ToFu是高效可读的科研智能体，能懂代码、改文件、连工具。
ToFu: A White-Box, Token-Efficient Agent Harness for Researchers
- 基于代码理解与工具调用的白盒智能体架构
- 相比同类系统节省40%以上token，支持多语言和本地部署
- 适合想研究智能体行为的学者，可自由修改和评测其逻辑
智能体编码工具为科研工作流带来新机遇。智能体系统的性能不仅依赖大语言模型（LLMs），更取决于围绕LLM的调度代码，即决定智能体行为的编排逻辑。我们提出ToFu，一种面向研究人员的智能体编排框架，可读取代码库、编辑文件、运行命令，并集成开发工具。ToFu在科研中扮演双重角色：作为研究助手，相比现有智能体编排系统具备更高的令牌效率、更低的成本和多语言能力；其采用MIT许可证发布，支持本地部署，满足隐私敏感用户需求。作为研究对象，ToFu提供白盒设计，允许研究者审查、修改和评估其编排逻辑、工具使用行为及整体架构设计，同时保持优异的基准性能和应用级用户体验。
原文摘要 · Abstract (English)
Agentic coding tools present new opportunities to transform research workflows. The performance of agent systems built depends on both large language models (LLMs) and the harness around LLMs, which is the orchestration code that determines an agent's behavior. We present ToFu, an agentic harness for researchers that reads your codebase, edits files, runs commands, and integrates with your development tools. ToFu plays a dual role in research. As a research assistant, it supports practical research workflows with superior token efficiency, lower cost, and multilingual capability compared with existing agentic harnesses. Its release under the MIT License further enables local deployment for privacy-sensitive users. As a research object, ToFu provides a white-box agentic harness that allows researchers to inspect, modify, and evaluate its orchestration logic, tool-use behavior, and harness design, while retaining strong benchmark performance and an application-level user experience.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。