Confucius Code Agent: An Open-sourced AI Software Engineer at Industrial Scale
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
2025-12-12
Summary
This paper introduces Confucius Code Agent (CCA), a new AI software engineer designed to handle large, complex coding tasks, and the Confucius SDK which it's built on.
What's the problem?
Current AI coding assistants either aren't powerful enough to tackle real-world software engineering projects with huge codebases and long-term tasks, or they work well but are 'black boxes' – meaning it's hard to understand *how* they work, customize them, or trust their results. Existing open-source options lack the power for industrial use, while proprietary systems lack transparency and control.
What's the solution?
The researchers created CCA and the Confucius SDK. The SDK focuses on three key areas: how the agent 'experiences' tasks, how users interact with it, and how developers can extend it. It includes a system for remembering information over long periods, a way to take and use notes, and a flexible system for adding new tools. A 'meta-agent' automatically improves CCA's performance by testing and refining its settings, making it adapt quickly to new challenges.
Why it matters?
CCA and the Confucius SDK represent a step forward in making AI coding assistants more practical and reliable for professional software development. They offer a balance between performance, transparency, and the ability to customize and extend the system, potentially bridging the gap between research prototypes and tools used in real-world software companies.
Abstract
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.