ChatPaper.aiChatPaper

孔子代码代理:工业级开源人工智能软件工程师

Confucius Code Agent: An Open-sourced AI Software Engineer at Industrial Scale

December 11, 2025
作者: Zhaodong Wang, Zhenting Qi, Sherman Wong, Nathan Hu, Samuel Lin, Jun Ge, Erwin Gao, Yining Yang, Ben Maurer, Wenlin Chen, David Recordon, Yilun Du, Minlan Yu, Ying Zhang
cs.AI

摘要

现实世界的人工智能软件工程需要编码智能体具备以下能力:在大规模代码库中进行推理、在长会话期间保持持久记忆、在测试阶段稳健协调复杂工具链。现有开源编码智能体虽具透明度,但在应对工业级工作负载时往往力有不逮;而专有编码智能体虽实践性能强劲,却在可扩展性、可解释性与可控性方面存在局限。我们推出孔子编码智能体(CCA),这是一款能在工业级规模运行的开源AI软件工程师。CCA构建于孔子SDK之上——该开源智能体开发平台围绕三个互补维度设计:智能体体验(AX)、用户体验(UX)和开发者体验(DX)。该SDK引入了具备分层工作记忆的统一编排器以实现长上下文推理,配备持久化笔记系统支持跨会话持续学习,并通过模块化扩展机制保障工具使用的稳健性。此外,元智能体通过"构建-测试-优化"循环自动完成智能体配置的合成、评估与优化,使其能快速适应新任务、新环境和新工具栈。基于孔子SDK这些机制实例化的CCA在真实软件工程任务中表现出色:在SWE-Bench-Pro基准测试中,CCA以54.3%的Resolve@1成绩刷新业界纪录,较现有编码智能体实现显著提升。孔子SDK与CCA共同为AI智能体提供了透明、可扩展、可复现的基础框架,弥合了研究原型与生产级系统之间的鸿沟,为工业级规模的智能体开发与部署提供支撑。
English
Real-world AI software engineering demands coding agents that can reason over massive repositories, maintain durable memory across and within long sessions, and robustly coordinate complex toolchains at test time. Existing open-source coding agents provide transparency but frequently fall short when pushed to these industrial-scale workloads, while proprietary coding agents offer strong practical performance but limited extensibility, interpretability, and controllability. We present the Confucius Code Agent (CCA), an open-sourced AI software engineer that can operate at an industrial scale. CCA is built atop the Confucius SDK, an open-sourced agent development platform designed around three complementary perspectives: Agent Experience (AX), User Experience (UX), and Developer Experience (DX). The SDK introduces a unified orchestrator with hierarchical working memory for long-context reasoning, a persistent note-taking system for cross-session continual learning, and a modular extension module for robust tool use. Moreover, a meta-agent automates the synthesis, evaluation, and refinement of agent configurations through a build-test-improve loop, enabling rapid agent development on new tasks, environments, and tool stacks. Instantiated on Confucius SDK with these mechanisms, CCA delivers strong performance on real-world software engineering tasks. On SWE-Bench-Pro, CCA achieves a state-of-the-art Resolve@1 performance of 54.3%, substantially improving over prior coding agents. Together, the Confucius SDK and CCA provide a transparent, extensible, and reproducible foundation for AI agents, bridge gaps between research prototypes and production-grade systems, and support agent development and deployment at industrial scale.
PDF21December 13, 2025