mlsanityData to 14 Oct 2026

OrcaLoca: An LLM Agent Framework for Software Issue Localization

arXiv 2502.00350 ↗First posted 1 Feb 2025cs.SE cs.AIcited by 45

On the map: LLM agents and tool use → Software engineering coding agents

Abstract (arXiv)

Recent developments in Large Language Model (LLM) agents are revolutionizing Autonomous Software Engineering (ASE), enabling automated coding, problem fixes, and feature improvements. However, localization -- precisely identifying software problems by navigating to relevant code sections -- remains a significant challenge. Current approaches often yield suboptimal results due to a lack of effective integration between LLM agents and precise code search mechanisms. This paper introduces OrcaLoca, an LLM agent framework that improves accuracy for software issue localization by integrating priority-based scheduling for LLM-guided action, action decomposition with relevance scoring, and distance-aware context pruning. Experimental results demonstrate that OrcaLoca becomes the new open-source state-of-the-art (SOTA) in function match rate (65.33%) on SWE-bench Lite. It also improves the final resolved rate of an open-source framework by 6.33 percentage points through its patch generation integration.

Key facts. Cited by 45 papers in the map (data through 14 Oct 2026). Placed in Software engineering coding agents, one of 16 directions in LLM agents and tool use. Builds on 19 of its 43 references that are in the map. First posted on arXiv 1 Feb 2025.

Builds on

19 of 43 references.

Closest ancestors · 7

Same direction, newest first

  1. 2024HyperAgent: Generalist Software Engineering Agents to Solve Coding Tasks at Scale9 Sep
  2. 2024MarsCode Agent: AI-native Automated Bug Fixing2 Sep
  3. 2024OpenHands: An Open Platform for AI Software Developers as Generalist Agents23 Jul
  4. 2024Agentless: Demystifying LLM-based Software Engineering Agents1 Jul
  5. 2024SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineering6 May
  6. 2024Executable Code Actions Elicit Better LLM Agents1 Feb
  7. 2023RCAgent: Cloud Root Cause Analysis by Autonomous Agents with Tool-Augmented Large Language Models25 Oct

Other references · 12

  1. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 14,132
  2. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,459
  3. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,695
  4. 2021Evaluating Large Language Models Trained on Codecited by 8,320
  5. 2023SWE-bench: Can Language Models Resolve Real-World GitHub Issues?cited by 3,373
  6. 2023MetaGPT: Meta Programming for A Multi-Agent Collaborative Frameworkcited by 1,808
  7. 2024AutoCodeRover: Autonomous Program Improvementcited by 278
  8. 2024RepoGraph: Enhancing AI Software Engineering with Repository-level Code Graphcited by 91
  9. 2023Large Language Models for Test-Free Fault Localizationcited by 67
  10. 2024AgentFL: Scaling LLM-based Fault Localization to Project-Level Contextcited by 47
  11. 2023Large Language Models in Fault Localisationcited by 28
  12. 2024ContrastRepair: Enhancing Conversation-Based Automated Program Repair via Contrastive Test Case Pairscited by 19

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 19; 2026: 26.

45 papers.

Sort:

By area:

  1. 2025LocAgent: Graph-Guided LLM Agents for Code Localizationcited by 86
  2. 2025SWE-Debate: Competitive Multi-Agent Debate for Software Issue Resolutioncited by 53
  3. 2025Stronger-MAS: Multi-Agent Reinforcement Learning for Collaborative LLMscited by 28
  4. 2025Retrieval-Augmented Code Generation: A Survey with Focus on Repository-Level Approachescited by 23
  5. 2025Issue Localization via LLM-Driven Iterative Code Graph Searchingcited by 22
  6. 2026SWE-Explore: Benchmarking How Coding Agents Explore Repositoriescited by 21
  7. 2025SweRank: Software Issue Localization with Code Rankingcited by 20
  8. 2025Improving Code Localization with Repository Memorycited by 20
  9. 2025GraphCodeAgent: Dual Graph-Guided LLM Agent for Retrieval-Augmented Repo-Level Code Generationcited by 17
  10. 2025Tool-integrated Reinforcement Learning for Repo Deep Searchcited by 15
  11. 2026CodeScout: An Effective Recipe for Reinforcement Learning of Code Search Agentscited by 9
  12. 2025Dissecting the SWE-Bench Leaderboards: Profiling Submitters and Architectures of LLM- and Agent-Based Repair Systemscited by 8
33 more
  1. 2025RANGER -- Repository-Level Agent for Graph-Enhanced Retrievalcited by 7
  2. 2025A Comprehensive Empirical Evaluation of Agent Frameworks on Code-centric Software Engineering Taskscited by 7
  3. 2025Agentic Software Issue Resolution with Large Language Models: A Surveycited by 6
  4. 2025Red Teaming Program Repair Agents: When Correct Patches can Hide Vulnerabilitiescited by 5
  5. 2025SweRank+: Multilingual, Multi-Turn Code Ranking for Software Issue Localizationcited by 5
  6. 2026RGFL: Reasoning Guided Fault Localization for Automated Program Repair Using Large Language Modelscited by 5
  7. 2026FastContext: Training Efficient Repository Explorer for Coding Agentscited by 5
  8. 2025BioVerge: A Comprehensive Benchmark and Study of Self-Evaluating Agents for Biomedical Hypothesis Generationcited by 4
  9. 2025GraphLocator: Graph-guided Causal Reasoning for Issue Localizationcited by 4
  10. 2026SWE-Adept: An LLM-Based Agentic Framework for Deep Codebase Analysis and Structured Issue Resolutioncited by 4
  11. 2026On the Role of Fault Localization Context for LLM-Based Program Repaircited by 3
  12. 2026LLM Agents Can See Code Repositoriescited by 3
  13. 2026Loc2Repair: A Framework for Evaluating the Impact of File-Level Issue Localization in Repo-Level LLM Repaircited by 3
  14. 2026ARISE: A Repository-level Graph Representation and Toolset for Agentic Program Repair and Fault Localizationcited by 2
  15. 2026MetaAgent-X : Breaking the Ceiling of Automatic Multi-Agent Systems via End-to-End Reinforcement Learningcited by 2
  16. 2026LARGER: Lexically Anchored Repository Graph Exploration and Retrievalcited by 2
  17. 2026SHERLOC: Structured Diagnostic Localization for Code Repair Agentscited by 2
  18. 2026PhoenixRepair: Rethinking Repair Strategy Exploration in Software Agentscited by 2
  19. 2025Natural Language Summarization Enables Multi-Repository Bug Localization by LLMs in Microservice Architecturescited by 1
  20. 2026Neurosymbolic Repo-level Code Localizationcited by 1
  21. 2026How Much Static Structure Do Code Agents Need? A Study of Deterministic Anchoringcited by 1
  22. 2026Cost-Effective Repository Exploration for Agentic Issue Localizationcited by 1
  23. 2025One Tool Is Enough: Reinforcement Learning for Repository-Level LLM Agentscited by 0
  24. 2026GREPO: A Benchmark for Graph Neural Networks on Repository-Level Bug Localizationcited by 0
  25. 2026Multi-CoLoR: Context-Aware Localization and Reasoning across Multi-Language Codebasescited by 0
  26. 2026Ekka: Automated Diagnosis of Silent Errors in LLM Inferencecited by 0
  27. 2026CodeNib: A Multi-View Data System for Serving Repository Context to Coding Agentscited by 0
  28. 2026A^2Agent: Action-Aware Reinforcement Learning for Repository-Level Code Localization Agentscited by 0
  29. 2026XAgent: eXecution-guided Agentic AI for Effective Localization and Resolution of GitHub Issuescited by 0
  30. 2026RepoAtlas: Guiding Coding Agents via Evolving Multimodal Repository Viewscited by 0
  31. 2026Semantic Navigation for Issue Localization in Code Repositorycited by 0
  32. 2026Small Agents with Semantic Search: Efficient Multilingual Code Localizationcited by 0
  33. 2026Quality, Not Just Outcome: A Structural Scoring Framework for Selecting Coding-Agent Trajectories for Supervised Fine-Tuningcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026LIDL: LLM Integration Defect Localization via Knowledge Graph-Enhanced Multi-Agent Analysis
  2. 2026Advances and Frontiers of LLM-based Issue Resolution in Software Engineering: A Comprehensive Survey
  3. 2024An Empirical Study on LLM-based Agents for Automated Bug Fixing
  4. 2026Retrieval-Oriented Code Representations in Agentic Bug Localization
  5. 2025Meta-RAG on Large Codebases Using Code Summarization
  6. 2025Reformulate, Retrieve, Localize: Agents for Repository-Level Bug Localization
  7. 2025SWE-Exp: Experience-Driven Software Issue Resolution
  8. 2024A Multi-Agent Approach to Fault Localization via Graph-Based Retrieval and Reflexion