mlsanityData to 14 Oct 2026

DeepWeaver: Bridging the Evidence Synthesis Gap in Open-Ended Question Answering

arXiv 2608.18988 ↗First posted 19 Aug 2026cs.CL cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

Retrieve-then-generate pipelines are commonly used to produce deep-research answers for open-ended questions, but retrieval alone is insufficient: LLMs must organize noisy and fragmented evidence into comprehensive, well-cited answers. We refer to this process as evidence synthesis. However, direct generation often underuses evidence, misaligns citations, and collapses diverse information into shallow summaries, exposing an evidence synthesis gap between retrieval and generation. Thus, we propose DeepWeaver, a novel framework that weaves noisy retrieved evidence into comprehensive answers by maintaining Thought Block Chains (TBCs), a structured representation that groups claims, salient information, keywords, and supporting evidence. DeepWeaver uses subordinate TBCs to inspect residual evidence, commit TBC revisions, and discover new claims before final generation. We evaluate DeepWeaver on open-ended QA over both knowledge bases and the web, and introduce LoQA, a high-density benchmark for evidence synthesis. Across multiple LLMs, DeepWeaver improves content sufficiency, citation grounding, and detail preservation on LoQA, while achieving deeper insights and higher citation quality on DeepResearch Bench. These results show that evidence weaving is an effective mechanism for bridging retrieval and generation in open-ended QA. Our code is available at https://github.com/KlozeWang/DeepWeaver.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 43 of its 61 references that are in the map. First posted on arXiv 19 Aug 2026.

Builds on

43 of 61 references.

References · 43

  1. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,297
  2. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,695
  3. 2023Toolformer: Language Models Can Teach Themselves to Use Toolscited by 4,182
  4. 2023Lost in the Middle: How Language Models Use Long Contextscited by 3,455
  5. 2020REALM: Retrieval-Augmented Language Model Pre-Trainingcited by 2,141
  6. 2023Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflectioncited by 1,839
  7. 2021WebGPT: Browser-assisted question-answering with human feedbackcited by 1,745
  8. 2025Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learningcited by 1,444
  9. 2023LongBench: A Bilingual, Multitask Benchmark for Long Context Understandingcited by 1,417
  10. 2024RULER: What's the Real Context Size of Your Long-Context Language Models?cited by 1,346
  11. 2020Leveraging Passage Retrieval with Generative Models for Open Domain Question Answeringcited by 1,210
  12. 2026DeepSeek-V4: Towards Highly Efficient Million-Token Context Intelligencecited by 1,040
31 more
  1. 2023In-Context Retrieval-Augmented Language Modelscited by 702
  2. 2023Enabling Large Language Models to Generate Text with Citationscited by 595
  3. 2023Plan-and-Solve Prompting: Improving Zero-Shot Chain-of-Thought Reasoning by Large Language Modelscited by 560
  4. 2025GLM-4.5: Agentic, Reasoning, and Coding (ARC) Foundation Modelscited by 467
  5. 2023LongLLMLingua: Accelerating and Enhancing LLMs in Long Context Scenarios via Prompt Compressioncited by 453
  6. 2024∞Bench: Extending Long Context Evaluation Beyond 100K Tokenscited by 367
  7. 2022Teaching language models to support answers with verified quotescited by 292
  8. 2025DeepResearcher: Scaling Deep Research via Reinforcement Learning in Real-world Environmentscited by 286
  9. 2024MinerU: An Open-Source Solution for Precise Document Content Extractioncited by 267
  10. 2023RECOMP: Improving Retrieval-Augmented LMs with Compression and Selective Augmentationcited by 256
  11. 2025DeepResearch Bench: A Comprehensive Benchmark for Deep Research Agentscited by 248
  12. 2023L-Eval: Instituting Standardized Evaluation for Long Context Language Modelscited by 233
  13. 2024Chain of Agents: Large Language Models Collaborating on Long-Context Taskscited by 206
  14. 2025WebDancer: Towards Autonomous Information Seeking Agencycited by 188
  15. 2023Chain-of-Note: Enhancing Robustness in Retrieval-Augmented Language Modelscited by 184
  16. 2024Retrieval-Augmented Generation with Graphs (GraphRAG)cited by 172
  17. 2024Assisting in Writing Wikipedia-like Articles From Scratch with Large Language Modelscited by 154
  18. 2024Language agents achieve superhuman synthesis of scientific knowledgecited by 137
  19. 2025NoLiMa: Long-Context Evaluation Beyond Literal Matchingcited by 126
  20. 2024Leave No Document Behind: Benchmarking Long-Context LLMs with Extended Multi-Doc QAcited by 122
  21. 2025WebShaper: Agentically Data Synthesizing via Information-Seeking Formalizationcited by 121
  22. 2024AutoSurvey: Large Language Models Can Automatically Write Surveyscited by 119
  23. 2023Skeleton-of-Thought: Prompting LLMs for Efficient Parallel Generationcited by 105
  24. 2024DocLayout-YOLO: Enhancing Document Layout Analysis through Diverse Synthetic Data and Global-to-Local Adaptive Perceptioncited by 82
  25. 2023Llama2Vec: Unsupervised Adaptation of Large Language Models for Dense Retrievalcited by 78
  26. 2025SurveyForge: On the Outline Heuristics, Memory-Driven Generation, and Multi-dimensional Evaluation for Automated Survey Writingcited by 49
  27. 2025WebWeaver: Structuring Web-Scale Evidence with Dynamic Outlines for Open-Ended Deep Researchcited by 46
  28. 2023Effective Large Language Model Adaptation for Improved Grounding and Citation Generationcited by 45
  29. 2024M-RAG: Reinforcing Large Language Model Performance through Retrieval-Augmented Generation with Multiple Partitionscited by 38
  30. 2025MCTS-RAG: Enhancing Retrieval-Augmented Generation with Monte Carlo Tree Searchcited by 21
  31. 2025SuperWriter: Reflection-Driven Long-Form Generation with Large Language Modelscited by 5

Built on by

Not cited yet.