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

2025-12-11

AI Summary

Current open-source coding agents lack the robustness required for industrial-scale software engineering tasks, while proprietary solutions suffer from limitations in scalability, interpretability, and controllability. To address these challenges, this paper introduces the first open-source AI coding engineer designed specifically for industrial-grade software development. Our approach features: (1) a hierarchical working memory and persistent notebook system enabling ultra-long-context reasoning and cross-session continual learning; (2) a meta-agent–driven closed loop for automatic configuration synthesis, evaluation, and optimization; and (3) a scalable architecture built upon the Confucius SDK—comprising a unified orchestrator, modular framework, and tri-perspective design (AX/UX/DX). Evaluated on SWE-Bench-Pro, our agent achieves 54.3% Resolve@1, establishing a new state-of-the-art among open-source coding agents. This work provides a foundational, interpretable, reproducible, and production-deployable framework for industrial AI coding assistants.

Technology Category

• Cognitive Modeling & Cognitive Systems: Agent Architectures
• Natural Language Processing: Code Generation / Program Synthesis from Natural Language
• Multiagent Systems: Agent/AI Theories and Architectures

Application Category

• Search and Retrieval-Augmented AI: Agentic search
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

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.

Problem

• Develops an open-source AI software engineer for industrial-scale coding tasks
• Addresses limitations of existing agents in handling large repositories and long sessions
• Enhances toolchain coordination and memory for real-world software engineering

Innovation

• Hierarchical memory for long-context reasoning
• Persistent note-taking for cross-session learning
• Meta-agent automates configuration synthesis and refinement