HackerPapers

arXiv:2307.07924cs.SE

ChatDev: Communicative Agents for Software Development

Chen Qian, Wei Liu, Hongzhang Liu, Nuo Chen, Yufan Dang, Jiahao Li, Cheng Yang, Weize Chen, Yusheng Su, Xin Cong, Juyuan Xu, Dahai Li, Zhiyuan Liu, Maosong Sun

Abstract

Software development is a complex task that necessitates cooperation among multiple members with diverse skills. Numerous studies used deep learning to improve specific phases in a waterfall model, such as design, coding, and testing. However, the deep learning model in each phase requires unique designs, leading to technical inconsistencies across various phases, which results in a fragmented and ineffective development process. In this paper, we introduce ChatDev, a chat-powered software development framework in which specialized agents driven by large language models (LLMs) are guided in what to communicate (via chat chain) and how to communicate (via communicative dehallucination). These agents actively contribute to the design, coding, and testing phases through unified language-based communication, with solutions derived from their multi-turn dialogues. We found their utilization of natural language is advantageous for system design, and communicating in programming language proves helpful in debugging. This paradigm demonstrates how linguistic communication facilitates multi-agent collaboration, establishing language as a unifying bridge for autonomous task-solving among LLM agents. The code and data are available at https://github.com/OpenBMB/ChatDev.

arXiv comments
Accepted to ACL 2024; https://github.com/OpenBMB/ChatDev
Journal reference
DOI
Subjects
cs.SESoftware Engineering cs.CLComputation and Language cs.MAMultiagent Systems

On Hacker News

Linked by 5 identifiable commenters in 10 comments across 9 threads, from Aug 2023 to May 2025. Found in 4 HN submissions from Jul 2023 to Oct 2023. Open submission discussions.

Comments linking this paper, per year.

Discussed in comments9 threads

  1. Jules: An asynchronous coding agent 1 comment

    • This has been proposed/exlored in 2023 already: ChatDev: Communicative Agents for Software Development - https://arxiv.org/abs/2307.07924

      PhilippGilleView on HNParent context

  2. GPT-4 vision prompt injection 1 comment

    • >The ChatGPT "AI" isn't an autonomous thinker performing its own actions based on reasoning of what's fed to it. Yes it is. Or it very well could be. Agency is trivial to implement in LLMs. https://github.com/microsoft/autogen https://arxiv.org/abs/2307.07924 The intelligence…

      famouswafflesView on HNParent context

  3. Autogen: Enable next-gen large language model applications 1 comment

    • https://arxiv.org/abs/2307.07924 at the very least, you can get things done that would be extremely difficult or practically impossible to do with a single instance.

      famouswafflesView on HNParent context

  4. LLMs can't self-correct in reasoning tasks, DeepMind study finds 1 comment

    • Not to discount your experience, I would just like to flag that your conclusion does not quite follow from the premises. I don't believe that there's anything inherent about LLMs that would make one incapable of recognizing the falsity of an argument made by another LLM. Rather…

      falcor84View on HNParent context

  5. OpenAI’s ChatGPT Is the Whole Game Studio [video] 1 comment

    • I mean, it's just a clickbait video. The research paper [0] is cool and all, I just wish we didn't have these hyperbolic clickbait titles like "OpenAI’s ChatGPT Makes A Game For $1!" - we really are in a bubble. [0] https://arxiv.org/abs/2307.07924

      loveparadeView on HNParent context

  6. AI chatbots were tasked to run a tech company 1 comment
  7. Google Meet’s new AI will be able to go to meetings for you 1 comment

    • AI taking to AI to do things is not necessarily an exercise in futility. This paper used 3.5, not even 4 and is basically a couple AI agents collaborating to create software. https://arxiv.org/abs/2307.07924 This is another example at multi AI agent collaboration.…

      famouswafflesView on HNParent context

  8. Generative Agents: Interactive Simulacra of Human Behavior, Now Open Source 1 comment

    • >The lack of effectiveness and usefulness of these agents has been shown time and over. Has it ? https://arxiv.org/abs/2307.07924 https://arxiv.org/abs/2307.02485 The first one doesn't even use GPT-4

      famouswafflesView on HNParent context

  9. MetaGPT: Meta Programming for Multi-Agent Collaborative Framework 2 comments

    • Papers that try to implement a multi agent system https://arxiv.org/abs/2307.07924 https://arxiv.org/abs/2307.02485

      famouswafflesView on HNParent context

    • It's more than just a react loop but i think there's promising research in multi gent cooperation. Notice the first doesn't even use GPT-4. https://arxiv.org/abs/2307.07924 https://arxiv.org/abs/2307.02485

      famouswafflesView on HNParent context

Submitted to Hacker News

Connected through shared HN threads, not inferred similarity or a recommendation.