs) are transforming the automation of GitHub issue resolution. Beyond the theoretical analysis, we have curated a comprehensive collection of datasets and model training resources, which are continuously synchronized with our GitHub repository and project documentation website.
🔍 Explore This Survey:
- 📊 Data: Evaluation and training datasets, data collection and synthesis methods
- 🛠️ Methods: Training-free (agent/workflow) and training-based (SFT/RL) approaches
- 🔍 Analysis: Insights into both data characteristics and method performance
- 📋 Tables & Resources: Comprehensive statistical tables and resources
- 📄 Full Paper: Read the complete survey paper
📊 Data¶
This section covers the datasets used for evaluation and training, as well as methods for data construction.
Evaluation Datasets¶
(2026-08)SWE-Bench ProMax: SWE-Bench ProMax: Benchmarking Agents on Large-Scale Multilingual Code Refactoring(2026-08)Active-SWE: Active-SWE: Benchmarking Coding Agents for Proactive Bug Fixing without Issue Reports(2026-07)MM-IssueLoc: MM-IssueLoc: A Controlled Benchmark for Evaluating Visual Evidence in Multimodal Repository-Level Issue Localization(2026-07)SWE-Review: SWE-Review: Closing the Loop on Issue Resolution with Agentic Code Review(2026-07)LLVM-Bench: LLVM-Bench: Benchmarking and Advancing Large Language Models for LLVM Compiler Issue Resolution(2026-06)A11YRepair: A11YRepair: Bridging Web Accessibility Barriers via Knowledge-Enhanced Divide-and-Conquer Repair(2026-06)MPC-Patch-Bench: MPC-Patch-Bench: Security-Aware LLM Code Patch for Multi-Party Computation(2026-06)SWE-Together: SWE-Together: Evaluating Coding Agents in Interactive User Sessions(2026-06)FrontierCode: Introducing FrontierCode(2026-05)SWE-Cycle: SWE-Cycle: Benchmarking Code Agents across the Complete Issue Resolution Cycle(2026-05)SmellBench: SmellBench: Evaluating LLM Agents on Architectural Code Smell Repair(2026-05)SWE-Chain: SWE-Chain: Benchmarking Coding Agents on Chained Release-Level Package Upgrades(2026-04)SWE-Shield: Does Pass Rate Tell the Whole Story? Evaluating Design Constraint Compliance in LLM-based Issue Resolution(2026-04)CI-Repair-Bench: CI-Repair-Bench: A Repository-Aware Benchmark for Automated Patch Validation via CI Workflows(2026-03)BeyondSWE: BeyondSWE: Can Current Code Agent Survive Beyond Single-Repo Bug Fixing?(2026-03)SWE-CI: SWE-CI: Evaluating Agent Capabilities in Maintaining Codebases via Continuous Integration(2026-03)SWE-Atlas(2026-03)SWE-Skills-Bench: SWE-Skills-Bench: Do Agent Skills Actually Help in Real-World Software Engineering?(2026-03)MobileDev-Bench: MobileDev-Bench: A Comprehensive Benchmark for Evaluating Language Models on Mobile Application Development(2026-03)ComBench: ComBench: A Repo-level Real-world Benchmark for Compilation Error Repair(2026-03)SWE-Milestone: SWE-Milestone: Evaluating AI Agents on Continuous Software Evolution(2026-02)SWE Context Bench: SWE Context Bench: A Benchmark for Context Learning in Coding(2026-02)SWE-ABS: SWE-ABS: Adversarial Benchmark Strengthening Exposes Inflated Success Rates on Test-based Benchmark(2026-02)Rust-SWE-bench: Evaluating and Improving Automated Repository-Level Rust Issue Resolution with LLM-based Agents(2026-02)SWE-Bench Mobile: SWE-Bench Mobile: Can Large Language Model Agents Develop Industry-Level Mobile Applications?(2026-02)SWE-Refactor: SWE-Refactor: A Repository-Level Benchmark for Real-World LLM-Based Code Refactoring(2025-12)SWE-InfraBench: SWE-InfraBench: Evaluating Language Models on Cloud Infrastructure Code(2025-12)SWE-EVO: SWE-EVO: Benchmarking Coding Agents in Long-Horizon Software Evolution Scenarios(2025-11)SWE-Sharp-Bench: SWE-Sharp-Bench: A Reproducible Benchmark for C# Software Engineering Tasks(2025-11)SWE-fficiency: SWE-fficiency: Can Language Models Optimize Real-World Repositories on Real Workloads?(2025-11)SWE-Compass: SWE-Compass: Towards Unified Evaluation of Agentic Coding Abilities for Large Language Models(2025-09)SWE-Bench Pro: SWE-Bench Pro: Can AI Agents Solve Long-Horizon Software Engineering Tasks?(2025-07)SWE-Perf: SWE-Perf: Can Language Models Optimize Code Performance on Real-World Repositories?(2025-05)SwingArena: SwingArena: Competitive Programming Arena for Long-context GitHub Issue Solving(2025-05)OmniGIRL: Omnigirl: A multilingual and multimodal benchmark for github issue resolution(2025-05)SWE-bench-Live: SWE-bench Goes Live!(2025-04)Multi-SWE-bench: Multi-SWE-bench: A Multilingual Benchmark for Issue Resolving(2025-04)SWE-PolyBench: SWE-PolyBench: A multi-language benchmark for repository level evaluation of coding agents(2025-04)SWE-bench Multilingual: SWE-smith: Scaling Data for Software Engineering Agents(2025-03)FEA-Bench: FEA-Bench: A Benchmark for Evaluating Repository-Level Code Generation for Feature Implementation(2025-03)SetUpAgent, SWEE-bench, SWA-bench: Automated Benchmark Generation for Repository-Level Coding Tasks(2025-02)SWE-Lancer: SWE-Lancer: Can Frontier LLMs Earn $1 Million from Real-World Freelance Software Engineering?(2024-12)Visual SWE-bench: CodeV: Issue Resolving with Visual Data(2024-10)SWE-bench Multimodal: SWE-bench Multimodal: Do AI Systems Generalize to Visual Software Domains?(2024-08)SWE-bench-java: SWE-bench-java: A GitHub Issue Resolving Benchmark for Java
