ToFu:面向研究人员的白盒、令牌高效代理工具包
ToFu: A White-Box, Token-Efficient Agent Harness for Researchers
- Northeastern University(东北大学)
- LongCat RSI, Meituan(美团龙猫RSI)
- NiuTrans Research(小牛翻译研究院)
机构由 AI 辅助整理,请以论文原文为准。
AI总结:
研究提出ToFu这一代理工具包,作为研究助手,以高令牌效率等支持实际研究流程,且能本地部署;作为研究对象,提供白盒工具包供研究人员检查、修改和评估,兼具强大性能与用户体验。
AI中文摘要:
代理编码工具为转变研究工作流程带来新机遇。构建的代理系统性能取决于大语言模型(LLMs)及其周围的工具包,即决定代理行为的编排代码。我们提出了ToFu,一个面向研究人员的代理工具包,可读取代码库、编辑文件、运行命令并与开发工具集成。ToFu在研究中扮演双重角色。作为研究助手,与现有代理工具包相比,它以更高的令牌效率、更低的成本和多语言能力支持实际研究工作流程。其在MIT许可下发布,进一步支持对隐私敏感用户进行本地部署。作为研究对象,ToFu提供了一个白盒代理工具包,允许研究人员检查、修改和评估其编排逻辑、工具使用行为和工具包设计,同时保持强大的基准性能和应用级用户体验。
英文摘要:
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.