Software development is a complex task that demands cooperation among agents with diverse roles. Large language models (LLMs) have enabled autonomous multi-agent software development frameworks that leverage role-based collaboration to automate requirements analysis, coding, testing, and refinement. However, existing approaches typically assume that intermediate agent outputs are equally reliable, leaving them vulnerable to hallucination propagation, where incorrect decisions generated in early development phases are transferred to downstream agents and negatively impact final software quality. To address this challenge, we propose UA-ChatDev, an uncertainty-aware multi-agent software development framework that integrates uncertainty quantification into agent interactions. It introduces a lightweight uncertainty estimation mechanism based on token-level log probabilities to assess the confidence of agent responses and employs phase-aware threshold calibration to selectively trigger retrieval-based verification when uncertainty exceeds acceptable levels. Extensive experiments on the SRDD benchmark demonstrate that UA-ChatDev consistently outperforms existing single-agent and multi-agent software development frameworks across completeness, executability, consistency, and overall quality metrics. Further ablation studies and communication analyses verify that uncertainty-aware interactions enhance code execution reliability.
Multi-Agent Collaboration via Evolving Orchestration
Tsinghua University(清华大学);Shanghai Jiao Tong University(上海交通大学);Beijing University of Posts and Telecommunications(北京邮电大学);Siemens(西门子);Tencent Robotics X(腾讯机器人研究院)
Multi-Agent Collaboration via Cross-Team Orchestration
State Key Lab of CAD & CG(CAD与CG国家重点实验室);Zhejiang Polytechnic Institute(浙江工业大学);Polytechnic Institute, Zhejiang University(浙江大学 polytechnic 院);Shanghai Jiao Tong University(上海交通大学);King’s College London(伦敦国王学院);Tsinghua University(清华大学);Beijing University of Posts and Telecommunications(北京邮电大学);Tencent Robotics X(腾讯机器人科技)
Co-Saving: Resource Aware Multi-Agent Collaboration for Software Development
Tsinghua University(清华大学);Shanghai Jiao Tong University(上海交通大学);Beijing University of Posts and Telecommunications(北京邮电大学);Siemens(西门子);Tencent Robotics X(腾讯机器人院)
AsynCodeBench: Benchmarking Collaboration of Asynchronous Multi-Agent Systems in Software Engineering
University of Houston(休斯顿大学);New York University(纽约大学);Texas A&M University(德克萨斯农工大学);UCSD(加州大学圣地亚哥分校);Worcester Polytechnic Institute(伍斯特理工学院);Oregon State University(俄勒冈州立大学)
How Developers Interact with AI: A Taxonomy of Human-AI Collaboration in Software Engineering
School of Computing and Information Systems(计算与信息系统学院);Singapore Management University(新加坡管理大学);School of Informatics, Computing, and Cyber Systems(信息学、计算与网络系统学院);Northern Arizona University(北亚利桑那大学)
The Role of Generative AI in Software Student CollaborAItion
Nuremberg Tech(纽伦堡技术大学);University of Toronto(多伦多大学);Aalto University(阿尔托大学);University of California, Berkeley(加利福尼亚大学伯克利分校);Temple University(天普大学);University of Jyväskylä(于韦斯屈莱大学)
Engineering Signals of Human-AI Collaboration in the Agentic Coding Era: A Longitudinal Analysis of 33,228 Pull Requests from vLLM and SGLang with Implications for Biomedical AI Agents and Bioinformatics Pipeline Developmen