# MASAI: Modular Architecture for Software-engineering AI Agents

arXiv: https://arxiv.org/abs/2406.11638 · HTML: https://mlsanity.com/paper/2406.11638/

## Key facts

- Cited by 49 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 28 of its 44 references that are in the map.
- First posted on arXiv 17 Jun 2024.

## Placed in

- LLM agents and tool use / [Software engineering coding agents](https://mlsanity.com/agents/software-engineering-coding-agents/)

## Builds on (most cited first, 28 of 28)

- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Evaluating Large Language Models Trained on Code](https://mlsanity.com/paper/2107.03374/) (2021)
- [Large Language Models are Zero-Shot Reasoners](https://mlsanity.com/paper/2205.11916/) (2022)
- [Reflexion: Language Agents with Verbal Reinforcement Learning](https://mlsanity.com/paper/2303.11366/) (2023)
- [Toolformer: Language Models Can Teach Themselves to Use Tools](https://mlsanity.com/paper/2302.04761/) (2023)
- [SWE-bench: Can Language Models Resolve Real-World GitHub Issues?](https://mlsanity.com/paper/2310.06770/) (2023)
- [Tree of Thoughts: Deliberate Problem Solving with Large Language Models](https://mlsanity.com/paper/2305.10601/) (2023)
- [Code Llama: Open Foundation Models for Code](https://mlsanity.com/paper/2308.12950/) (2023)
- [MetaGPT: Meta Programming for A Multi-Agent Collaborative Framework](https://mlsanity.com/paper/2308.00352/) (2023)
- [Gorilla: Large Language Model Connected with Massive APIs](https://mlsanity.com/paper/2305.15334/) (2023)
- [Language Models as Zero-Shot Planners: Extracting Actionable Knowledge for Embodied Agents](https://mlsanity.com/paper/2201.07207/) (2022)
- [Large Language Models Can Be Easily Distracted by Irrelevant Context](https://mlsanity.com/paper/2302.00093/) (2023)
- [Large Language Model based Multi-Agents: A Survey of Progress and Challenges](https://mlsanity.com/paper/2402.01680/) (2024)
- [AgentVerse: Facilitating Multi-Agent Collaboration and Exploring Emergent Behaviors](https://mlsanity.com/paper/2308.10848/) (2023)
- [Language Agent Tree Search Unifies Reasoning Acting and Planning in Language Models](https://mlsanity.com/paper/2310.04406/) (2023)
- [Executable Code Actions Elicit Better LLM Agents](https://mlsanity.com/paper/2402.01030/) (2024)
- [AutoCodeRover: Autonomous Program Improvement](https://mlsanity.com/paper/2404.05427/) (2024)
- [SwiftSage: A Generative Agent with Fast and Slow Thinking for Complex Interactive Tasks](https://mlsanity.com/paper/2305.17390/) (2023)
- [CodePlan: Repository-level Coding using LLMs and Planning](https://mlsanity.com/paper/2309.12499/) (2023)
- [Code Generation with AlphaCodium: From Prompt Engineering to Flow Engineering](https://mlsanity.com/paper/2401.08500/) (2024)
- [CodeR: Issue Resolving with Multi-Agent and Task Graphs](https://mlsanity.com/paper/2406.01304/) (2024)
- [If LLM Is the Wizard, Then Code Is the Wand: A Survey on How Code Empowers Large Language Models to Serve as Intelligent Agents](https://mlsanity.com/paper/2401.00812/) (2024)
- [Igniting Language Intelligence: The Hitchhiker's Guide From Chain-of-Thought Reasoning to Language Agents](https://mlsanity.com/paper/2311.11797/) (2023)
- [AutoDev: Automated AI-Driven Development](https://mlsanity.com/paper/2403.08299/) (2024)
- [Fixing Rust Compilation Errors using LLMs](https://mlsanity.com/paper/2308.05177/) (2023)
- [Multi-Level Compositional Reasoning for Interactive Instruction Following](https://mlsanity.com/paper/2308.09387/) (2023)

