# FS-Researcher: Test-Time Scaling for Long-Horizon Research Tasks with File-System-Based Agents

arXiv: https://arxiv.org/abs/2602.01566 · HTML: https://mlsanity.com/paper/2602.01566/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Placed in Knowledge- and tool-augmented reasoning, one of 17 directions in LLM reasoning.
- Builds on 13 of its 24 references that are in the map.
- First posted on arXiv 2 Feb 2026.

## Placed in

- LLM reasoning / [Knowledge- and tool-augmented reasoning](https://mlsanity.com/lr/knowledge-and-tool-augmented-reasoning/)
- LLM agents and tool use / [Web, search, and research agents](https://mlsanity.com/agents/web-search-and-research-agents/)

## Builds on (most cited first, 13 of 13)

- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025)
- [SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineering](https://mlsanity.com/paper/2405.15793/) (2024)
- [τ-bench: A Benchmark for Tool-Agent-User Interaction in Real-World Domains](https://mlsanity.com/paper/2406.12045/) (2024)
- [OpenAI o1 System Card](https://mlsanity.com/paper/2412.16720/) (2024)
- [WebThinker: Empowering Large Reasoning Models with Deep Research Capability](https://mlsanity.com/paper/2504.21776/) (2025)
- [DeepResearcher: Scaling Deep Research via Reinforcement Learning in Real-world Environments](https://mlsanity.com/paper/2504.03160/) (2025)
- [DeepResearch Bench: A Comprehensive Benchmark for Deep Research Agents](https://mlsanity.com/paper/2506.11763/) (2025)
- [WebShaper: Agentically Data Synthesizing via Information-Seeking Formalization](https://mlsanity.com/paper/2507.15061/) (2025)
- [WebWeaver: Structuring Web-Scale Evidence with Dynamic Outlines for Open-Ended Deep Research](https://mlsanity.com/paper/2509.13312/) (2025)
- [Understanding Tool-Integrated Reasoning](https://mlsanity.com/paper/2508.19201/) (2025)
- [MCP-AgentBench: Evaluating Real-World Language Agent Performance with MCP-Mediated Tools](https://mlsanity.com/paper/2509.09734/) (2025)
- [Enterprise Deep Research: Steerable Multi-Agent Deep Research for Enterprise Analytics](https://mlsanity.com/paper/2510.17797/) (2025)
- [RhinoInsight: Improving Deep Research through Control Mechanisms for Model Behavior and Context](https://mlsanity.com/paper/2511.18743/) (2025)

## Built on by (most cited first, 6 of 6)

- [ScaffoldAgent: Utility-Guided Dynamic Outline Optimization for Open-Ended Deep Research](https://mlsanity.com/paper/2606.20122/) (2026)
- [Deep Research of Deep Research: From Transformer to Agent, From AI to AI for Science](https://mlsanity.com/paper/2603.28361/) (2026)
- [Fetch-then-Explore: Decoupling Selection from Extraction over a Persistent Workspace for Search Agents](https://mlsanity.com/paper/2608.02097/) (2026)
- [VeriTrace: Evolving Mental Models for Deep Research Agents](https://mlsanity.com/paper/2605.26081/) (2026)
- [LongCat-DeepResearch Technical Report](https://mlsanity.com/paper/2609.36071/) (2026)
- [Pack Light, CarryOn: Building Object-Oriented Context for Long-Horizon Agents](https://mlsanity.com/paper/2610.18784/) (2026)

## Abstract (arXiv)

Deep research is emerging as a representative long-horizon task for large language model (LLM) agents. However, long trajectories in deep research often exceed model context limits, compressing token budgets for both evidence collection and report writing, and preventing effective test-time scaling. We introduce FS-Researcher, a file-system-based, dual-agent framework that scales deep research beyond the context window via a persistent workspace. Specifically, a Context Builder agent acts as a librarian which browses the internet, writes structured notes, and archives raw sources into a hierarchical knowledge base that can grow far beyond context length. A Report Writer agent then composes the final report section by section, treating the knowledge base as the source of facts. In this framework, the file system serves as a durable external memory and a shared coordination medium across agents and sessions, enabling iterative refinement beyond the context window. Experiments on two open-ended benchmarks (DeepResearch Bench and DeepConsult) show that FS-Researcher achieves state-of-the-art report quality across different backbone models. Further analyses demonstrate a positive correlation between final report quality and the computation allocated to the Context Builder, validating effective test-time scaling under the file-system paradigm. The code and data are open-sourced at https://github.com/Ignoramus0817/FS-Researcher.