ToFu: A White-Box, Token-Efficient Agent Harness for Researchers

2026-07-13

AI Summary

Existing agent systems struggle to integrate deeply into scientific workflows due to low token efficiency, high costs, opaque black-box designs, and limited customizability. To address these limitations, this work proposes a white-box agent framework tailored for researchers, which supports codebase reading, file editing, command execution, and integration with development tools, serving simultaneously as a practical assistant and a researchable artifact. Built upon large language models, the framework employs a modular orchestration architecture that enables tool invocation, behavior monitoring, and logic modification. It offers multilingual support, local deployment capability, and full inspectability. While maintaining strong benchmark performance and a seamless user experience, the system significantly reduces inference costs, making it suitable for privacy-sensitive scenarios and providing an open-source (MIT-licensed), reproducible experimental platform for agent mechanism research.

Abstract

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.

Problem

• agentic harness
• token efficiency
• white-box
• research workflow
• privacy-sensitive deployment

Innovation

• token-efficient
• white-box
• agentic harness
• local deployment
• orchestration logic