mlsanityData to 14 Oct 2026

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

arXiv 2509.13312 ↗First posted 16 Sep 2025cs.CLcited by 46

Not on the map. Why?

Cited by 29 in LLM agents and tool use, but placed by its own abstract, which didn’t fit.

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.

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

28 of 43 references.

References · 28

  1. 2025Qwen3 Technical Reportcited by 8,820
  2. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,695
  3. 2023Judging LLM-as-a-Judge with MT-Bench and Chatbot Arenacited by 8,626
  4. 2023Lost in the Middle: How Language Models Use Long Contextscited by 3,455
  5. 2025gpt-oss-120b & gpt-oss-20b Model Cardcited by 1,386
  6. 2023GAIA: a benchmark for General AI Assistantscited by 1,128
  7. 2024A Survey on Large Language Models for Code Generationcited by 658
  8. 2025BrowseComp: A Simple Yet Challenging Benchmark for Browsing Agentscited by 647
  9. 2024Long-context LLMs Struggle with Long In-context Learningcited by 286
  10. 2025DeepResearch Bench: A Comprehensive Benchmark for Deep Research Agentscited by 248
  11. 2025WebSailor: Navigating Super-human Reasoning for Web Agentcited by 229
  12. 2022Re3: Generating Longer Stories With Recursive Reprompting and Revisioncited by 193
16 more
  1. 2025WebDancer: Towards Autonomous Information Seeking Agencycited by 188
  2. 2024Assisting in Writing Wikipedia-like Articles From Scratch with Large Language Modelscited by 154
  3. 2024LongWriter: Unleashing 10,000+ Word Generation from Long Context LLMscited by 144
  4. 2025WebShaper: Agentically Data Synthesizing via Information-Seeking Formalizationcited by 121
  5. 2024Agents' Room: Narrative Generation through Multi-step Collaborationcited by 57
  6. 2025DeepResearchGym: A Free, Transparent, and Reproducible Evaluation Sandbox for Deep Researchcited by 53
  7. 2024A Systematic Survey of Text Summarization: From Statistical Methods to Large Language Modelscited by 52
  8. 2024LongGenBench: Benchmarking Long-Form Generation in Long Context LLMscited by 47
  9. 2024Generating Long-form Story Using Dynamic Hierarchical Outlining with Memory-Enhancementcited by 30
  10. 2024Researchy Questions: A Dataset of Multi-Perspective, Decompositional Questions for LLM Web Agentscited by 23
  11. 2025MaskSearch: A Universal Pre-Training Framework to Enhance Agentic Search Capabilitycited by 22
  12. 2024Refiner: Restructure Retrieval Content Efficiently to Advance Question-Answering Capabilitiescited by 16
  13. 2025Beyond Outlining: Heterogeneous Recursive Planning for Adaptive Long-form Writing with Language Modelscited by 16
  14. 2025A Cognitive Writing Perspective for Constrained Long-Form Text Generationcited by 14
  15. 2025SciSage: A Multi-Agent Framework for High-Quality Scientific Survey Generationcited by 12
  16. 2025Towards Long Context Hallucination Detectioncited by 7

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 10; 2026: 36.

46 papers.

Sort:

By area:

