[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-86236-en":3,"doc-seo-86236-105":30,"detail-sidebar-cat-0-en-105":91},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":20,"is_deleted":4,"is_public":21,"is_downloadable":21,"audit_status":21,"page_count":22,"language":23,"language_code":24,"site_id":25,"html_lang":24,"table_of_contents":26,"faqs":27,"seo_title":13,"seo_description":14,"update_tm":28,"read_time":29},86236,1374391974585,"Genevieve","https://ap-avatar.wpscdn.com/davatar_276721f389ce27ea32af1340a28f341c",8,"Research & Report","TOFU: White-Box, Token-Efficient Agent Harness for Researchers","Agentic coding tools reshape research workflows, but agent performance depends not only on large language models (LLMs) and also on the surrounding orchestration harness. TOFU is an agentic harness for researchers that reads codebases, edits files, runs commands, and integrates with development tools. It supports practical workflows with superior token efficiency, lower cost, and multilingual capability, and can be deployed locally under the MIT License. As a white-box research object, TOFU lets researchers inspect, modify, and evaluate orchestration logic and tool-use behavior.","TOFU: A White-Box, Token-Efficient Agent Harness for Researchers  \nJunhao Ruan 1 ,2 * , Yuan Ge 1∗, Bei Li2†, Yongjing Yin2 , Yuchun Fan 1 ,2 , Xin Chen2 , Jingang Wang2 , Chenglong Wang 1 ,3 , Jingbo Zhu 1 ,3 , Tong Xiao 1 ,3‡  \n1 Northeastern University, China  \n2 LongCat RSI, Meituan  \n3 NiuTrans Research  \narXiv :2607 . 1 1423v 1 [ cs .CL] 13 Jul 2026  \nAbstract  \nAgentic 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 whitebox 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.  \n§ [github.com/NiuTrans/ToFu](github.com/NiuTrans/ToFu)  \n1 Introduction  \nLarge language models (LLMs) present new opportunities to transform intelligent assistants. Rather than merely receiving user requests and generating textual responses (Liu et al., 2024 ; Singh et al., 2025 ; Anthropic, 2024), modern intelligent assistants can interact with external tools and environments to perform actions such as web search, file editing, and code execution (Yao et al., 2023 ; Anthropic, 2025 ; OpenAI, 2025 ; Li et al., 2025) .  \nThe performance of agentic systems depends on both LLMs and the surrounding harness: the orchestration code that shapes an agent’s behavior. An agentic system acts toward a goal with  \n*Equal contribution.†Project leader.‡Corresponding author.  \nUser Agentic harness LLMs  \nFigure 1: Human interaction with TOFU harness.  \na degree of autonomy (Anthropic, 2025 ; OpenAI, 2025 ; OpenClaw, 2026) . Harness enables the agent to read documents or codebase, plan sequences of actions, execute them using real development tools, evaluate the results, and adjust its approach.  \nThe widespread adoption of current agentic systems is constrained by the following challenges of agentic harness. (i) Token efficiency: even responding to a simple query such as “hello” requires anagentic system to consume thousands of context tokens, while complex multi-step tasks incur substantial financial costs. (ii) Multilingual capability: the multilingual performance of agentic systems depends on that of backbone LLMs, resulting ina better user experience for English speakers than for users of other widely spoken or low-resource languages (Shi et al., 2023 ; Qin et al., 2024 ; Mu et al., 2024 ; Hofman et al., 2026) . (iii) Open-source projects and local deployment: privacy-sensitive users require both LLMs and agentic harness to be deployed locally to ensure information security (Xu et al., 2024 ; Ge et al., 2024 ; Siyan et al., 2025) . (iv) White-box research instrument: current harnesses face the trade-off: research-oriented harnesses are reproducible but benchmark-shaped and lack a usable product surface (Yang et al., 2024 ; Wang et al., 2025), while polished products default to proprietary models that are silently updated server-side, making them poor instruments for research (Ope-  \nnAI, 2025 ; Anthropic, 2025) . Research on harness evolution (Lee et al., 2026 ; Seong et al., 2026 ; Lin et al., 2026a,b ; Chen et al., 2026) requires an open-source harness with both strong benchmark performance and application-level user experience. In this paper, we present TOFU, a token-efficient, multilingual-en","cbCaipUe5UikBXcr","https://ap.wps.com/l/cbCaipUe5UikBXcr","pdf",3728604,3,1,10,"English","en",105,"# Introduction\n## Challenges and motivations\n# TOFU architecture\n## Framework overview","[{\"question\":\"What is TOFU and what tasks does it support for researchers?