打造可扩展的代码代理，让AI在真实大型项目中持续高效协作。
Confucius Code Agent: Scalable Agent Scaffolding for Real-World Codebases
- 基于三重体验框架构建统一代理平台，支持长上下文与跨会话学习。
- 在SWE-Bench-Pro上达成59%修复率，超越研究与商用基准。
- 自动生成与优化代理，适合快速部署到新任务与工具链。
真实世界软件工程任务需要能在大规模代码库中运行、维持长时会话并可靠协调复杂工具链的编码代理。现有研究级编码代理虽透明但难以扩展至生产级负载，而生产级系统虽性能强，却缺乏可扩展性、可解释性和可控性。我们提出Confucius Code Agent（CCA），一个可在大规模代码库中运行的软件工程代理。CCA基于Confucius SDK，该平台围绕三个互补视角构建：代理体验（AX）、用户体验（UX）与开发者体验（DX）。SDK提供统一编排器，支持长上下文推理；持久化笔记系统实现跨会话持续学习；模块化扩展系统保障工具可靠使用。此外，我们引入元代理，通过构建-测试-改进循环自动化代理的构建、评估与优化，实现新任务与工具栈的快速代理开发。在相同代码库、模型后端和工具访问条件下，基于元代理在Confucius SDK上实例化的CCA在SWE-Bench-Pro上达到59%的Resolve@1，优于先前研究基线及商业结果。
原文摘要 · Abstract (English)
Real-world software engineering tasks require coding agents that can operate on massive repositories, sustain long-horizon sessions, and reliably coordinate complex toolchains at test time. Existing research-grade coding agents offer transparency but struggle when scaled to heavier, production-level workloads, while production-grade systems achieve strong practical performance but provide limited extensibility, interpretability, and controllability. We introduce the Confucius Code Agent (CCA), a software engineering agent that can operate at large-scale codebases. CCA is built on top of the Confucius SDK, an agent development platform structured around three complementary perspectives: Agent Experience (AX), User Experience (UX), and Developer Experience (DX). The SDK supports a unified orchestrator with advanced context management for long-context reasoning, a persistent note-taking system for cross-session continual learning, and a modular extension system for reliable tool use. In addition, we introduce a meta-agent that automates the construction, evaluation, and refinement of agents through a build-test-improve cycle, enabling rapid agent development on new tasks and tool stacks. Instantiated on the Confucius SDK using the meta-agent, CCA demonstrates strong performance on real-world software engineering tasks. On SWE-Bench-Pro, CCA achieves a Resolve@1 of 59%, exceeding prior research baselines as well as commercial results, under identical repositories, model backends, and tool access.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。