mlsanityData to 7 Oct 2026

MASAI: Modular Architecture for Software-engineering AI Agents

arXiv 2406.11638 ↗First posted 17 Jun 2024cs.AI cs.SEcited by 49

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

Abstract (arXiv)

A common method to solve complex problems in software engineering, is to divide the problem into multiple sub-problems. Inspired by this, we propose a Modular Architecture for Software-engineering AI (MASAI) agents, where different LLM-powered sub-agents are instantiated with well-defined objectives and strategies tuned to achieve those objectives. Our modular architecture offers several advantages: (1) employing and tuning different problem-solving strategies across sub-agents, (2) enabling sub-agents to gather information from different sources scattered throughout a repository, and (3) avoiding unnecessarily long trajectories which inflate costs and add extraneous context. MASAI enabled us to achieve the highest performance (28.33% resolution rate) on the popular and highly challenging SWE-bench Lite dataset consisting of 300 GitHub issues from 11 Python repositories. We conduct a comprehensive evaluation of MASAI relative to other agentic methods and analyze the effects of our design decisions and their contribution to the success of MASAI.

Key facts. Cited by 49 papers in the map (data through 7 Oct 2026). Placed in Software engineering coding agents, one of 16 directions in LLM agents and tool use. Builds on 28 of its 44 references that are in the map. First posted on arXiv 17 Jun 2024.

Builds on

28 of 44 references.

Closest ancestors · 1

Same direction, newest first

  1. 2024Executable Code Actions Elicit Better LLM Agents1 Feb

Other references · 27

  1. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,302
  2. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,160
  3. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,355
  4. 2021Evaluating Large Language Models Trained on Codecited by 8,053
  5. 2022Large Language Models are Zero-Shot Reasonerscited by 4,323
  6. 2023Toolformer: Language Models Can Teach Themselves to Use Toolscited by 4,072
  7. 2023Reflexion: Language Agents with Verbal Reinforcement Learningcited by 4,064
  8. 2023SWE-bench: Can Language Models Resolve Real-World GitHub Issues?cited by 3,193
  9. 2023Tree of Thoughts: Deliberate Problem Solving with Large Language Modelscited by 3,155
  10. 2023Code Llama: Open Foundation Models for Codecited by 2,105
  11. 2023MetaGPT: Meta Programming for A Multi-Agent Collaborative Frameworkcited by 1,761
  12. 2023Gorilla: Large Language Model Connected with Massive APIscited by 1,302
15 more
  1. 2022Language Models as Zero-Shot Planners: Extracting Actionable Knowledge for Embodied Agentscited by 1,029
  2. 2023Large Language Models Can Be Easily Distracted by Irrelevant Contextcited by 820
  3. 2024Large Language Model based Multi-Agents: A Survey of Progress and Challengescited by 752
  4. 2023AgentVerse: Facilitating Multi-Agent Collaboration and Exploring Emergent Behaviorscited by 580
  5. 2023Language Agent Tree Search Unifies Reasoning Acting and Planning in Language Modelscited by 551
  6. 2024AutoCodeRover: Autonomous Program Improvementcited by 272
  7. 2023SwiftSage: A Generative Agent with Fast and Slow Thinking for Complex Interactive Taskscited by 166
  8. 2023CodePlan: Repository-level Coding using LLMs and Planningcited by 139
  9. 2024Code Generation with AlphaCodium: From Prompt Engineering to Flow Engineeringcited by 100
  10. 2024CodeR: Issue Resolving with Multi-Agent and Task Graphscited by 89
  11. 2024If LLM Is the Wizard, Then Code Is the Wand: A Survey on How Code Empowers Large Language Models to Serve as Intelligent Agentscited by 77
  12. 2023Igniting Language Intelligence: The Hitchhiker's Guide From Chain-of-Thought Reasoning to Language Agentscited by 72
  13. 2024AutoDev: Automated AI-Driven Developmentcited by 24
  14. 2023Fixing Rust Compilation Errors using LLMscited by 7
  15. 2023Multi-Level Compositional Reasoning for Interactive Instruction Followingcited by 7

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 8; 2025: 22; 2026: 19.

49 papers.

Sort:

By area:

  1. 2024Agentless: Demystifying LLM-based Software Engineering Agentscited by 400
  2. 2024Agent-as-a-Judge: Evaluate Agents with Agentscited by 223
  3. 2024CodexGraph: Bridging Large Language Models and Code Repositories via Code Graph Databasescited by 62
  4. 2024HyperAgent: Generalist Software Engineering Agents to Solve Coding Tasks at Scalecited by 61
  5. 2024Human-In-the-Loop Software Development Agentscited by 42
  6. 2026A Survey of Agent Memory in the Second Half: Towards Self-Evolving and Long-Horizon Agentscited by 40
  7. 2024TDD-Bench Verified: Can LLMs Generate Tests for Issues Before They Get Resolved?cited by 32
  8. 2025RefactorBench: Evaluating Stateful Reasoning in Language Agents Through Codecited by 28
  9. 2025Process-Centric Analysis of Agentic Software Systemscited by 24
  10. 2025PatchPilot: A Cost-Efficient Software Engineering Agent with Early Attempts on Formal Verificationcited by 22
  11. 2025Large Language Model-based Data Science Agent: A Surveycited by 22
  12. 2025debug-gym: A Text-Based Environment for Interactive Debuggingcited by 19
37 more
  1. 2025Code Researcher: Deep Research Agent for Large Systems Code and Commit Historycited by 19
  2. 2025Understanding Automated Program Repair Agents Through the Lens of Traceability: An Empirical Studycited by 16
  3. 2025A Comprehensive Survey on Benchmarks and Solutions in Software Engineering of LLM-Empowered Agentic Systemcited by 15
  4. 2026Inside the Scaffold: A Source-Code Taxonomy of Coding Agent Architecturescited by 15
  5. 2025Git Context Controller: Manage the Context of LLM-based Agents like Gitcited by 13
  6. 2026Coding Agents are Effective Long-Context Processorscited by 11
  7. 2025Agent That Debugs: Dynamic State-Guided Vulnerability Repaircited by 7
  8. 2025RefAgent: A Multi-agent LLM-based Framework for Automatic Software Refactoringcited by 7
  9. 2025BOAD: Discovering Hierarchical Software Engineering Agents via Bandit Optimizationcited by 7
  10. 2025SWE-Factory: Your Automated Factory for Issue Resolution Training Data and Evaluation Benchmarkscited by 6
  11. 2025Agentic Software Issue Resolution with Large Language Models: A Surveycited by 6
  12. 2026Autonomous Research Agents: A Survey of AI Scientists and the Verification Gapcited by 6
  13. 2025Context Engineering for Multi-Agent LLM Code Assistants Using Elicit, NotebookLM, ChatGPT, and Claude Codecited by 5
  14. 2026What makes a harness a harness: necessary and sufficient conditions for an agent harnesscited by 5
  15. 2025Code Reasoning for Software Engineering Tasks: A Survey and A Call to Actioncited by 4
  16. 2025Investigating Test Overfitting on SWE-benchcited by 4
  17. 2025Agint: Agentic Graph Compilation for Software Engineering Agentscited by 4
  18. 2024SuperCoder2.0: Technical Report on Exploring the feasibility of LLMs as Autonomous Programmercited by 3
  19. 2025Designing LLM-based Multi-Agent Systems for Software Engineering Tasks: Quality Attributes, Design Patterns and Rationalecited by 3
  20. 2025TN-AutoRCA: Benchmark Construction and Agentic Framework for Self-Improving Alarm-Based Root Cause Analysis in Telecommunication Networkscited by 2
  21. 2026From Historical Patches to Repair Plans: Outcome-Conditioned Reasoning for Repository-Level Program Repaircited by 2
  22. 2024PyGen: A Collaborative Human-AI Approach to Python Package Creationcited by 1
  23. 2025COSMIR: Chain Orchestrated Structured Memory for Iterative Reasoning over Long Contextcited by 1
  24. 2025TREAT: A Code LLMs Trustworthiness / Reliability Evaluation and Testing Frameworkcited by 1
  25. 2026Debug2Fix: Can Interactive Debugging Help Coding Agents Fix More Bugs?cited by 1
  26. 2026Resolving Java Code Repository Issues with iSWE Agentcited by 1
  27. 2026A Study on the Impact of Fault localization Granularity for Repository-Scale Code Repair Taskscited by 1
  28. 2026Unlocking Model Potentials Through Adaptive Multi-Agent Scaffolding for Efficient Issue Resolutioncited by 1
  29. 2026Writing Bug Reports for Software Repair Agents: What Information Matters Most?cited by 1
  30. 2026Harness Engineering: Anatomy, Architecture, and Evolution of Coding Agents -- A Source-Code Study of Eleven Systemscited by 1
  31. 2026An Empirical Study of Harness Design for Coding Agentscited by 1
  32. 2026AgenticAKM : Enroute to Agentic Architecture Knowledge Managementcited by 0
  33. 2026MobileDev-Bench: A Benchmark for Issue Resolution in Mobile Application Developmentcited by 0
  34. 2026Multi-Agent LLM Collaboration for Unit Test Generation via Human-Testing-Inspired Workflowscited by 0
  35. 2026Benchmarking the Residual: What Long-Horizon Evaluations Add Beyond Matched Short-Task Performancecited by 0
  36. 2026GxP-Agent: Process-DAG Topology for Reliable Clinical Trial Programming with LLM Agentscited by 0
  37. 2026ExecCritic: Learn to Test, Test to Improve for Coding Agentscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026Developing LLM-based Multi-Agent Systems in Software Engineering: A Mixed-Method Experience Report
  2. 2026Agentic AI in the Software Development Lifecycle: Architecture, Empirical Evidence, and the Reshaping of Software Engineering
  3. 2026Agentic Software: How AI Agents Are Restructuring the Software Paradigm
  4. 2026Reproducible, Explainable, and Effective Evaluations of Agentic AI for Software Engineering
  5. 2024Experimenting with Multi-Agent Software Development: Towards a Unified Platform
  6. 2026SWE-Master: Unleashing the Potential of Software Engineering Agents via Post-Training
  7. 2024Agents in Software Engineering: Survey, Landscape, and Vision
  8. 2024Large Language Model-Based Agents for Software Engineering: A Survey