Training Datasets¶
(2026-07)MM-IssueLoc: MM-IssueLoc: A Controlled Benchmark for Evaluating Visual Evidence in Multimodal Repository-Level Issue Localization(2026-06)TraceView: TraceView: Interactive Visualization of Agentic Program Repair Trajectories(2026-06)Open-SWE-Traces: Open-SWE-Traces: Advancing Dual-Mode Multilingual Distillation for Software Engineering Agents(2026-05)From Patches to Trajectories: From Patches to Trajectories: Privileged Process Supervision for Software-Engineering Agents(2026-04)From SWE-ZERO to SWE-HERO: From SWE-ZERO to SWE-HERO: Execution-free to Execution-based Fine-tuning for Software Engineering Agents(2026-03)OpenSWE: daVinci-Env: Open SWE Environment Synthesis at Scale(2026-02)SWE-Universe: SWE-Universe: Scale Real-World Verifiable Environments to Millions(2026-02)SWE-rebench V2: SWE-rebench V2: Language-Agnostic SWE Task Collection at Scale(2026-02)Scale-SWE: Immersion in the GitHub Universe: Scaling Coding Agents to Mastery(2026-01)daVinci-Dev: daVinci-Dev: Agent-native Mid-training for Software Engineering(2025-06)Skywork-SWE: Skywork-SWE: Unveiling Data Scaling Laws for Software Engineering in LLMs(2025-05)SWELoc: SweRank: Software Issue Localization with Code Ranking(2025-04)Multi-SWE-RL: Multi-SWE-bench: A Multilingual Benchmark for Issue Resolving(2025-04)SWE-Smith: SWE-smith: Scaling Data for Software Engineering Agents(2025-02)LocAgent: OrcaLoca: An LLM Agent Framework for Software Issue Localization(2025-01)SWE-Fixer: SWE-Fixer: Training Open-Source LLMs for Effective and Efficient GitHub Issue Resolution(2023-10)SWE-bench-extra: SWE-bench: Can Language Models Resolve Real-world Github Issues?
Data Collection¶
(2026-03)OpenSWE: daVinci-Env: Open SWE Environment Synthesis at Scale(2026-03)SWE-Next: SWE-Next: Scalable Real-World Software Engineering Tasks for Agents(2026-03)RepoLaunch: RepoLaunch: Automating Build&Test Pipeline of Code Repositories on ANY Language and ANY Platform(2026-02)DockSmith: DockSmith: Scaling Reliable Coding Environments via an Agentic Docker Builder(2026-02)SWE-rebench V2: SWE-rebench V2: Language-Agnostic SWE Task Collection at Scale(2026-02)Scale-SWE: Immersion in the GitHub Universe: Scaling Coding Agents to Mastery(2026-01)MEnvAgent: MEnvAgent: Scalable Polyglot Environment Construction for Verifiable Software Engineering(2025-12)Multi-Docker-Eval: Multi-Docker-Eval: A 'Shovel of the Gold Rush' Benchmark on Automatic Environment Building for Software Engineering(2025-08)RepoForge: RepoForge: Training a SOTA Fast-thinking SWE Agent with an End-to-End Data Curation Pipeline Synergizing SFT and RL at Scale(2025-07)SWE-MERA: SWE-MERA: A Dynamic Benchmark for Agenticly Evaluating Large Language Models on Software Engineering Tasks(2025-06)SWE-Factory: SWE-Factory: Your Automated Factory for Issue Resolution Training Data and Evaluation Benchmarks(2025-05)SWE-rebench: SWE-rebench: An Automated Pipeline for Task Collection and Decontaminated Evaluation of Software Engineering Agents(2025-03)SetUpAgent, SWEE-bench, SWA-bench: Automated Benchmark Generation for Repository-Level Coding Tasks
Data Synthesis¶
(2026-02)SWE-World: SWE-World: Building Software Engineering Agents in Docker-Free Environments(2026-02)SWE-Hub: SWE-Hub: A Unified Production System for Scalable, Executable Software Engineering Tasks(2025-09)SWE-Mirror: SWE-Mirror: Scaling Issue-Resolving Datasets by Mirroring Issues Across Repositories(2025-06)SWE-Flow: Synthesizing Software Engineering Data in a Test-Driven Manner(2025-04)R2E-Gym: R2E-Gym: Procedural Environment Generation and Hybrid Verifiers for Scaling Open-Weights SWE Agents(2025-04)SWE-Synth: SWE-Synth: Synthesizing Verifiable Bug-Fix Data to Enable Large Language Models in Resolving Real-World Bugs(2025-04)SWE-Smith: SWE-smith: Scaling Data for Software Engineering Agents(2025-01)Learn-by-interact: Learn-by-interact: A Data-Centric Framework For Self-Adaptive Agents in Realistic Environments
🛠️ Methods¶
This section covers both training-free and training-based methods for issue resolution.
