MASAI: Modular Architecture for Software-engineering AI Agents
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866911920762650624 |
|---|---|
| author | Arora, Daman Sonwane, Atharv Wadhwa, Nalin Mehrotra, Abhav Utpala, Saiteja Bairi, Ramakrishna Kanade, Aditya Natarajan, Nagarajan |
| author_facet | Arora, Daman Sonwane, Atharv Wadhwa, Nalin Mehrotra, Abhav Utpala, Saiteja Bairi, Ramakrishna Kanade, Aditya Natarajan, Nagarajan |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2406_11638 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | MASAI: Modular Architecture for Software-engineering AI Agents Arora, Daman Sonwane, Atharv Wadhwa, Nalin Mehrotra, Abhav Utpala, Saiteja Bairi, Ramakrishna Kanade, Aditya Natarajan, Nagarajan Artificial Intelligence Software Engineering 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. |
| title | MASAI: Modular Architecture for Software-engineering AI Agents |
| topic | Artificial Intelligence Software Engineering |
| url | https://arxiv.org/abs/2406.11638 |