WikiLoop: Jointly Learning to Build and Navigate Agent-Native Wikis with Downstream Feedback

• URL: http://arxiv.org/abs/2607.26604v1
• Date: Wed, 29 Jul 2026 08:28:30 GMT
• Title: WikiLoop: Jointly Learning to Build and Navigate Agent-Native Wikis with Downstream Feedback
• Abstract summary: We present WikiLoop, a feedback-coupled framework that jointly learns to build and navigate an agent-native Wiki.<n>A role-conditioned shared policy supports two interfaces: a Navigator retrieves evidence from the Wiki to answer queries, and a Builder proposes structured edits evaluated through downstream navigation.
• Score: 7.599036682788788
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Knowledge-base construction and querying are typically optimized in isolation: retrieval-augmented agents operate over a fixed, externally maintained index, whereas construction receives no signal from downstream use. We present WikiLoop, a feedback-coupled framework that jointly learns to build and navigate an agent-native Wiki, a persistent linked-page knowledge base designed for machine navigation. A role-conditioned shared policy supports two interfaces: a Navigator retrieves evidence from the Wiki to answer queries, and a Builder proposes structured edits evaluated through downstream navigation. The Navigator follows a sufficiency-before-efficiency objective that applies retrieval-cost penalties only after full evidence has been collected. The Builder learns from utility differences: a frozen Navigator scores each candidate edit by its change in downstream performance, while a guard penalty discourages regressions on unrelated queries. Training combines sequential role-specific optimization with a final joint stage over role-homogeneous batches. With Qwen3.5-9B as the common backbone, WikiLoop reaches 62.6 aggregate Answer Correctness on AuthTrace, 6.3 points above LLM-Wiki, base, with the largest gains on multi-document queries. Controlled comparisons support the intended effects of both objectives, and the learned edits remain useful to a held-out Navigator. Paired comparisons indicate that the final shared policy largely retains both role-specific capabilities, improves Navigator and end-to-end Answer Correctness by 0.4 points relative to the corresponding specialist references, and consolidates both interfaces into one model. Without dataset-specific training, WikiLoop also improves over the same-backbone LLM-Wiki, base on HotpotQA and MuSiQue.

Related papers

• SearchWiki: Learning to Build and Navigate Knowledge Wikis for Active Information Seeking [11.506364987885492]
  SearchWiki is a framework that synthesizes a corpus into a hierarchical, typed, navigable wiki.<n>We train an agent, WikiResearcher-9B, to retrieve information through multi-turn tool use.
  arXiv  Detail & Related papers  (2026-08-30T18:36:13Z)
• Knowledge Reutilization in Meta-Reinforcement Learning [51.07319647819108]
  We propose a meta-knowledge reutilization framework that learns task-level knowledge on a dynamics-simplified agent and transfers it to heterogeneous agents.<n>We show that our framework reduces final-step tracking error by 94.75% -- 99.79% compared with recent state-of-the-art baselines.
  arXiv  Detail & Related papers  (2026-06-16T16:32:28Z)
• Retrieval as Reasoning: Self-Evolving Agent-Native Retrieval via LLM-Wiki [6.956097396264084]
  LLM agents require retrieval to behave less like one-shot context fetching and more like reasoning.<n>Current Retrieval-Augmented Generation (RAG) systems organize external knowledge as flat chunks retrieved by embedding similarity.<n>We propose LLM-Wiki, an agent-native retrieval system that operationalizes the Retrieval-as-Reasoning paradigm by treating external knowledge as a compilable, composable, and self-evolving structure.
  arXiv  Detail & Related papers  (2026-05-25T06:36:14Z)
• DeepRefine: Agent-Compiled Knowledge Refinement via Reinforcement Learning [60.35032268606525]
  Agent-compiled knowledge bases provide persistent external knowledge for large language model (LLM) agents in downstream tasks.<n>Yet their quality is systematically limited by emphincompleteness, emphincorrectness, and emphredundancy
  arXiv  Detail & Related papers  (2026-05-11T12:48:31Z)
• Don't Retrieve, Navigate: Distilling Enterprise Knowledge into Navigable Agent Skills for QA and RAG [7.558933130117637]
  Corpus2Skill distills a document corpus into a hierarchical skill directory offline.<n>The compilation pipeline iteratively clusters documents, generates LLM-written summaries at each level, and materializes the result as a tree of navigable skill files.<n>At serve time, the agent receives a bird's-eye view of the corpus, drills into topic branches via progressively finer summaries, and retrieves full documents by ID.
  arXiv  Detail & Related papers  (2026-04-16T03:05:37Z)
• NaviRAG: Towards Active Knowledge Navigation for Retrieval-Augmented Generation [50.16741209529908]
  NaviRAG is a novel framework that shifts from passive segment retrieval to active knowledge navigation.<n>We show that NaviRAG consistently improves both retrieval recall and end-to-end answer performance over conventional RAG baselines.
  arXiv  Detail & Related papers  (2026-04-14T14:07:01Z)
• Benchmarking Interaction, Beyond Policy: a Reproducible Benchmark for Collaborative Instance Object Navigation [54.6417539730783]
  Question-Asking Navigation (QAsk-Nav) is the first reproducible benchmark for Collaborative Instance Object Navigation (CoIN)<n>We develop Light-CoNav, a lightweight unified model for collaborative navigation that is 3x smaller and 70x faster than existing modular methods.
  arXiv  Detail & Related papers  (2026-03-31T21:45:00Z)
• CodeCompass: Navigating the Navigation Paradox in Agentic Code Intelligence [0.0]
  We identify the Navigation Paradox: agents perform poorly because navigation and retrieval are fundamentally distinct problems.<n>We demonstrate that graph-based structural navigation via Code--a Model Context Protocol server exposing dependency graphs--achieves 99.4% task completion on hidden-dependency tasks.
  arXiv  Detail & Related papers  (2026-02-23T16:58:37Z)
• List-aware Reranking-Truncation Joint Model for Search and Retrieval-augmented Generation [80.12531449946655]
  We propose a Reranking-Truncation joint model (GenRT) that can perform the two tasks concurrently. GenRT integrates reranking and truncation via generative paradigm based on encoder-decoder architecture. Our method achieves SOTA performance on both reranking and truncation tasks for web search and retrieval-augmented LLMs.
  arXiv  Detail & Related papers  (2024-02-05T06:52:53Z)
• Merging Generated and Retrieved Knowledge for Open-Domain QA [72.42262579925911]
  COMBO is a compatibility-Oriented knowledge Merging for Better Open-domain QA framework. We show that COMBO outperforms competitive baselines on three out of four tested open-domain QA benchmarks.
  arXiv  Detail & Related papers  (2023-10-22T19:37:06Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.