🧑💻 Training-free Methods¶
Single-Agent¶
(2026-05)EvoRepair: EvoRepair: Enhancing Vulnerability Repair Agents Through Experience-Based Self-Evolution(2026-05)EviACT: EviACT: An Evidence-to-Action Framework for Agentic Program Repair(2026-05)ContraFix: ContraFix: Skill-Enhanced Contrastive Runtime Analysis for Vulnerability Repair(2026-04)REAgent: REAgent: Requirement-Driven LLM Agents for Software Issue Resolution(2026-04)DebugHarness: DebugHarness: Emulating Human Dynamic Debugging for Autonomous Program Repair(2025-12)Confucius Code Agent: Confucius Code Agent: Scalable Agent Scaffolding for Real-World Codebases(2025-10)TOM-SWE: TOM-SWE: User Mental Modeling For Software Engineering Agents(2025-09)Lita: Lita: Light Agent Uncovers the Agentic Coding Capabilities of LLMs(2025-08)Live-SWE-agent: SE-Agent: Self-Evolution Trajectory Optimization in Multi-Step Reasoning with LLM-Based Agents(2025-07)Trae Agent: Trae Agent: An LLM-based Agent for Software Engineering with Test-time Scaling(2025-05)LCLM: Putting It All into Context: Simplifying Agents with LCLMs(2025-02)PatchPilot: PatchPilot: A Cost-Efficient Software Engineering Agent with Early Attempts on Formal Verification(2024-05)SWE-agent: Swe-agent: Agent-computer interfaces enable automated software engineering(2024-03)Devin: SWE-bench technical report(2023-06)Aider
Multi-Agent¶
(2026-07)AgenticRepair: AgenticRepair: Multi-Faceted Program Context Engineering for Agentic Vulnerability Repair(2026-07)MultiFixer: MultiFixer: A Coordinator-Proposer Based Multi-Agent Framework For Fixing Multi-Hunk Bugs(2026-07)PhoenixRepair: PhoenixRepair: Rethinking Repair Strategy Exploration in Software Agents(2026-06)icat-agent: Unlocking Model Potentials Through Adaptive Multi-Agent Scaffolding for Efficient Issue Resolution(2026-06)Phoenix: Phoenix: Safe GitHub Issue Resolution via Multi-Agent LLMs(2026-04)AgentForge: AgentForge: Execution-Grounded Multi-Agent LLM Framework for Autonomous Software Engineering(2026-04)Agent-CoEvo: Beyond Fixed Tests: Repository-Level Issue Resolution as Coevolution of Code and Behavioral Constraints(2026-03)SWE-Adept: SWE-Adept: An LLM-Based Agentic Framework for Deep Codebase Analysis and Structured Issue Resolution(2026-03)iSWE Agent: Resolving Java Code Repository Issues with iSWE Agent(2025-08)Meta-RAG: Meta-RAG on Large Codebases Using Code Summarization(2025-07)SWE-Debate: SWE-Debate: Competitive Multi-Agent Debate for Software Issue Resolution(2025-06)AgentScope: SWE-Bench - AgentScope(2025-05)Devlo: Achieving SOTA on SWE-bench(2025-05)Refact.ai Agent: AI Coding Agent for Software Development - Refact.ai(2025-03)Lingxi: Lingxi/docs/Lingxi Technical Report 2505.pdf at master · lingxi-agent/Lingxi(2025-02)OrcaLora: OrcaLoca: An LLM Agent Framework for Software Issue Localization(2025-01)CodeCoR: CodeCoR: An LLM-Based Self-Reflective Multi-Agent Framework for Code Generation(2024-09)MarsCode Agent: MarsCode Agent: AI-native Automated Bug Fixing(2024-09)HyperAgent: HyperAgent: Generalist Software Engineering Agents to Solve Coding Tasks at Scale(2024-08)DEI: Diversity Empowers Intelligence: Integrating Expertise of Software Engineering Agents(2024-07)OpenHands: OpenHands: An Open Platform for AI Software Developers as Generalist Agents(2024-06)CodeR: CodeR: Issue Resolving with Multi-Agent and Task Graphs(2024-04)AutoCodeRover: AutoCodeRover: Autonomous Program Improvement(2024-03)MAGIS: MAGIS: LLM-Based Multi-Agent Framework for GitHub Issue Resolution
Workflow¶
(2025-07)SynFix: SynFix: Dependency-Aware Program Repair via RelationGraph Analysis(2025-06)GUIRepair: Seeing is Fixing: Cross-Modal Reasoning with Multimodal LLMs for Visual Software Issue Fixing(2024-12)CodeV: CodeV: Issue Resolving with Visual Data(2024-10)Conversational Pipeline: Exploring the Potential of Conversational Test Suite Based Program Repair on SWE-bench(2024-07)Agentless: Demystifying LLM-Based Software Engineering Agents
Tool¶
