# WebWeaver: Structuring Web-Scale Evidence with Dynamic Outlines for Open-Ended Deep Research

arXiv: https://arxiv.org/abs/2509.13312 · HTML: https://mlsanity.com/paper/2509.13312/

## Key facts

- Cited by 46 papers in the map (data through 14 Oct 2026).
- Builds on 28 of its 43 references that are in the map.
- First posted on arXiv 16 Sep 2025.

## Builds on (most cited first, 28 of 28)

- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [Lost in the Middle: How Language Models Use Long Contexts](https://mlsanity.com/paper/2307.03172/) (2023)
- [gpt-oss-120b & gpt-oss-20b Model Card](https://mlsanity.com/paper/2508.10925/) (2025)
- [GAIA: a benchmark for General AI Assistants](https://mlsanity.com/paper/2311.12983/) (2023)
- [A Survey on Large Language Models for Code Generation](https://mlsanity.com/paper/2406.00515/) (2024)
- [BrowseComp: A Simple Yet Challenging Benchmark for Browsing Agents](https://mlsanity.com/paper/2504.12516/) (2025)
- [Long-context LLMs Struggle with Long In-context Learning](https://mlsanity.com/paper/2404.02060/) (2024)
- [DeepResearch Bench: A Comprehensive Benchmark for Deep Research Agents](https://mlsanity.com/paper/2506.11763/) (2025)
- [WebSailor: Navigating Super-human Reasoning for Web Agent](https://mlsanity.com/paper/2507.02592/) (2025)
- [Re3: Generating Longer Stories With Recursive Reprompting and Revision](https://mlsanity.com/paper/2210.06774/) (2022)
- [WebDancer: Towards Autonomous Information Seeking Agency](https://mlsanity.com/paper/2505.22648/) (2025)
- [Assisting in Writing Wikipedia-like Articles From Scratch with Large Language Models](https://mlsanity.com/paper/2402.14207/) (2024)
- [LongWriter: Unleashing 10,000+ Word Generation from Long Context LLMs](https://mlsanity.com/paper/2408.07055/) (2024)
- [WebShaper: Agentically Data Synthesizing via Information-Seeking Formalization](https://mlsanity.com/paper/2507.15061/) (2025)
- [Agents' Room: Narrative Generation through Multi-step Collaboration](https://mlsanity.com/paper/2410.02603/) (2024)
- [DeepResearchGym: A Free, Transparent, and Reproducible Evaluation Sandbox for Deep Research](https://mlsanity.com/paper/2505.19253/) (2025)
- [A Systematic Survey of Text Summarization: From Statistical Methods to Large Language Models](https://mlsanity.com/paper/2406.11289/) (2024)
- [LongGenBench: Benchmarking Long-Form Generation in Long Context LLMs](https://mlsanity.com/paper/2409.02076/) (2024)
- [Generating Long-form Story Using Dynamic Hierarchical Outlining with Memory-Enhancement](https://mlsanity.com/paper/2412.13575/) (2024)
- [Researchy Questions: A Dataset of Multi-Perspective, Decompositional Questions for LLM Web Agents](https://mlsanity.com/paper/2402.17896/) (2024)
- [MaskSearch: A Universal Pre-Training Framework to Enhance Agentic Search Capability](https://mlsanity.com/paper/2505.20285/) (2025)
- [Refiner: Restructure Retrieval Content Efficiently to Advance Question-Answering Capabilities](https://mlsanity.com/paper/2406.11357/) (2024)
- [Beyond Outlining: Heterogeneous Recursive Planning for Adaptive Long-form Writing with Language Models](https://mlsanity.com/paper/2503.08275/) (2025)
- [A Cognitive Writing Perspective for Constrained Long-Form Text Generation](https://mlsanity.com/paper/2502.12568/) (2025)
- [SciSage: A Multi-Agent Framework for High-Quality Scientific Survey Generation](https://mlsanity.com/paper/2506.12689/) (2025)
- [Towards Long Context Hallucination Detection](https://mlsanity.com/paper/2504.19457/) (2025)

