paper-with-me

홈 › Papers

Confucius Code Agent: Scalable Agent Scaffolding for Real-World Codebases

2025-12-11 · Sherman Wong, Zhenting Qi, Zhaodong Wang, Nathan Hu, Samuel Lin, Jun Ge, Erwin Gao, Wenlin Chen, Yilun Du, Minlan Yu, Ying Zhang arxiv

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.

📄 PDF Abstract BibTeX arXiv:2512.10398

Code (0)

등록된 구현이 없습니다.

Tasks

Continual Learning

Similar Papers 제목 키워드 기반

Don't Blame the Large Language Model: How Scaffolding Evolution Shapes Coding Agent Quality

2026-07-04 · Oussama Ben Sghaier, Hao Li, Bram Adams, Ahmed E. Hassan arxiv

Coding agents, autonomous systems that use large language models (LLMs) to resolve software engineering tasks, rely on agentic scaffolding: a middleware layer in between a developer and a large language model that orches…

Steerability via constraints: a substrate for scalable oversight of coding agents

2026-07-02 · Thomas Winninger arxiv

Coding agents are capable; human oversight is the bottleneck. Unconstrained agents introduce security risks, erode codebase scalability, and make human review increasingly costly. We argue that the same methods used for …

Reliable Weak-to-Strong Monitoring of LLM Agents

2025-08-26 · Neil Kale, Chen Bo Calvin Zhang, Kevin Zhu, Ankit Aich 외 arxiv

We stress test monitoring systems for detecting covert misbehavior in autonomous LLM agents (e.g., secretly sharing private information). To this end, we systematize a monitor red teaming (MRT) workflow that incorporates…

Adversarial RobustnessRed Teaming

Pull Requests as a Training Signal for Repo-Level Code Editing

2026-02-07 · Qinglin Zhu, Tianyu Chen, Shuai Lu, Lei Ji 외 arxiv

Repository-level code editing requires models to understand complex dependencies and execute precise multi-file modifications across a large codebase. While recent gains on SWE-bench rely heavily on complex agent scaffol…

Data Augmentation

AgentBreeder: Mitigating the AI Safety Impact of Multi-Agent Scaffolds via Self-Improvement

2025-02-02 · J Rosser, Jakob Nicolaus Foerster

Scaffolding Large Language Models (LLMs) into multi-agent systems often improves performance on complex tasks, but the safety impact of such scaffolds has not been thoroughly explored. We introduce AgentBreeder, a framew…