ChatDev: Communicative Agents for Software Development

By Cheng Qian, Wei Liu, Hongzhang Liu, Nuo Chen, Yufan Dang, Jiahao Li, Cheng Yang, Weize Chen, Yusheng Su, Xin Cong and 4 more. Annual Meeting of the Association for Computational Linguistics, 2023

988 citations recorded by the source corpus.

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.

Subfields: Artificial Intelligence, Management Information Systems

View Paper: https://www.semanticscholar.org/paper/9474b463654fd92a62c103b21f95aed94b087907

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Nian Li
2. Fengli Xu
3. Yong Li
4. Chen Gao

Citations in the corpus

• Why Do Multi-Agent LLM Systems Fail? (2025, neutral): “Building on this characteristic, multi-agent systems are increasingly explored in various domains, such as software engineering (Qian et al., 2023; Wang et al., 2024d), drug discoveries (Gottweis et al., 2025; Swanson et al., 2024), scientific simulations (Park et al., 2023b), and general-purpose…”
• AI Agents vs. Agentic AI: A Conceptual Taxonomy, Applications and Challenges (2025, neutral): “A set of basic distinctions between AI Agents and Agentic AI systems, particularly in terms of scope, autonomy, architectural composition, coordination strategy, and operational complexity, are synthesized in Table I, which was derived from close analysis of prominent frameworks such as Au-toGen…”
• Large language models empowered agent-based modeling and simulation: a survey and perspectives (2023, positive): “CHATDEV (Qian et al., 2024) is a virtual software development company where LLM Agents collaborate to develop computer software, with different roles for agents including CEO, CTO, designers, and programmers.”
• Multi-Agent Collaboration Mechanisms: A Survey of LLMs (2025, positive): “[ ChatDev NLG • Employs a chat chain to break each phase into smaller subtasks, enabling multi-turn communication among agents to collaboratively develop solutions.”
• Harnessing the Wisdom of LLM Crowds through Complementarity-Driven Iterative Collaboration (2026, unknown): “For manually designed MAS, human experts predefine clear role divisions and collaboration workflows based on specific task properties and domain knowledge (Xiong et al. 2023, Hong et al. 2024, Qian et al. 2024).”
• Multi-View Encoders for Performance Prediction in LLM-Based Agentic Workflows (2025, unknown): “Rather than manually designing a fixed workflow (Qian et al., 2024; Chen et al., 2024; Du et al., 2024) or paying repeated inference costs to synthesize one per query (Zhuge et al., 2024; Liu et al., 2024b), Agen-tic Predictor presents a lightweight performance predictor to rapidly estimate the…”