(2026-07)MM-IssueLoc: MM-IssueLoc: A Controlled Benchmark for Evaluating Visual Evidence in Multimodal Repository-Level Issue Localization(2026-07)LLVM-Bench: LLVM-Bench: Benchmarking and Advancing Large Language Models for LLVM Compiler Issue Resolution(2026-07)Know Before Fix: Know Before Fix: QA-Driven Repository Knowledge Acquisition for Software Issue Resolution(2026-07)TrajSpec: Bug Report Specification Refinement with Trajectory Guidance for Automated Program Repair(2026-07)PhoenixRepair: PhoenixRepair: Rethinking Repair Strategy Exploration in Software Agents(2026-07)Beyond Fail-to-Pass: Beyond Fail-to-Pass: Iterative Hardening of Co-Generated Bug Reproduction Tests and Fixes(2026-07)IssueExec: IssueExec: A Test-Driven Approach for Localizing Software Engineering Issues(2026-07)VisualRepair: VisualRepair: Dynamic Tool Calling and Region Focusing for Visual Software Issue Repair(2026-07)CT-Repair: Multi-Perspective Agentic Program Repair via Code Property Graphs and Temporal Execution Graphs(2026-07)Retrieval-Oriented Code Representations in Agentic Bug Localization(2026-07)ReProAgent: ReProAgent: Tool-Augmented Multi-Stage Agentic Generation of Bug Reproduction Tests from Issue Reports(2026-07)Beyond Textual Repository Exploration: Beyond Textual Repository Exploration: Dual-Modal Structural Reasoning for Agentic Issue Resolution(2026-07)ContextSniper: ContextSniper: AntTrail's Token-Efficient Code Memory for Repository-Level Program Repair(2026-07)A Single Patch Is Not Enough: A Single Patch Is Not Enough: Deterministic Fusion of Repair Candidates(2026-07)SWE-Doctor: SWE-Doctor: Guiding Software Engineering Agents with Runtime Diagnosis from Multi-Faceted Bug Reproduction Tests(2026-06)Loc2Repair: Loc2Repair: A Framework for Evaluating the Impact of File-Level Issue Localization in Repo-Level LLM Repair(2026-06)PracRepair: PracRepair: LLM-Empowered Automated Program Repair Inspired by Human-Like Debugging Practices(2026-05)EviACT: EviACT: An Evidence-to-Action Framework for Agentic Program Repair(2026-05)BLAgent: BLAgent: Agentic RAG for File-Level Bug Localization(2026-05)ContraFix: ContraFix: Skill-Enhanced Contrastive Runtime Analysis for Vulnerability Repair(2026-05)ARISE: ARISE: A Repository-level Graph Representation and Toolset for Agentic Program Repair and Fault Localization(2026-04)AgentForge: AgentForge: Execution-Grounded Multi-Agent LLM Framework for Autonomous Software Engineering(2026-04)GALA: GALA: Multimodal Graph Alignment for Bug Localization in Automated Program Repair(2026-04)Empowering Autonomous Debugging Agents with Efficient Dynamic Analysis(2026-04)DebugHarness: DebugHarness: Emulating Human Dynamic Debugging for Autonomous Program Repair(2026-04)PROBE: Probe to Generate: Program Variant-Guided Test Augmentation for Repository-Level Repair Benchmarks(2026-03)SWE-Adept: SWE-Adept: An LLM-Based Agentic Framework for Deep Codebase Analysis and Structured Issue Resolution(2026-03)RepoRepair: RepoRepair: Leveraging Code Documentation for Repository-Level Automated Program Repair(2026-03)FailureMem: FailureMem: A Failure-Aware Multimodal Framework for Autonomous Software Repair(2026-03)A Study on the Impact of Fault localization Granularity for Repository-Scale Code Repair Tasks(2026-03)DAIRA: Dynamic analysis enhances issue resolution(2026-02)Closing the Loop: Closing the Loop: Universal Repository Representation with RPG-Encoder(2026-01)SWE-Tester: SWE-Tester: Training Open-Source LLMs for Issue Reproduction in Real-World Repositories(2025-12)GraphLocator: GraphLocator: Graph-guided Causal Reasoning for Issue Localization(2025-11)InfCode: InfCode: Adversarial Iterative Refinement of Tests and Patches for Reliable Software Issue Resolution(2025-10)BugPilot: BugPilot: Complex Bug Generation for Efficient Learning of SWE Skills(2025-10)TestPrune: When Old Meets New: Evaluating the Impact of Regression Tests on SWE Issue Resolution(2025-09)Nemotron-CORTEXA: Nemotron-CORTEXA: Enhancing LLM Agents for Software Engineering Tasks via Improved Localization and Solution Diversity(2025-08)Git Context Controller: Git Context Controller: Manage the Context of LLM-based Agents like Git(2025-07)Prometheus: Prometheus: Unified Knowledge Graphs for Issue Resolution in Multilingual Codebases(2025-06)SACL: SACL: Understanding and Combating Textual Bias in Code Retrieval with Semantic-Augmented Reranking and Localization(2025-06)OpenHands-Versa: Coding Agents with Multimodal Browsing are Generalist Problem Solvers(2025-06)SemAgent: SemAgent: A Semantics Aware Program Repair Agent(2025-06)Repeton: Repeton: Structured Bug Repair with ReAct-Guided Patch-and-Test Cycles(2025-06)cAST: cAST: Enhancing Code Retrieval-Augmented Generation with Structural Chunking via Abstract Syntax Tree(2025-05)InfantAgent-Next: InfantAgent-Next: A Multimodal Generalist Agent for Automated Computer Interaction(2025-05)SWERank: SweRank: Software Issue Localization with Code Ranking(2025-03)DARS: DARS: Dynamic Action