{"paper":{"title":"WikiLoop: Jointly Learning to Build and Navigate Agent-Native Wikis with Downstream Feedback","arxiv_id":"2607.26604","primary_cat":"cs.CL","submitted_at":"2026-07-29T08:28:30+00:00","version_compiled":"v1"},"notice":"Every quoted sentence is the authors' text from the arXiv listing abstract. Labels and probabilities are the outputs of classifier-1.13.0 on the question bank abstract-p1-20260923, exactly as returned. No sentence in this record was written by a language model.","schema":"pith.compiled-record/v0","status":"compiled","abstract":{"source":"arXiv listing abstract v1","sentences":[{"i":0,"p":0.66,"id":"s0","own":false,"role":"background","text":"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.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.06,"main_claim_p":0.03,"quantitative":false,"quantitative_p":0.3,"role_probabilities":{"gap":0.34,"method":0.0,"result":0.0,"background":0.66,"limitation":0.0,"future_work":0.0,"contribution":0.0,"interpretation":0.0}},{"i":1,"p":1.0,"id":"s1","own":true,"role":"contribution","text":"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.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.9,"main_claim_p":0.15,"quantitative":false,"quantitative_p":0.03,"role_probabilities":{"gap":0.0,"method":0.0,"result":0.0,"background":0.0,"limitation":0.0,"future_work":0.0,"contribution":1.0,"interpretation":0.0}},{"i":2,"p":0.94,"id":"s2","own":true,"role":"method","text":"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.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.82,"main_claim_p":0.06,"quantitative":false,"quantitative_p":0.04,"role_probabilities":{"gap":0.0,"method":0.94,"result":0.0,"background":0.0,"limitation":0.0,"future_work":0.0,"contribution":0.06,"interpretation":0.0}},{"i":3,"p":0.99,"id":"s3","own":true,"role":"method","text":"The Navigator follows a sufficiency-before-efficiency objective that applies retrieval-cost penalties only after full evidence has been collected.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.83,"main_claim_p":0.03,"quantitative":false,"quantitative_p":0.1,"role_probabilities":{"gap":0.0,"method":0.99,"result":0.0,"background":0.0,"limitation":0.0,"future_work":0.0,"contribution":0.01,"interpretation":0.0}},{"i":4,"p":1.0,"id":"s4","own":true,"role":"method","text":"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.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.94,"main_claim_p":0.04,"quantitative":false,"quantitative_p":0.29,"role_probabilities":{"gap":0.0,"method":1.0,"result":0.0,"background":0.0,"limitation":0.0,"future_work":0.0,"contribution":0.0,"interpretation":0.0}},{"i":5,"p":1.0,"id":"s5","own":true,"role":"method","text":"Training combines sequential role-specific optimization with a final joint stage over role-homogeneous batches.","hedge":{"p":0.99,"label":"asserted"},"own_p":0.86,"main_claim_p":0.03,"quantitative":false,"quantitative_p":0.04,"role_probabilities":{"gap":0.0,"method":1.0,"result":0.0,"background":0.0,"limitation":0.0,"future_work":0.0,"contribution":0.0,"interpretation":0.0}},{"i":6,"p":1.0,"id":"s6","own":true,"role":"result","text":"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.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.97,"main_claim_p":0.32,"quantitative":true,"quantitative_p":0.99,"role_probabilities":{"gap":0.0,"method":0.0,"result":1.0,"background":0.0,"limitation":0.0,"future_work":0.0,"contribution":0.0,"interpretation":0.0}},{"i":7,"p":0.83,"id":"s7","own":true,"role":"result","text":"Controlled comparisons support the intended effects of both objectives, and the learned edits remain useful to a held-out Navigator.","hedge":{"p":0.99,"label":"asserted"},"own_p":0.95,"main_claim_p":0.15,"quantitative":false,"quantitative_p":0.06,"role_probabilities":{"gap":0.0,"method":0.0,"result":0.83,"background":0.0,"limitation":0.0,"future_work":0.0,"contribution":0.0,"interpretation":0.17}},{"i":8,"p":0.98,"id":"s8","own":true,"role":"result","text":"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.","hedge":{"p":0.77,"label":"hedged_possibility"},"own_p":0.96,"main_claim_p":0.3,"quantitative":true,"quantitative_p":0.99,"role_probabilities":{"gap":0.0,"method":0.0,"result":0.98,"background":0.0,"limitation":0.0,"future_work":0.0,"contribution":0.0,"interpretation":0.02}},{"i":9,"p":1.0,"id":"s9","own":true,"role":"result","text":"Without dataset-specific training, WikiLoop also improves over the same-backbone LLM-Wiki, base on HotpotQA and MuSiQue.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.94,"main_claim_p":0.12,"quantitative":true,"quantitative_p":0.77,"role_probabilities":{"gap":0.0,"method":0.0,"result":1.0,"background":0.0,"limitation":0.0,"future_work":0.0,"contribution":0.0,"interpretation":0.0}}]},"compiled":{"main_claim":{"p":0.73,"text":"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.","location":"abstract s8","hedge_strength":{"p":0.77,"label":"hedged possibility"}},"provenance":{"route":{"via":"TypeSafe API","model":"classifier-1.13.0","endpoint":"https://api.typesafe.ai/v1/systemone","provider":"TypeSafe"},"packing":"one request per paper","requests":1,"input_tokens":7703,"cost_usd_reported":0.0},"compiled_at":"2026-09-23","bank_version":"abstract-p1-20260923","model_version":"classifier-1.13.0","abstract_states":{"claims_first":0.08,"states_limitation":0.22,"human_participants":0.04,"controlled_comparison":0.96,"randomized_assignment":0.02,"states_quantitative_result":0.99,"compares_with_prior_results":0.98,"mentions_code_or_data_availability":0.03},"evidential_basis":{"p":0.96,"value":"observation or experiment","probabilities":{"argument":0.0,"literature":0.0,"proof_or_derivation":0.0,"analysis_of_existing_data":0.0,"observation_or_experiment":0.96,"simulation_or_computation":0.04}},"contribution_type":{"p":1.0,"value":"method or tool","probabilities":{"review":0.0,"method_or_tool":1.0,"empirical_study":0.0,"simulation_study":0.0,"theoretical_result":0.0,"dataset_or_benchmark":0.0,"position_or_commentary":0.0}},"contribution_statement":{"p":1.0,"text":"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.","location":"abstract s1"}},"coverage":{"tier":"abstract","levels_run":["P abstract"],"not_examined":["full text","figures and tables","references and citing sentences","relations to other papers"],"sources_read":["arXiv listing abstract v1"],"levels_not_run":["S sections","T body sentences","C citations","R cross-paper relations"],"sentences_examined":10,"sentences_in_abstract":10},"measured_accuracy":{"url":"https://pith.science/accuracy","measured_on":"2026-10-02","method":"two independent model families labelled a fresh random sample blind; the figure is how often the published label matches their consensus","sentence_role_agreement":0.92,"main_claim_agreement":0.908,"typed_citation_agreement":0.933,"typed_citation_agreement_95_interval":[0.917,0.945],"review_comments_accurate":0.758,"review_comments_accurate_95_interval":[0.684,0.82],"review_caught_admitted_error_found_or_related":0.448,"review_comments_judged":{"judged_by":["gpt-5.6-luna","grok-4.7"],"judged_against":"Pith's own text copy of each paper: text extracted from the PDF, the first 90,000 characters","measured_on":"2026-10-04","accurate":113,"decided":149,"sampled_reviews":200,"split_by_lane":false,"by_lane":"https://pith.science/accuracy#by-lane"}}}