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

2026-08-30

AI Summary

为解决信息检索中忽略文档结构的问题，提出SearchWiki框架构建分层知识维基，并训练WikiResearcher-9B模型通过多轮工具使用进行有效导航和检索。

Abstract

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.

Problem

• flat retrieval
• document hierarchy
• cross-document structure
• information seeking

Innovation

• hierarchical knowledge organization
• reinforcement learning for navigation
• multi-turn tool use