Re-Sampling to Enhance Coding Agent Performance by Adaptive Tree Traversal(2025-03)Issue2Test: Issue2Test: Generating Reproducing Test Cases from Issue Reports(2025-03)KGCompass: Enhancing repository-level software repair via repository-aware knowledge graphs(2025-03)CoSIL: Issue Localization via LLM-Driven Iterative Code Graph Searching(2025-02)OrcaLoca: OrcaLoca: An LLM Agent Framework for Software Issue Localization(2025-02)Otter: Otter: Generating Tests from Issues to Validate SWE Patches(2025-02)Quadropic Insiders: Quadropic Insiders : Syntheo Tops Swelite Feb(2024-12)CoRNStack: CoRNStack: High-Quality Contrastive Data for Better Code Retrieval and Reranking(2024-11)AEGIS: AEGIS: An Agent-based Framework for General Bug Reproduction from Issue Descriptions(2024-10)RepoGraph: RepoGraph: Enhancing AI Software Engineering with Repository-level Code Graph(2024-09)SuperCoder2.0: SuperCoder2.0: Technical Report on Exploring the feasibility of LLMs as Autonomous Programmer(2024-08)SpecRover: SpecRover: Code Intent Extraction via LLMs(2024-06)Alibaba LingmaAgent: Alibaba LingmaAgent: Improving Automated Issue Resolution via Comprehensive Repository Exploration
Memory¶
(2026-07)STAIR: Reusing Past Repairs Through Hierarchical Trajectory Abstraction for Coding Agents(2026-07)Know Before Fix: Know Before Fix: QA-Driven Repository Knowledge Acquisition for Software Issue Resolution(2026-07)TrajSpec: Bug Report Specification Refinement with Trajectory Guidance for Automated Program Repair(2026-05)EvoRepair: EvoRepair: Enhancing Vulnerability Repair Agents Through Experience-Based Self-Evolution(2026-05)MemRepair: MemRepair: Hierarchical Memory for Agentic Repository-Level Vulnerability Repair(2026-03)FailureMem: FailureMem: A Failure-Aware Multimodal Framework for Autonomous Software Repair(2026-01)MemGovern: MemGovern: Enhancing Code Agents through Learning from Governed Human Experiences(2025-10)RepoMem: Improving Code Localization with Repository Memory(2025-09)AgentDiet: Improving the Efficiency of LLM Agent Systems through Trajectory Reduction(2025-07)Agent KB: Agent KB: Leveraging Cross-Domain Experience for Agentic Problem Solving(2025-07)SWE-Exp: SWE-Exp: Experience-Driven Software Issue Resolution(2025-06)ExpeRepair: EXPEREPAIR: Dual-Memory Enhanced LLM-based Repository-Level Program Repair(2025-05)DGM: Darwin Godel Machine: Open-Ended Evolution of Self-Improving Agents(2024-11)Infant Agent: Infant Agent: A Tool-Integrated, Logic-Driven Agent with Cost-Effective API Usage(2024-11)EvoCoder: LLMs as Continuous Learners: Improving the Reproduction of Defective Code in Software Issues
Inference-time Scaling¶
(2026-07)LLVM-Bench: LLVM-Bench: Benchmarking and Advancing Large Language Models for LLVM Compiler Issue Resolution(2026-01)Agentic Rubrics: Agentic Rubrics as Contextual Verifiers for SWE Agents(2025-10)SIADAFIX: SIADAFIX: issue description response for adaptive program repair(2025-09)SWE-PRM: When Agents go Astray: Course-Correcting SWE Agents with PRMs(2025-01)ReasoningBank: CodeMonkeys: Scaling Test-Time Compute for Software Engineering(2024-10)SWE-Search: SWE-Search: Enhancing Software Agents with Monte Carlo Tree Search and Iterative Refinement
🧠 Training-based Methods¶
SFT-based Methods¶
(2026-06)Open-SWE-Traces: Open-SWE-Traces: Advancing Dual-Mode Multilingual Distillation for Software Engineering Agents(2026-05)From Patches to Trajectories: From Patches to Trajectories: Privileged Process Supervision for Software-Engineering Agents(2026-04)SWE-AGILE: SWE-AGILE: A Software Agent Framework for Efficiently Managing Dynamic Reasoning Context(2026-04)From SWE-ZERO to SWE-HERO: From SWE-ZERO to SWE-HERO: Execution-free to Execution-based Fine-tuning for Software Engineering Agents(2026-03)OpenSWE: daVinci-Env: Open SWE Environment Synthesis at Scale(2026-03)SWEzze: Compressing Code Context for LLM-based Issue Resolution(2026-02)Scale-SWE: Immersion in the GitHub Universe: Scaling Coding Agents to Mastery(2026-01)SWE-Lego: SWE-Lego: Pushing the Limits of Supervised Fine-tuning for Software Issue Resolving(2026-01)SWE-Replay: SWE-Replay: Efficient Test-Time Scaling for Software Engineering Agents(2025-12)SWE-Compressor: Context as a Tool: Context Management for Long-Horizon SWE-Agents(2025-09)Devstral: Devstral: Fine-tuning Language Models for Coding Agent Applications(2025-06)MCTS-Refined CoT: MCTS-Refined CoT: High-Quality Fine-Tuning Data for LLM-Based Repository Issue Resolution(2025-05)Search