## Built on by (most cited first, 30 of 46)

- [Tongyi DeepResearch Technical Report](https://mlsanity.com/paper/2510.24701/) (2025)
- [Enterprise Deep Research: Steerable Multi-Agent Deep Research for Enterprise Analytics](https://mlsanity.com/paper/2510.17797/) (2025)
- [Learning Query-Specific Rubrics from Human Preferences for DeepResearch Report Generation](https://mlsanity.com/paper/2602.03619/) (2026)
- [Toward Effective Tool-Integrated Reasoning via Self-Evolved Preference Learning](https://mlsanity.com/paper/2509.23285/) (2025)
- [ArenaRL: Scaling RL for Open-Ended Agents via Tournament-based Relative Ranking](https://mlsanity.com/paper/2601.06487/) (2026)
- [DEER: A Benchmark for Evaluating Deep Research Agents on Expert Report Generation](https://mlsanity.com/paper/2512.17776/) (2025)
- [RubricEM: Meta-RL with Rubric-guided Policy Decomposition beyond Verifiable Rewards](https://mlsanity.com/paper/2605.10899/) (2026)
- [O-Researcher: An Open Ended Deep Research Model via Multi-Agent Distillation and Agentic RL](https://mlsanity.com/paper/2601.03743/) (2026)
- [WebAggregator: Enhancing Compositional Reasoning Capabilities of Deep Research Agent Foundation Models](https://mlsanity.com/paper/2510.14438/) (2025)
- [Video-Browser: Towards Agentic Open-web Video Browsing](https://mlsanity.com/paper/2512.23044/) (2025)
- [RhinoInsight: Improving Deep Research through Control Mechanisms for Model Behavior and Context](https://mlsanity.com/paper/2511.18743/) (2025)
- [WebAnchor: Anchoring Agent Planning to Stabilize Long-Horizon Web Reasoning](https://mlsanity.com/paper/2601.03164/) (2026)
- [Demystifying Reinforcement Learning for Long-Horizon Tool-Using Agents: A Comprehensive Recipe](https://mlsanity.com/paper/2603.21972/) (2026)
- [Agentic Environment Engineering for Large Language Models: A Survey of Environment Modeling, Synthesis, Evaluation, and Application](https://mlsanity.com/paper/2606.12191/) (2026)
- [Deep Ideation: Designing LLM Agents to Generate Novel Research Ideas on Scientific Concept Network](https://mlsanity.com/paper/2511.02238/) (2025)
- [Evolving from Tool User to Creator via Training-Free Experience Reuse in Multimodal Reasoning](https://mlsanity.com/paper/2602.01983/) (2026)
- [MindWatcher: Toward Smarter Multimodal Tool-Integrated Reasoning](https://mlsanity.com/paper/2512.23412/) (2025)
- [FS-Researcher: Test-Time Scaling for Long-Horizon Research Tasks with File-System-Based Agents](https://mlsanity.com/paper/2602.01566/) (2026)
- [Search More, Think Less: Rethinking Long-Horizon Agentic Search for Efficiency and Generalization](https://mlsanity.com/paper/2602.22675/) (2026)
- [ProductResearch: Training E-Commerce Deep Research Agents via Multi-Agent Synthetic Trajectory Distillation](https://mlsanity.com/paper/2602.23716/) (2026)
- [When Deep Research Agents Stagnate: Enhancing Reasoning with Retrieval-Aware Agent Control](https://mlsanity.com/paper/2608.15191/) (2026)
- [IntentRL: Training Proactive User-intent Agents for Open-ended Deep Research via Reinforcement Learning](https://mlsanity.com/paper/2602.03468/) (2026)
- [Evaluating the Search Agent in a Parallel World](https://mlsanity.com/paper/2603.04751/) (2026)
- [AgentDisCo: Towards Disentanglement and Collaboration in Open-ended Deep Research Agents](https://mlsanity.com/paper/2605.11732/) (2026)
- [Planner-Centric Reinforcement Learning for Deep Research with Structure-Aware Reward](https://mlsanity.com/paper/2605.30824/) (2026)
- [Optimizing Retrieval for RAG via Reinforcement Learning](https://mlsanity.com/paper/2510.24652/) (2025)
- [AgentCPM-Report: Interleaving Drafting and Deepening for Open-Ended Deep Research](https://mlsanity.com/paper/2602.06540/) (2026)
- [ViDR: Grounding Multimodal Deep Research Reports in Source Visual Evidence](https://mlsanity.com/paper/2605.13034/) (2026)
- [Can AI Agents Synthesize Scientific Conclusions?](https://mlsanity.com/paper/2606.11337/) (2026)
- [ToolAnchor: Anchoring Counterfactual Context to Boost Agentic Tool-use Capability](https://mlsanity.com/paper/2607.14145/) (2026)

## Abstract (arXiv)

This paper tackles open-ended deep research (OEDR), a complex challenge where AI agents must synthesize vast web-scale information into insightful reports. Current approaches are plagued by dual-fold limitations: static research pipelines that decouple planning from evidence acquisition and monolithic generation paradigms that include redundant, irrelevant evidence, suffering from hallucination issues and low citation accuracy. To address these challenges, we introduce WebWeaver, a novel dual-agent framework that emulates the human research process. The planner operates in a dynamic cycle, iteratively interleaving evidence acquisition with outline optimization to produce a comprehensive, citation-grounded outline linking to a memory bank of evidence. The writer then executes a hierarchical retrieval and writing process, composing the report section by section. By performing targeted retrieval of only the necessary evidence from the memory bank via citations for each part, it effectively mitigates long-context issues and citation hallucinations. Our framework establishes a new state-of-the-art across major OEDR benchmarks, including DeepResearch Bench, DeepConsult, and DeepResearchGym. These results validate our human-centric, iterative methodology, demonstrating that adaptive planning and focused synthesis are crucial for producing comprehensive, trusted, and well-structured reports.