  1. 2025Tongyi DeepResearch Technical Reportcited by 66
  2. 2025Enterprise Deep Research: Steerable Multi-Agent Deep Research for Enterprise Analyticscited by 20
  3. 2026Learning Query-Specific Rubrics from Human Preferences for DeepResearch Report Generationcited by 18
  4. 2025Toward Effective Tool-Integrated Reasoning via Self-Evolved Preference Learningcited by 17
  5. 2026ArenaRL: Scaling RL for Open-Ended Agents via Tournament-based Relative Rankingcited by 17
  6. 2025DEER: A Benchmark for Evaluating Deep Research Agents on Expert Report Generationcited by 12
  7. 2026RubricEM: Meta-RL with Rubric-guided Policy Decomposition beyond Verifiable Rewardscited by 12
  8. 2026O-Researcher: An Open Ended Deep Research Model via Multi-Agent Distillation and Agentic RLcited by 11
  9. 2025WebAggregator: Enhancing Compositional Reasoning Capabilities of Deep Research Agent Foundation Modelscited by 10
  10. 2025Video-Browser: Towards Agentic Open-web Video Browsingcited by 10
  11. 2025RhinoInsight: Improving Deep Research through Control Mechanisms for Model Behavior and Contextcited by 8
  12. 2026WebAnchor: Anchoring Agent Planning to Stabilize Long-Horizon Web Reasoningcited by 8
34 more
  1. 2026Demystifying Reinforcement Learning for Long-Horizon Tool-Using Agents: A Comprehensive Recipecited by 8
  2. 2026Agentic Environment Engineering for Large Language Models: A Survey of Environment Modeling, Synthesis, Evaluation, and Applicationcited by 8
  3. 2025Deep Ideation: Designing LLM Agents to Generate Novel Research Ideas on Scientific Concept Networkcited by 7
  4. 2026Evolving from Tool User to Creator via Training-Free Experience Reuse in Multimodal Reasoningcited by 7
  5. 2025MindWatcher: Toward Smarter Multimodal Tool-Integrated Reasoningcited by 6
  6. 2026FS-Researcher: Test-Time Scaling for Long-Horizon Research Tasks with File-System-Based Agentscited by 6
  7. 2026Search More, Think Less: Rethinking Long-Horizon Agentic Search for Efficiency and Generalizationcited by 5
  8. 2026ProductResearch: Training E-Commerce Deep Research Agents via Multi-Agent Synthetic Trajectory Distillationcited by 3
  9. 2026When Deep Research Agents Stagnate: Enhancing Reasoning with Retrieval-Aware Agent Controlcited by 3
  10. 2026IntentRL: Training Proactive User-intent Agents for Open-ended Deep Research via Reinforcement Learningcited by 2
  11. 2026Evaluating the Search Agent in a Parallel Worldcited by 2
  12. 2026AgentDisCo: Towards Disentanglement and Collaboration in Open-ended Deep Research Agentscited by 2
  13. 2026Planner-Centric Reinforcement Learning for Deep Research with Structure-Aware Rewardcited by 2
  14. 2025Optimizing Retrieval for RAG via Reinforcement Learningcited by 1
  15. 2026AgentCPM-Report: Interleaving Drafting and Deepening for Open-Ended Deep Researchcited by 1
  16. 2026ViDR: Grounding Multimodal Deep Research Reports in Source Visual Evidencecited by 1
  17. 2026Can AI Agents Synthesize Scientific Conclusions?cited by 1
  18. 2026ToolAnchor: Anchoring Counterfactual Context to Boost Agentic Tool-use Capabilitycited by 1
  19. 2026ReDesign: Recovering Editable Design Structures from Images via Agentic Decompositioncited by 1
  20. 2026Can LLM design high-quality experiments? A Comprehensive and Systematic Benchmark on Autonomous Experimental Designcited by 1
  21. 2026Who is the Agent to Blame? Localizing Faithfulness and Citation Mistakes in Agentic Deep Researchcited by 1
  22. 2026ArenaFlow: From Trajectory Ranking to Hierarchical Credit Propagation for Open-Ended Agent RLcited by 1
  23. 2026WebClipper: Efficient Evolution of Web Agents with Graph-based Trajectory Pruningcited by 0
  24. 2026Mind DeepResearch Technical Reportcited by 0
  25. 2026TimelineReasoner: Advancing Timeline Summarization with Large Reasoning Modelscited by 0
  26. 2026VeriTrace: Evolving Mental Models for Deep Research Agentscited by 0
  27. 2026When RAG Meets Query Planning: Logical Query Trees for Resolving Exploratory Reasoning Problemscited by 0
  28. 2026Mint-Agent: Introducing Finance-Native Agentic Foundation Modelscited by 0
  29. 2026DeepWeaver: Bridging the Evidence Synthesis Gap in Open-Ended Question Answeringcited by 0
  30. 2026IterSynth: Rethinking Deep Search Agents via Role-Decoupled Iterative Synthesiscited by 0
  31. 2026LongCat-DeepResearch Technical Reportcited by 0
  32. 2026DAGent: Evaluate-then-Grow Planning for Deep Research Agentscited by 0
  33. 2026Faithful Chart Generation for Multimodal Deep Research: Frame-Evidence Co-Adaptationcited by 0
  34. 2026It Takes Workflows to Evolve Better Workflowscited by 0