for training: Guided Search Strategies in Non-Serializable Environments with Applications to Software Engineering Agents(2025-05)Co-PatcheR: Co-PatcheR: Collaborative Software Patching with Component(s)-specific Small Reasoning Models(2025-05)CGM: Code Graph Model (CGM): A Graph-Integrated Large Language Model for Repository-Level Software Engineering Tasks(2025-03)Thinking Longer: Thinking Longer, Not Larger: Enhancing Software Engineering Agents via Scaling Test-Time Compute(2024-12)ReSAT: Repository Structure-Aware Training Makes SLMs Better Issue Resolver(2024-12)Scaling data collection: Scaling Data Collection for Training SWE Agents(2024-12)SWE-Gym: Training Software Engineering Agents and Verifiers with SWE-Gym(2024-11)Lingma SWE-GPT: SWE-GPT: A Process-Centric Language Model for Automated Software Improvement(2024-11)CodeXEmbed: CodeXEmbed: A Generalist Embedding Model Family for Multilingual and Multi-task Code Retrieval
RL-based Methods¶
(2026-05)BoostAPR: BoostAPR: Boosting Automated Program Repair via Execution-Grounded Reinforcement Learning with Dual Reward Models(2026-04)SWE-AGILE: SWE-AGILE: A Software Agent Framework for Efficiently Managing Dynamic Reasoning Context(2026-04)RTMC: RTMC: Step-Level Credit Assignment via Rollout Trees(2026-04)SWE-TRACE: SWE-TRACE: Optimizing Long-Horizon SWE Agents Through Rubric Process Reward Models and Heuristic Test-Time Scaling(2026-03)SWE-Fuse: SWE-Fuse: Empowering Software Agents via Issue-free Trajectory Learning and Entropy-aware RLVR Training(2026-02)SWE-Master: SWE-Master: Unleashing the Potential of Software Engineering Agents via Post-Training(2026-02)SWE-Protégé: SWE-Protégé: Learning to Selectively Collaborate With an Expert Unlocks Small Language Models as Software Engineering Agents(2026-02)SWE-MiniSandbox: SWE-MiniSandbox: Container-Free Reinforcement Learning for Building Software Engineering Agents(2026-01)MiMo-V2-Flash: MiMo-V2-Flash Technical Report(2026-01)SWE-Manager: SWE-Manager: Selecting and Synthesizing Golden Proposals Before Coding(2025-12)Self-play SWE-RL: Toward Training Superintelligent Software Agents through Self-Play SWE-RL(2025-12)SWE-Playground: Training Versatile Coding Agents in Synthetic Environments(2025-12)SWE-RM: SWE-RM: Execution-free Feedback For Software Engineering Agents(2025-12)One Tool Is Enough: One Tool Is Enough: Reinforcement Learning for Repository-Level LLM Agents(2025-12)Let It Flow: Let It Flow: Agentic Crafting on Rock and Roll, Building the ROME Model within an Open Agentic Learning Ecosystem(2025-12)Deepseek V3.2: DeepSeek-V3.2: Pushing the Frontier of Open Large Language Models(2025-11)TSP: Think-Search-Patch: A Retrieval-Augmented Reasoning Framework for Repository-Level Code Repair(2025-10)CWM: CWM: An Open-Weights LLM for Research on Code Generation with World Models(2025-10)FoldGRPO: Scaling Long-Horizon LLM Agent via Context-Folding(2025-10)GRPO-based Method: A Practitioner's Guide to Multi-turn Agentic Reinforcement Learning(2025-10)Supervised RL: Supervised Reinforcement Learning: From Expert Trajectories to Step-wise Reasoning(2025-10)KAT-Coder: KAT-Coder Technical Report(2025-09)CoreThink: CoreThink: A Symbolic Reasoning Layer to reason over Long Horizon Tasks with LLMs(2025-09)EntroPO: Building Coding Agents via Entropy-Enhanced Multi-Turn Preference Optimization(2025-09)Kimi-Dev: Kimi-Dev: Agentless Training as Skill Prior for SWE-Agents(2025-09)LongCat-Flash-Think: Introducing LongCat-Flash-Thinking: A Technical Report(2025-08)Tool-integrated RL: Tool-integrated Reinforcement Learning for Repo Deep Search(2025-08)SWE-Swiss: SWE-Swiss: A Multi-Task Fine-Tuning and RL Recipe for High-Performance Issue Resolution(2025-08)SeamlessFlow: SeamlessFlow: A Trainer Agent Isolation RL Framework Achieving Bubble-Free Pipelines via Tag Scheduling(2025-08)DAPO: Training Long-Context, Multi-Turn Software Engineering Agents with Reinforcement Learning(2025-08)GLM-4.6: gpt-oss-120b & gpt-oss-20b model card(2025-07)DeepSWE: DeepSWE: Training a State-of-the-Art Coding Agent from Scratch by Scaling RL(2025-07)Kimi-K2-Instruct: Kimi K2: Open Agentic Intelligence(2025-06)Agent-RLVR: Agent-RLVR: Training Software Engineering Agents via Guidance and Environment Rewards(2025-06)SWE-Dev2: SWE-Dev: Building Software Engineering Agents with Training and Inference Scaling(2025-06)Minimax M2: MiniMax-M1: Scaling Test-Time Compute Efficiently with Lightning Attention(2025-05)SWE-Dev1: SWE-Dev: Evaluating and Training Autonomous Feature-Driven Software Development(2025-05)Satori-SWE: Satori-SWE: Evolutionary Test-Time Scaling for Sample-Efficient Software Engineering(2025-05)Qwen3-Coder: Qwen3 Technical Report(2025-04)Seed1.5-Thinking: Seed1.5-Thinking: Advancing Superb Reasoning Models with Reinforcement Learning(2025-03)SEAlign: SEAlign: Alignment Training for Software Engineering Agent(2025-02)SWE-RL: SWE-RL: Advancing LLM Reasoning via Reinforcement Learning on Open Software Evolution(2025-02)SoRFT: SoRFT: Issue Resolving with Subtask-oriented Reinforced Fine-Tuning(2024-10)OSCA: Scaling LLM Inference Efficiently with Optimized Sample Compute Allocation
🔍 Analysis¶
This section includes research works that provide in-depth analysis and discussion of data, methods, and related phenomena in issue resolution.
Data Analysis¶
(2026-07)Rethinking Issue Resolution for AI/ML Systems(2025-12)Data contamination: Does SWE-Bench-Verified Test Agent Ability or Model Memory?(2025-11)Test Overfitting on SWE-bench: Investigating Test Overfitting on SWE-bench(2025-07)Rigorous agentic benchmarks: Establishing Best Practices for Building Rigorous Agentic Benchmarks(2025-07)SPICE: SPICE: An Automated SWE-Bench Labeling Pipeline for Issue Clarity, Test Coverage, and Effort Estimation(2025-06)UTBoost: UTBoost: Rigorous Evaluation of Coding Agents on SWE-Bench(2025-06)Trustworthiness: Is Your Automated Software Engineer Trustworthy?(2025-06)The SWE-Bench Illusion: The SWE-Bench Illusion: When State-of-the-Art LLMs Remember Instead of Reason(2025-04)Revisiting SWE-Bench: Revisiting SWE-Bench: On the Importance of Data Quality for LLM-Based Code Models(2025-03)Patch Correctness: Are "Solved Issues" in SWE-bench Really Solved Correctly? An Empirical Study(2024-08)SWE-bench Verified: Introducing SWE-bench Verified | OpenAI
Methods Analysis¶
(2026-07)SWE-Review: SWE-Review: Closing the Loop on Issue Resolution with Agentic Code Review(2026-07)Validation Evidence in LLM Repair Agents: Validation Evidence in LLM Repair Agents: How Much of What Passes Actually Tests the Bug?(2026-07)How Do LLMs Read Bug Reports? An Empirical Study of Attention in LLMs for Automated Program Repair(2026-07)Semantic Drift in Bug Resolution: Semantic Drift in Bug Resolution: How Behavioral Signals Propagate from Reports to Tests and Patches(2026-07)Writing Bug Reports for Software Repair Agents: Writing Bug Reports for Software Repair Agents: What Information Matters Most?(2026-07)What Makes a Good Bug Report for an AI Agent?(2026-06)To Run or Not to Run: To Run or Not to Run: Analyzing the Cost-Effectiveness of Code Execution in LLM-Based Program Repair(2026-06)TraceView: TraceView: Interactive Visualization of Agentic Program Repair Trajectories(2026-05)"Refactoring Runaway": "Refactoring Runaway": Understanding and Mitigating Tangled Refactorings in Coding Agents for Issue Resolution(2026-05)Characterizing the Failure Modes of LLMs in Resolving Real-World GitHub Issues(2026-04)On the Role of Fault Localization Context for LLM-Based Program Repair(2026-03)A Study on the Impact of Fault localization Granularity for Repository-Scale Code Repair Tasks(2026-02)ContextBench: ContextBench: A Benchmark for Context Retrieval in Coding Agents(2025-12)SWEnergy: SWEnergy: An Empirical Study on Energy Efficiency in Agentic Issue Resolution Frameworks with SLMs(2025-09)Failures analysis: An Empirical Study on Failures in Automated Issue Solving(2025-07)Security analysis: How Safe Are AI-Generated Patches? A Large-scale Study on Security Risks in LLM and Agentic Automated Program Repair on SWE-bench(2025-06)Dissecting the SWE-Bench Leaderboards: Dissecting the SWE-Bench Leaderboards: Profiling Submitters and Architectures of LLM- and Agent-Based Repair Systems(2025-05)GSO: GSO: Challenging Software Optimization Tasks for Evaluating SWE-Agents(2025-05)Strong-Weak Model Collaboration: An Empirical Study on Strong-Weak Model Collaboration for Repo-level Code Generation(2025-05)Agents in the Wild(2025-04)SeaView: SeaView: Software Engineering Agent Visual Interface for Enhanced Workflow(2025-03)Beyond final code: Beyond Final Code: A Process-Oriented Error Analysis of Software Development Agents in Real-World GitHub Scenarios(2025-02)Overthinking: The Danger of Overthinking: Examining the Reasoning-Action Dilemma in Agentic Tasks(2024-10)Evaluating software development agents: Evaluating Software Development Agents: Patch Patterns, Code Quality, and Issue Complexity in Real-World GitHub Scenarios(2024-06)Context Retrieval: On The Importance of Reasoning for Context Retrieval in Repository-Level Code Editing
