arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2412.01992cs.HCcs.AI
收藏

ChatCollab:探索软件团队中人类与 AI 智能体之间的协作

ChatCollab: Exploring Collaboration Between Humans and AI Agents in Software Teams

Stanford University(斯坦福大学)

Benjamin Klieger, Charis Charitsis, Miroslav Suzara, Sierra Wang, Nick Haber, John C. Mitchell

AI总结:

提出 ChatCollab 框架,支持人类与 AI 智能体以同伴身份在 Slack 中承担不同角色协作,并通过软件开发实验和自动化协作动态分析验证其有效性。

摘要:

我们通过提出并初步测试一个通用框架,探索人类与人工智能(AI)之间开展富有成效的团队协作的潜力;该框架使多个人类与 AI 智能体能够作为同伴共同工作。ChatCollab 的新颖架构允许智能体——无论是人类还是 AI——以任意角色加入协作,在 Slack 中自主参与任务和沟通,并且无需知晓协作者是人类还是 AI。以软件工程作为案例研究,我们发现 AI 智能体能够成功识别自身角色与职责,与其他智能体协调,并在继续之前等待所请求的输入或交付物。相对于此前三个用于软件开发的多智能体 AI 系统,我们发现 ChatCollab AI 智能体在一项交互式游戏开发任务中产出了相当或更好的软件。我们还提出了一种用于分析协作动态的自动化方法,该方法能有效识别具有不同角色的智能体的行为特征,使我们能够在一系列实验条件下定量比较协作动态。例如,在比较 ChatCollab AI 智能体时,我们发现 AI CEO 智能体提供建议的频率通常是 AI 产品经理或 AI 开发者的 2 至 4 倍,这表明 ChatCollab 中的智能体能够有意义地承担差异化的协作角色。我们的代码和数据可在 https://github.com/ChatCollab 获取。

英文摘要:

We explore the potential for productive team-based collaboration between humans and Artificial Intelligence (AI) by presenting and conducting initial tests with a general framework that enables multiple human and AI agents to work together as peers. ChatCollab's novel architecture allows agents - human or AI - to join collaborations in any role, autonomously engage in tasks and communication within Slack, and remain agnostic to whether their collaborators are human or AI. Using software engineering as a case study, we find that our AI agents successfully identify their roles and responsibilities, coordinate with other agents, and await requested inputs or deliverables before proceeding. In relation to three prior multi-agent AI systems for software development, we find ChatCollab AI agents produce comparable or better software in an interactive game development task. We also propose an automated method for analyzing collaboration dynamics that effectively identifies behavioral characteristics of agents with distinct roles, allowing us to quantitatively compare collaboration dynamics in a range of experimental conditions. For example, in comparing ChatCollab AI agents, we find that an AI CEO agent generally provides suggestions 2-4 times more often than an AI product manager or AI developer, suggesting agents within ChatCollab can meaningfully adopt differentiated collaborative roles. Our code and data can be found at: https://github.com/ChatCollab.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