## Built on by (most cited first, 30 of 49)

- [Agentless: Demystifying LLM-based Software Engineering Agents](https://mlsanity.com/paper/2407.01489/) (2024)
- [Agent-as-a-Judge: Evaluate Agents with Agents](https://mlsanity.com/paper/2410.10934/) (2024)
- [CodexGraph: Bridging Large Language Models and Code Repositories via Code Graph Databases](https://mlsanity.com/paper/2408.03910/) (2024)
- [HyperAgent: Generalist Software Engineering Agents to Solve Coding Tasks at Scale](https://mlsanity.com/paper/2409.16299/) (2024)
- [A Survey of Agent Memory in the Second Half: Towards Self-Evolving and Long-Horizon Agents](https://mlsanity.com/paper/2602.06052/) (2026)
- [Human-In-the-Loop Software Development Agents](https://mlsanity.com/paper/2411.12924/) (2024)
- [TDD-Bench Verified: Can LLMs Generate Tests for Issues Before They Get Resolved?](https://mlsanity.com/paper/2412.02883/) (2024)
- [RefactorBench: Evaluating Stateful Reasoning in Language Agents Through Code](https://mlsanity.com/paper/2503.07832/) (2025)
- [Process-Centric Analysis of Agentic Software Systems](https://mlsanity.com/paper/2512.02393/) (2025)
- [Large Language Model-based Data Science Agent: A Survey](https://mlsanity.com/paper/2508.02744/) (2025)
- [PatchPilot: A Cost-Efficient Software Engineering Agent with Early Attempts on Formal Verification](https://mlsanity.com/paper/2502.02747/) (2025)
- [Code Researcher: Deep Research Agent for Large Systems Code and Commit History](https://mlsanity.com/paper/2506.11060/) (2025)
- [debug-gym: A Text-Based Environment for Interactive Debugging](https://mlsanity.com/paper/2503.21557/) (2025)
- [Inside the Scaffold: A Source-Code Taxonomy of Coding Agent Architectures](https://mlsanity.com/paper/2604.03515/) (2026)
- [Understanding Automated Program Repair Agents Through the Lens of Traceability: An Empirical Study](https://mlsanity.com/paper/2506.08311/) (2025)
- [Git Context Controller: Manage the Context of LLM-based Agents like Git](https://mlsanity.com/paper/2508.00031/) (2025)
- [A Comprehensive Survey on Benchmarks and Solutions in Software Engineering of LLM-Empowered Agentic System](https://mlsanity.com/paper/2510.09721/) (2025)
- [Coding Agents are Effective Long-Context Processors](https://mlsanity.com/paper/2603.20432/) (2026)
- [Autonomous Research Agents: A Survey of AI Scientists and the Verification Gap](https://mlsanity.com/paper/2608.05179/) (2026)
- [RefAgent: A Multi-agent LLM-based Framework for Automatic Software Refactoring](https://mlsanity.com/paper/2511.03153/) (2025)
- [Agent That Debugs: Dynamic State-Guided Vulnerability Repair](https://mlsanity.com/paper/2504.07634/) (2025)
- [SWE-Factory: Your Automated Factory for Issue Resolution Training Data and Evaluation Benchmarks](https://mlsanity.com/paper/2506.10954/) (2025)
- [BOAD: Discovering Hierarchical Software Engineering Agents via Bandit Optimization](https://mlsanity.com/paper/2512.23631/) (2025)
- [Investigating Test Overfitting on SWE-bench](https://mlsanity.com/paper/2511.16858/) (2025)
- [Agentic Software Issue Resolution with Large Language Models: A Survey](https://mlsanity.com/paper/2512.22256/) (2025)
- [What makes a harness a harness: necessary and sufficient conditions for an agent harness](https://mlsanity.com/paper/2606.10106/) (2026)
- [Harness Engineering: Anatomy, Architecture, and Evolution of Coding Agents -- A Source-Code Study of Eleven Systems](https://mlsanity.com/paper/2609.00006/) (2026)
- [An Empirical Study of Harness Design for Coding Agents](https://mlsanity.com/paper/2609.20804/) (2026)
- [Context Engineering for Multi-Agent LLM Code Assistants Using Elicit, NotebookLM, ChatGPT, and Claude Code](https://mlsanity.com/paper/2508.08322/) (2025)
- [Code Reasoning for Software Engineering Tasks: A Survey and A Call to Action](https://mlsanity.com/paper/2506.13932/) (2025)

## 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.