Others¶
🚀 Challenges and Opportunities¶
High computational overhead¶
In online RL, performing concurrent rollouts necessitates the simultaneous orchestration of numerous sandboxed containers, which incurs substantial storage footprints and computational costs. Similarly, verifying instances during data construction requires extensive parallel validation. This highlights the need for lightweight sandboxing and optimized resource scheduling.
Lack of efficiency-aware evaluation¶
Current evaluations of issue resolution methods mainly focus on effectiveness metrics such as resolve rates while overlooking efficiency metrics like API costs and inference time. This oversight creates a biased domain where the computational and economic burdens of high-performing models are obscured. Consequently, future research must integrate both resolve rates and efficiency metrics into the evaluation framework to objectively reflect the comprehensive performance of issue resolution methods.
Limited visually-grounded reasoning¶
Multimodal tasks are rare in current benchmarks, hindering the evaluation of visually-dependent tasks such as frontend development and data visualization. Moreover, existing methods often simply flatten visuals into text, failing to capture the critical alignment between rendering and code. To address this, future research must prioritize constructing multimodal benchmarks and training specialized code-centric models.
Safety risks in autonomous resolution¶
Recently, some agents have exhibited unsafe behaviors on coding tasks, including deleting a user's codebase and cheating during evaluation. These failures motivate safer agent frameworks and more robust model safety alignment to prevent reward hacking in real deployments.
Lack of fine-grained rewards¶
Most RL methods for issue resolution still rely on outcome-level rewards, typically the binary test pass/fail signal. However, issue resolution requires multi-turn interaction with the environment, and an outcome reward makes credit assignment across action steps ambiguous. A promising direction is to design finer-grained process rewards to provide denser supervision and improve policy optimization.
Data leakage and contamination¶
As benchmarks like SWE-Bench approach saturation, evaluation reliability is threatened by significant data leakage and quality control issues. Models may inadvertently memorize solutions due to unclear training cutoff dates, while the benchmarks themselves frequently suffer from invalid instances—including ambiguous descriptions, solution hints, and insufficient test coverage. To restore trust, future frameworks must prioritize rigorous data curation and decontamination protocols to guarantee the validity of comparative assessments.
Lack of autonomous context management mechanisms¶
Issue resolution tasks often require long-horizon, multi-turn interaction between the model and the code environment. This both raises API cost and degrades performance due to context rot. A promising solution is to construct an autonomous context management mechanism that proactively compresses and curates the model's interaction history.
Insufficient patch validation and human review¶
Since gold tests are unavailable in real-world development, relying solely on generation capability is insufficient. Future agents should incorporate intrinsic validation mechanisms, utilizing regression testing and dependency analysis to prevent feature regression. Additionally, to bridge the trust gap, research can prioritize human-centric interfaces, such as visual explanations and concise summaries, that assist developers in efficiently reviewing and accepting model-generated solutions.
Lack of universality across SWE domains¶
While existing research predominantly focuses on the implementation and integration phases of the Software Development Life Cycle (SDLC), it often fails to address the comprehensive needs of the broader software engineering field. Future research should therefore broaden its scope to encompass diverse lifecycle stages—such as requirements analysis and architectural design—to develop more versatile automated software generation methods.
📚 More to read¶
- 📂 GitHub Repository: DeepSoftwareAnalytics/Awesome-Issue-Resolution
- 📄 Paper PDF: PDF
- 📧 Contact: GitHub Issues