菜单

关于 🐙 GitHub
arXiv 提交日期: 2025-12-08
📄 Abstract - DeepCode: Open Agentic Coding

Recent advances in large language models (LLMs) have given rise to powerful coding agents, making it possible for code assistants to evolve into code engineers. However, existing methods still face significant challenges in achieving high-fidelity document-to-codebase synthesis--such as scientific papers to code--primarily due to a fundamental conflict between information overload and the context bottlenecks of LLMs. In this work, we introduce DeepCode, a fully autonomous framework that fundamentally addresses this challenge through principled information-flow management. By treating repository synthesis as a channel optimization problem, DeepCode seamlessly orchestrates four information operations to maximize task-relevant signals under finite context budgets: source compression via blueprint distillation, structured indexing using stateful code memory, conditional knowledge injection via retrieval-augmented generation, and closed-loop error correction. Extensive evaluations on the PaperBench benchmark demonstrate that DeepCode achieves state-of-the-art performance, decisively outperforming leading commercial agents such as Cursor and Claude Code, and crucially, surpassing PhD-level human experts from top institutes on key reproduction metrics. By systematically transforming paper specifications into production-grade implementations comparable to human expert quality, this work establishes new foundations for autonomous scientific reproduction that can accelerate research evaluation and discovery.

顶级标签: llm agents systems
详细标签: code generation multi-agent systems retrieval-augmented generation information flow benchmark 或 搜索:

DeepCode:一个基于信息流管理的文档到代码库合成框架 / DeepCode: Open Agentic Coding


1️⃣ 一句话总结

DeepCode是一个全新的、完全自主的智能编码框架,它将复杂的文档(如科学论文)到可执行代码库的合成过程,重新构想为一个信息流管理问题,通过协调多种信息操作(如蓝图蒸馏、结构化记忆、检索增强生成和闭环纠错),在有限的上文预算下最大化任务相关信号,从而在基准测试中超越了领先的商业代理和人类专家。


2️⃣ 论文创新点

1. 信息论视角与设计原则

2. DeepCode多阶段框架与四大信息操作

3. 蓝图生成阶段:分层内容索引与多智能体规范分析

4. 代码生成阶段:状态化CodeMem与条件CodeRAG双机制

5. 自动化验证与精炼阶段


3️⃣ 主要结果与价值

结果亮点

实际价值


4️⃣ 术语表

源自 arXiv: 2512.07921