Self-Evolving Multi-Agent Collaboration Networks for Software Development

• URL: http://arxiv.org/abs/2410.16946v1
• Date: Tue, 22 Oct 2024 12:20:23 GMT
• Title: Self-Evolving Multi-Agent Collaboration Networks for Software Development
• Authors: Yue Hu, Yuzhu Cai, Yaxin Du, Xinyu Zhu, Xiangrui Liu, Zijie Yu, Yuchen Hou, Shuo Tang, Siheng Chen,
• Abstract summary: We introduce EvoMAC, a novel self-evolving paradigm for MAC networks. Inspired by traditional neural network training, EvoMAC obtains text-based environmental feedback. We propose rSDE-Bench, a requirement-oriented software development benchmark.
• Score: 32.78667834175446
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: LLM-driven multi-agent collaboration (MAC) systems have demonstrated impressive capabilities in automatic software development at the function level. However, their heavy reliance on human design limits their adaptability to the diverse demands of real-world software development. To address this limitation, we introduce EvoMAC, a novel self-evolving paradigm for MAC networks. Inspired by traditional neural network training, EvoMAC obtains text-based environmental feedback by verifying the MAC network's output against a target proxy and leverages a novel textual backpropagation to update the network. To extend coding capabilities beyond function-level tasks to more challenging software-level development, we further propose rSDE-Bench, a requirement-oriented software development benchmark, which features complex and diverse software requirements along with automatic evaluation of requirement correctness. Our experiments show that: i) The automatic requirement-aware evaluation in rSDE-Bench closely aligns with human evaluations, validating its reliability as a software-level coding benchmark. ii) EvoMAC outperforms previous SOTA methods on both the software-level rSDE-Bench and the function-level HumanEval benchmarks, reflecting its superior coding capabilities. The benchmark can be downloaded at https://yuzhu-cai.github.io/rSDE-Bench/.

