Related papers: MASAI: Modular Architecture for Software-engineering AI Agents

MASAI: Modular Architecture for Software-engineering AI Agents

URL: http://arxiv.org/abs/2406.11638v1
Date: Mon, 17 Jun 2024 15:19:51 GMT
Title: MASAI: Modular Architecture for Software-engineering AI Agents
Authors: Daman Arora, Atharv Sonwane, Nalin Wadhwa, Abhav Mehrotra, Saiteja Utpala, Ramakrishna Bairi, Aditya Kanade, Nagarajan Natarajan,
Abstract summary: A common method to solve complex problems in software engineering, is to divide the problem into multiple sub-problems. 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.
Score: 7.289893771424848
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Abstract: 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.

Related papers

Diversity Empowers Intelligence: Integrating Expertise of Software Engineering Agents [106.87436596397816]
Large language model (LLM) agents have shown great potential in solving real-world software engineering (SWE) problems. We propose DEI (Diversity Empowered Intelligence), a framework that leverages their unique expertise. Experiments show that a DEI-guided committee of agents is able to surpass the best individual agent's performance by a large margin.
arXiv Detail & Related papers (2024-08-13T17:50:28Z)
Scalable Mechanism Design for Multi-Agent Path Finding [87.40027406028425]
Multi-Agent Path Finding (MAPF) involves determining paths for multiple agents to travel simultaneously and collision-free through a shared area toward given goal locations. Finding an optimal solution is often computationally infeasible, making the use of approximate, suboptimal algorithms essential. We introduce the problem of scalable mechanism design for MAPF and propose three strategyproof mechanisms, two of which even use approximate MAPF algorithms.
arXiv Detail & Related papers (2024-01-30T14:26:04Z)
Pangu-Agent: A Fine-Tunable Generalist Agent with Structured Reasoning [50.47568731994238]
Key method for creating Artificial Intelligence (AI) agents is Reinforcement Learning (RL) This paper presents a general framework model for integrating and learning structured reasoning into AI agents' policies.
arXiv Detail & Related papers (2023-12-22T17:57:57Z)
MechAgents: Large language model multi-agent collaborations can solve mechanics problems, generate new data, and integrate knowledge [0.6708125191843434]
A set of AI agents can solve mechanics tasks, here demonstrated for elasticity problems, via autonomous collaborations. A two-agent team can effectively write, execute and self-correct code, in order to apply finite element methods to solve classical elasticity problems. For more complex tasks, we construct a larger group of agents with enhanced division of labor among planning, formulating, coding, executing and criticizing the process and results.
arXiv Detail & Related papers (2023-11-14T13:49:03Z)
Agent Lumos: Unified and Modular Training for Open-Source Language Agents [89.78556964988852]
We introduce LUMOS, one of the first frameworks for training open-source LLM-based agents. LUMOS features a learnable, unified, and modular architecture with a planning module that learns high-level subgoal generation. We collect large-scale, unified, and high-quality training annotations derived from diverse ground-truth reasoning rationales.
arXiv Detail & Related papers (2023-11-09T00:30:13Z)
OpenAGI: When LLM Meets Domain Experts [51.86179657467822]
Human Intelligence (HI) excels at combining basic skills to solve complex tasks. This capability is vital for Artificial Intelligence (AI) and should be embedded in comprehensive AI Agents. We introduce OpenAGI, an open-source platform designed for solving multi-step, real-world tasks.
arXiv Detail & Related papers (2023-04-10T03:55:35Z)
Multi-Agent Reinforcement Learning for Microprocessor Design Space Exploration [71.95914457415624]
Microprocessor architects are increasingly resorting to domain-specific customization in the quest for high-performance and energy-efficiency. We propose an alternative formulation that leverages Multi-Agent RL (MARL) to tackle this problem. Our evaluation shows that the MARL formulation consistently outperforms single-agent RL baselines.
arXiv Detail & Related papers (2022-11-29T17:10:24Z)
Compilation-based Solvers for Multi-Agent Path Finding: a Survey, Discussion, and Future Opportunities [7.766921168069532]
We show the lessons learned from past developments and current trends in the topic and discuss its wider impact. Two major approaches to optimal MAPF solving include (1) dedicated search-based methods, which solve MAPF directly, and (2) compilation-based methods that reduce a MAPF instance to an instance in a different well established formalism.
arXiv Detail & Related papers (2021-04-23T20:13:12Z)

This list is automatically generated from the titles and abstracts of the papers in this site.