Confucius Code Agent: Scalable Agent Scaffolding for Real-World Codebases
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866912870114000896 |
|---|---|
| author | Wong, Sherman Qi, Zhenting Wang, Zhaodong Hu, Nathan Lin, Samuel Ge, Jun Gao, Erwin Chen, Wenlin Du, Yilun Yu, Minlan Zhang, Ying |
| author_facet | Wong, Sherman Qi, Zhenting Wang, Zhaodong Hu, Nathan Lin, Samuel Ge, Jun Gao, Erwin Chen, Wenlin Du, Yilun Yu, Minlan Zhang, Ying |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2512_10398 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Confucius Code Agent: Scalable Agent Scaffolding for Real-World Codebases Wong, Sherman Qi, Zhenting Wang, Zhaodong Hu, Nathan Lin, Samuel Ge, Jun Gao, Erwin Chen, Wenlin Du, Yilun Yu, Minlan Zhang, Ying Computation and Language Artificial Intelligence Machine Learning Software Engineering 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. |
| title | Confucius Code Agent: Scalable Agent Scaffolding for Real-World Codebases |
| topic | Computation and Language Artificial Intelligence Machine Learning Software Engineering |
| url | https://arxiv.org/abs/2512.10398 |