mlsanityData to 14 Oct 2026

SearchWiki: Learning to Build and Navigate Knowledge Wikis for Active Information Seeking

arXiv 2608.29953 ↗First posted 30 Aug 2026cs.AIcited by 0

On the map: Retrieval-augmented generation → Agentic RAG, agents and memory

Abstract (arXiv)

Flat retrieval-augmented generation treats a corpus as a bag of chunks, discarding document hierarchy and cross document structure. We introduce SearchWiki, a harness framework that synthesizes a corpus into a hierarchical, typed, navigable wiki and trains an agent, WikiResearcher-9B, to retrieve information through multi-turn tool use. The wiki organizes knowledge into three layers - document overviews, cross- document topic pages, and page-level source records; enabling progressive refinement of retrieval when initial lookup misses. We optimize the agent's navigation policy with on-policy reinforcement learning with a multi-component reward function balancing answer correctness, retrieval quality and trajectory efficiency. Evaluation on ViDoRe-V3 (8 domains), FinanceBench, and memory benchmarks (LoCoMo, LongMemEval, PersonaMem-v2) shows that WikiResearcher- 9B which is our RL-tuned Qwen 9B model, significantly outperforms same-size untrained baselines and exceeds or matches larger external models. SearchWiki paired with WikiResearcher-9B demonstrates that learned navigation over structured corpora is a superior alternative to flat retrieval.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Agentic RAG, agents and memory, one of 15 directions in Retrieval-augmented generation. Builds on 27 of its 49 references that are in the map. First posted on arXiv 30 Aug 2026.

Builds on

27 of 49 references.

Closest ancestors · 2

Same direction, newest first

  1. 2026A-RAG: Scaling Agentic Retrieval-Augmented Generation via Hierarchical Retrieval Interfaces3 Feb
  2. 2025Interact-RAG: Reason and Interact with the Corpus, Beyond Black-Box Retrieval31 Oct

Other references · 25

  1. 2024DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Modelscited by 9,379
  2. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,297
  3. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,695
  4. 2023Judging LLM-as-a-Judge with MT-Bench and Chatbot Arenacited by 8,626
  5. 2020Dense Passage Retrieval for Open-Domain Question Answeringcited by 3,824
  6. 2023G-Eval: NLG Evaluation using GPT-4 with Better Human Alignmentcited by 2,276
  7. 2023Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflectioncited by 1,839
  8. 2024From Local to Global: A Graph RAG Approach to Query-Focused Summarizationcited by 1,453
  9. 2025Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learningcited by 1,444
  10. 2023MemGPT: Towards LLMs as Operating Systemscited by 1,389
  11. 2025gpt-oss-120b & gpt-oss-20b Model Cardcited by 1,386
  12. 2019ZeRO: Memory Optimizations Toward Training Trillion Parameter Modelscited by 1,301
13 more
  1. 2022Interleaving Retrieval with Chain-of-Thought Reasoning for Knowledge-Intensive Multi-Step Questionscited by 923
  2. 2024LongMemEval: Benchmarking Chat Assistants on Long-Term Interactive Memorycited by 707
  3. 2021Retrieval Augmentation Reduces Hallucination in Conversationcited by 692
  4. 2024RAPTOR: Recursive Abstractive Processing for Tree-Organized Retrievalcited by 532
  5. 2024Adaptive-RAG: Learning to Adapt Retrieval-Augmented Large Language Models through Question Complexitycited by 451
  6. 2023FinanceBench: A New Benchmark for Financial Question Answeringcited by 270
  7. 2024ColPali: Efficient Document Retrieval with Vision Language Modelscited by 195
  8. 2026GDPO: Group reward-Decoupled Normalization Policy Optimization for Multi-reward RL Optimizationcited by 193
  9. 2021Dense Hierarchical Retrieval for Open-Domain Question Answeringcited by 34
  10. 2026Tmax: A simple recipe for terminal agentscited by 33
  11. 2026GrepSeek: Training Search Agents for Direct Corpus Interactioncited by 10
  12. 2026Retrieval as Reasoning: Self-Evolving Agent-Native Retrieval via LLM-Wikicited by 9
  13. 2026From Passive Retrieval to Active Memory Navigation: Learning to Use Memory as a Structured Action Spacecited by 2

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026WikiLoop: Jointly Learning to Build and Navigate Agent-Native Wikis with Downstream Feedback
  2. 2026WikiKV: Schema-Evolving Path-Indexed Storage for Hierarchical Knowledge Navigation
  3. 2026LexiHorizon: Stabilizing Reinforcement Learning for Long-Horizon Deep Search
  4. 2026OThink-SRR1: Search, Refine and Reasoning with Reinforced Learning for Large Language Models
  5. 2025MARAG-R1: Beyond Single Retriever via Reinforcement-Learned Multi-Tool Agentic Retrieval
  6. 2025Scent of Knowledge: Optimizing Search-Enhanced Reasoning with Information Foraging
  7. 2026CoSearch: Joint Training of Reasoning and Document Ranking via Reinforcement Learning for Agentic Search
  8. 2025R1-Searcher++: Incentivizing the Dynamic Knowledge Acquisition of LLMs via Reinforcement Learning