\",\"answer\":\"TOFU is an agentic harness for researchers that reads a codebase, edits files, runs commands, and integrates with development tools to support research workflows.\"},{\"question\":\"How does TOFU improve token efficiency and reduce cost?\",\"answer\":\"TOFU uses three-layer context compaction and harness design for context management, achieving fewer tokens on SWE-bench Verified compared with Claude Code while maintaining better performance.\"},{\"question\":\"What does “white-box” mean for TOFU in research usage?\",\"answer\":\"TOFU is designed as an open-source white-box harness, enabling researchers to inspect, modify, and evaluate its orchestration logic, tool-use behavior, and harness design.\"}]",1784209704,25,{"code":4,"msg":31,"data":32},"ok",{"site_id":25,"language":24,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":86,"head_meta":88,"extra_data":90,"updated_unix":28},"tofu-white-box-token-efficient-agent-harness-for-researchers","",{"@graph":36,"@context":85},[37,53,68],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,50],{"item":41,"name":42,"@type":43,"position":21},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":47},"https://docshare.wps.com/document/","Document",2,{"item":49,"name":12,"@type":43,"position":20},"https://docshare.wps.com/document/research-report/",{"item":51,"name":13,"@type":43,"position":52},"https://docshare.wps.com/document/tofu-white-box-token-efficient-agent-harness-for-researchers/86236/",4,{"url":51,"name":13,"@type":54,"author":55,"headline":13,"publisher":57,"fileFormat":60,"inLanguage":24,"description":14,"dateModified":61,"datePublished":62,"encodingFormat":60,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":56},"Person",{"url":41,"name":58,"@type":59},"DocShare","Organization","application/pdf","2026-07-24","2026-07-16",true,{"@type":65,"interactionType":66,"userInteractionCount":20},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"What is TOFU and what tasks does it support for researchers?","Question",{"text":75,"@type":76},"TOFU is an agentic harness for researchers that reads a codebase, edits files, runs commands, and integrates with development tools to support research workflows.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How does TOFU improve token efficiency and reduce cost?",{"text":80,"@type":76},"TOFU uses three-layer context compaction and harness design for context management, achieving fewer tokens on SWE-bench Verified compared with Claude Code while maintaining better performance.",{"name":82,"@type":73,"acceptedAnswer":83},"What does “white-box” mean for TOFU in research usage?",{"text":84,"@type":76},"TOFU is designed as an open-source white-box harness, enabling researchers to inspect, modify, and evaluate its orchestration logic, tool-use behavior, and harness design.","https://schema.org",{"og:url":51,"og:type":87,"og:title":13,"og:site_name":58,"og:description":14},"article",{"robots":89,"canonical":51},"index,follow",{"doc_id":7,"site_id":25},{"code":4,"msg":5,"data":92},[93,97,101,105,110,115,120,123,128,131,134],{"id":21,"doc_module":4,"doc_module_name":46,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":52,"doc_module":4,"doc_module_name":46,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":46,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":111,"doc_module":4,"doc_module_name":46,"category_name":112,"show_sort_weight":113,"slug":114},6,"Technology",50,"technology",{"id":116,"doc_module":4,"doc_module_name":46,"category_name":117,"show_sort_weight":118,"slug":119},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":121,"slug":122},30,"research-report",{"id":124,"doc_module":4,"doc_module_name":46,"category_name":125,"show_sort_weight":126,"slug":127},9,"Religion & Spirituality",20,"religion-spirituality",{"id":126,"doc_module":4,"doc_module_name":46,"category_name":129,"show_sort_weight":126,"slug":130},"World Cup","world-cup",{"id":22,"doc_module":4,"doc_module_name":46,"category_name":132,"show_sort_weight":22,"slug":133},"Lifestyle","lifestyle",{"id":135,"doc_module":4,"doc_module_name":46,"category_name":136,"show_sort_weight":106,"slug":137},19,"General","general"]