{"paper":{"title":"TactiNavi: Serving and Revising an LLM Game Coach with Explicit Strategy Conditions","arxiv_id":"2611.04772","primary_cat":"cs.AI","submitted_at":"2026-11-03T12:13:50+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":0.98,"id":"s0","own":false,"role":"background","text":"A deployed LLM coaching agent answers requests whose correct response depends on player state and game version, so advice that is right for one player can be wrong for the next.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.24,"main_claim_p":0.04,"quantitative":false,"quantitative_p":0.1,"role_probabilities":{"gap":0.02,"method":0.0,"result":0.0,"background":0.98,"limitation":0.0,"future_work":0.0,"contribution":0.0,"interpretation":0.0}},{"i":1,"p":0.99,"id":"s1","own":true,"role":"contribution","text":"We describe TactiNavi, the serving system behind the LLM coach of a commercial open-world game, which makes strategy applicability an explicit artifact shared by offline compilation, online execution, failure diagnosis, and release.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.87,"main_claim_p":0.13,"quantitative":false,"quantitative_p":0.03,"role_probabilities":{"gap":0.0,"method":0.01,"result":0.0,"background":0.0,"limitation":0.0,"future_work":0.0,"contribution":0.99,"interpretation":0.0}},{"i":2,"p":0.99,"id":"s2","own":true,"role":"method","text":"An offline compiler turns versioned game evidence and expert guidance into strategy packages with explicit prerequisites, the serving plane evaluates those prerequisites as three-valued conditions over structured player state and records decision traces, and a control plane uses the resulting condition-rule dependencies to validate revisions on held-out traffic before release.","hedge":{"p":0.99,"label":"asserted"},"own_p":0.91,"main_claim_p":0.11,"quantitative":false,"quantitative_p":0.06,"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":3,"p":1.0,"id":"s3","own":true,"role":"result","text":"In a retrospective evaluation of 1,122 logged coaching turns from three deployment periods, condition-bearing packages raise correctness from 57.9% to 82.0% over atomic facts and reduce strategy misapplication under changed player state from 18.1% to 10.4%, while trace-based claim verification reaches 86.4% precision at a median reply latency of 2.07 s.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.96,"main_claim_p":0.46,"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":4,"p":0.81,"id":"s4","own":true,"role":"result","text":"The deployment also showed that most apparent fixes are generation noise, because an unchanged-system rerun recovers 38.4% of failing turns and only one of 15 shipped revision units passes the release checks retrospectively.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.95,"main_claim_p":0.13,"quantitative":true,"quantitative_p":0.99,"role_probabilities":{"gap":0.0,"method":0.0,"result":0.81,"background":0.0,"limitation":0.0,"future_work":0.0,"contribution":0.0,"interpretation":0.19}},{"i":5,"p":0.92,"id":"s5","own":true,"role":"interpretation","text":"We distill these results into lessons on treating applicability as a first-class serving object, sizing traces for later diagnosis, and building the null model into the release path.","hedge":{"p":0.9,"label":"asserted"},"own_p":0.82,"main_claim_p":0.4,"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":0.06,"contribution":0.02,"interpretation":0.92}}]},"compiled":{"main_claim":{"p":0.49,"text":"In a retrospective evaluation of 1,122 logged coaching turns from three deployment periods, condition-bearing packages raise correctness from 57.9% to 82.0% over atomic facts and reduce strategy misapplication under changed player state from 18.1% to 10.4%, while trace-based claim verification reaches 86.4% precision at a median reply latency of 2.07 s.","location":"abstract s3","hedge_strength":{"p":1.0,"label":"asserted"}},"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":5264,"cost_usd_reported":0.0},"compiled_at":"2026-11-04","bank_version":"abstract-p1-20260923","model_version":"classifier-1.13.0","abstract_states":{"claims_first":0.04,"states_limitation":0.89,"human_participants":0.31,"controlled_comparison":0.82,"randomized_assignment":0.02,"states_quantitative_result":0.99,"compares_with_prior_results":0.87,"mentions_code_or_data_availability":0.04},"evidential_basis":{"p":0.54,"value":"analysis of existing data","probabilities":{"argument":0.0,"literature":0.0,"proof_or_derivation":0.0,"analysis_of_existing_data":0.54,"observation_or_experiment":0.46,"simulation_or_computation":0.0}},"contribution_type":{"p":0.99,"value":"method or tool","probabilities":{"review":0.0,"method_or_tool":0.99,"empirical_study":0.01,"simulation_study":0.0,"theoretical_result":0.0,"dataset_or_benchmark":0.0,"position_or_commentary":0.0}},"contribution_statement":{"p":0.78,"text":"We describe TactiNavi, the serving system behind the LLM coach of a commercial open-world game, which makes strategy applicability an explicit artifact shared by offline compilation, online execution, failure diagnosis, and release.","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":6,"sentences_in_abstract":6},"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"}}}