Related papers

• WebUIBench: A Comprehensive Benchmark for Evaluating Multimodal Large Language Models in WebUI-to-Code [57.45181837786448]
  Multimodal Large Language Models (MLLMs) have the potential to act as AI software engineers capable of executing complex web application development.<n>Existing benchmarks usually fail to provide an assessment of sub-capabilities and focus solely on webpage generation outcomes.<n>We propose WebUIBench, a benchmark systematically designed to evaluate MLLMs in four key areas: WebUI Perception, HTML Programming,WebUI-HTML Understanding, and WebUI-to-Code.
  arXiv  Detail & Related papers  (2025-06-09T14:46:02Z)
• OSS-UAgent: An Agent-based Usability Evaluation Framework for Open Source Software [47.02288620982592]
  Our framework employs intelligent agents powered by large language models (LLMs) to simulate developers performing programming tasks.<n> OSS-UAgent ensures accurate and context-aware code generation.<n>Our demonstration showcases OSS-UAgent's practical application in evaluating graph analytics platforms.
  arXiv  Detail & Related papers  (2025-05-29T08:40:10Z)
• R&D-Agent: Automating Data-Driven AI Solution Building Through LLM-Powered Automated Research, Development, and Evolution [60.80016554091364]
  R&D-Agent is a dual-agent framework for iterative exploration.<n>The Researcher agent uses performance feedback to generate ideas, while the Developer agent refines code based on error feedback.<n>R&D-Agent is evaluated on MLE-Bench and emerges as the top-performing machine learning engineering agent.
  arXiv  Detail & Related papers  (2025-05-20T06:07:00Z)
• A Path Less Traveled: Reimagining Software Engineering Automation via a Neurosymbolic Paradigm [9.900581015679935]
  We propose Neurosymbolic Software Engineering as a promising paradigm combining neural learning with symbolic (rule-based) reasoning.<n>This hybrid methodology aims to enhance efficiency, reliability, and transparency in AI-driven software engineering.
  arXiv  Detail & Related papers  (2025-05-04T22:10:21Z)
• SEAlign: Alignment Training for Software Engineering Agent [38.05820118124528]
  We propose SEAlign to bridge the gap between code generation models and real-world software development tasks. We evaluate SEAlign on three standard agentic benchmarks for real-world software engineering, including HumanEvalFix, SWE-Bench-Lite, and SWE-Bench-Verified. We develop an agent-based software development platform using SEAlign, which successfully automates the creation of several small applications.
  arXiv  Detail & Related papers  (2025-03-24T08:59:21Z)
• OS-Genesis: Automating GUI Agent Trajectory Construction via Reverse Task Synthesis [55.390060529534644]
  We propose OS-Genesis, a novel data synthesis pipeline for Graphical User Interface (GUI) agents. Instead of relying on pre-defined tasks, OS-Genesis enables agents first to perceive environments and perform step-wise interactions. We demonstrate that training GUI agents with OS-Genesis significantly improves their performance on highly challenging online benchmarks.
  arXiv  Detail & Related papers  (2024-12-27T16:21:58Z)
• Human-In-the-Loop Software Development Agents [12.830816751625829]
  Large Language Models (LLMs) are introduced to automatically resolve software development tasks. We introduce a Human-in-the-loop LLM-based Agents framework (HULA) for software development. We design, implement, and deploy the HULA framework into Atlassian for internal uses.
  arXiv  Detail & Related papers  (2024-11-19T23:22:33Z)
• SWE-Search: Enhancing Software Agents with Monte Carlo Tree Search and Iterative Refinement [18.84439000902905]
  SWE-Search is a multi-agent framework that integrates Monte Carlo Tree Search (MCTS) with a self-improvement mechanism to enhance software agents' performance. This work highlights the potential of self-evaluation driven search techniques to enhance agent reasoning and planning in complex, dynamic software engineering environments.
  arXiv  Detail & Related papers  (2024-10-26T22:45:56Z)
• Contextual Augmented Multi-Model Programming (CAMP): A Hybrid Local-Cloud Copilot Framework [8.28588489551341]
  This paper presents CAMP, a multi-model AI-assisted programming framework that consists of a local model that employs Retrieval-Augmented Generation (RAG) RAG retrieves contextual information from the cloud model to facilitate context-aware prompt construction. The methodology is actualized in Copilot for Xcode, an AI-assisted programming tool crafted for the Apple software ecosystem.
  arXiv  Detail & Related papers  (2024-10-20T04:51:24Z)
• Codev-Bench: How Do LLMs Understand Developer-Centric Code Completion? [60.84912551069379]
  We present the Code-Development Benchmark (Codev-Bench), a fine-grained, real-world, repository-level, and developer-centric evaluation framework. Codev-Agent is an agent-based system that automates repository crawling, constructs execution environments, extracts dynamic calling chains from existing unit tests, and generates new test samples to avoid data leakage.
  arXiv  Detail & Related papers  (2024-10-02T09:11:10Z)
• Agent-Driven Automatic Software Improvement [55.2480439325792]
  This research proposal aims to explore innovative solutions by focusing on the deployment of agents powered by Large Language Models (LLMs) The iterative nature of agents, which allows for continuous learning and adaptation, can help surpass common challenges in code generation. We aim to use the iterative feedback in these systems to further fine-tune the LLMs underlying the agents, becoming better aligned to the task of automated software improvement.
  arXiv  Detail & Related papers  (2024-06-24T15:45:22Z)
• SOEN-101: Code Generation by Emulating Software Process Models Using Large Language Model Agents [50.82665351100067]
  FlowGen is a code generation framework that emulates software process models based on multiple Large Language Model (LLM) agents. We evaluate FlowGenScrum on four benchmarks: HumanEval, HumanEval-ET, MBPP, and MBPP-ET.
  arXiv  Detail & Related papers  (2024-03-23T14:04:48Z)
• Self-evolving Autoencoder Embedded Q-Network [9.414875682358085]
  We propose SAQN, a self-evolving autoencoder embedded with a Q-Network. In SAQN, the autoencoder architecture adapts and evolves as the agent explores the environment. We show that the proposed SAQN significantly outperforms state-of-the-art counterparts.
  arXiv  Detail & Related papers  (2024-02-18T14:42:47Z)
• CodeRL: Mastering Code Generation through Pretrained Models and Deep Reinforcement Learning [92.36705236706678]
  "CodeRL" is a new framework for program synthesis tasks through pretrained LMs and deep reinforcement learning. During inference, we introduce a new generation procedure with a critical sampling strategy. For the model backbones, we extended the encoder-decoder architecture of CodeT5 with enhanced learning objectives.
  arXiv  Detail & Related papers  (2022-07-05T02:42:15Z)
• QTRAN++: Improved Value Transformation for Cooperative Multi-Agent Reinforcement Learning [70.382101956278]
  QTRAN is a reinforcement learning algorithm capable of learning the largest class of joint-action value functions. Despite its strong theoretical guarantee, it has shown poor empirical performance in complex environments. We propose a substantially improved version, coined QTRAN++.
  arXiv  Detail & Related papers  (2020-06-22T05:08:36Z)

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

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.