{"paper":{"title":"RecSys Factory: Bounding LLM Agent Autonomy to Decision Points in the Industrial Recommender Lifecycle","arxiv_id":"2608.11241","primary_cat":"cs.AI","submitted_at":"2026-07-31T15:42:45+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":0.95,"id":"s0","own":false,"role":"background","text":"Deploying LLM agents into industrial recommender operations exposes a three-way tension we frame as the autonomy-determinism-efficiency trilemma: general autonomy (interpreting operator intent, generating glue code zero-shot), industrial determinism (schema-conforming feature extraction, non-crashing A/B, zero compliance-path hallucination), and end-to-end efficiency.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.35,"main_claim_p":0.21,"quantitative":false,"quantitative_p":0.4,"role_probabilities":{"gap":0.05,"method":0.0,"result":0.0,"background":0.95,"limitation":0.0,"future_work":0.0,"contribution":0.0,"interpretation":0.0}},{"i":1,"p":0.86,"id":"s1","own":false,"role":"background","text":"Any two can be maximized against the third.","hedge":{"p":0.99,"label":"asserted"},"own_p":0.19,"main_claim_p":0.27,"quantitative":true,"quantitative_p":0.59,"role_probabilities":{"gap":0.02,"method":0.0,"result":0.0,"background":0.86,"limitation":0.01,"future_work":0.0,"contribution":0.0,"interpretation":0.11}},{"i":2,"p":0.92,"id":"s2","own":true,"role":"contribution","text":"We present RecSys Factory, an LLM-agent platform deployed for 78 days across three heterogeneous Tencent recommender business lines.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.94,"main_claim_p":0.05,"quantitative":true,"quantitative_p":0.96,"role_probabilities":{"gap":0.0,"method":0.07,"result":0.01,"background":0.0,"limitation":0.0,"future_work":0.0,"contribution":0.92,"interpretation":0.0}},{"i":3,"p":0.64,"id":"s3","own":true,"role":"contribution","text":"The design principle is autonomy at decision points, not over pipelines, made concrete through three deconstructions that each discharge one vertex of the trilemma.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.81,"main_claim_p":0.3,"quantitative":false,"quantitative_p":0.44,"role_probabilities":{"gap":0.0,"method":0.36,"result":0.0,"background":0.0,"limitation":0.0,"future_work":0.0,"contribution":0.64,"interpretation":0.0}},{"i":4,"p":0.95,"id":"s4","own":true,"role":"method","text":"Runtime is deconstructed into three host-emitted event sources (Claude Code Stop hooks, corporate-IM webhooks, workflow scheduler APIs): the platform carries no long-running daemon during the wait phase and consumes zero CPU during the 94% of wall-clock spent waiting on Spark or GPU jobs.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.93,"main_claim_p":0.05,"quantitative":true,"quantitative_p":0.99,"role_probabilities":{"gap":0.0,"method":0.95,"result":0.01,"background":0.0,"limitation":0.0,"future_work":0.0,"contribution":0.04,"interpretation":0.0}},{"i":5,"p":0.91,"id":"s5","own":true,"role":"method","text":"Capability is deconstructed into a 29-file skill ecosystem (8,971 lines of SKILL.md) whose per-skill pitfall tables mechanically compile into a 400-entry PitfallStore, confining autonomy to bounded typed decision surfaces inside pre-committed pipelines.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.93,"main_claim_p":0.1,"quantitative":true,"quantitative_p":0.98,"role_probabilities":{"gap":0.0,"method":0.91,"result":0.0,"background":0.0,"limitation":0.0,"future_work":0.0,"contribution":0.09,"interpretation":0.0}},{"i":6,"p":0.98,"id":"s6","own":true,"role":"limitation","text":"Deployment spans three business lines with disjoint label semantics, A/B layer topologies, and operator personas; an onboarding-time compression is observed on two of the three and is reported as a case-study observation, not a generalization claim, and not measured against a controlled pre-platform baseline.","hedge":{"p":0.62,"label":"asserted"},"own_p":0.9,"main_claim_p":0.04,"quantitative":true,"quantitative_p":0.86,"role_probabilities":{"gap":0.0,"method":0.0,"result":0.02,"background":0.0,"limitation":0.98,"future_work":0.0,"contribution":0.0,"interpretation":0.0}},{"i":7,"p":0.9,"id":"s7","own":true,"role":"method","text":"The human is retained at the diagnostic-versus-execution boundary via a human-in-the-loop card protocol, deployed as an audit-trail primitive (schema-validated, idempotent, replayable) and reported from an 8-day 16-run pilot.","hedge":{"p":0.99,"label":"asserted"},"own_p":0.93,"main_claim_p":0.05,"quantitative":true,"quantitative_p":0.97,"role_probabilities":{"gap":0.0,"method":0.9,"result":0.01,"background":0.0,"limitation":0.0,"future_work":0.0,"contribution":0.09,"interpretation":0.0}},{"i":8,"p":1.0,"id":"s8","own":true,"role":"result","text":"Across the 78-day window the platform recorded 1,624 CLI-tool dispatches at a 78.6% aggregate success rate.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.95,"main_claim_p":0.06,"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}}]},"compiled":{"main_claim":{"p":0.86,"text":"The design principle is autonomy at decision points, not over pipelines, made concrete through three deconstructions that each discharge one vertex of the trilemma.","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":7373,"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":0.05,"states_limitation":0.96,"human_participants":0.83,"controlled_comparison":0.09,"randomized_assignment":0.05,"states_quantitative_result":0.98,"compares_with_prior_results":0.09,"mentions_code_or_data_availability":0.04},"evidential_basis":{"p":1.0,"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":1.0,"simulation_or_computation":0.0}},"contribution_type":{"p":0.98,"value":"method or tool","probabilities":{"review":0.0,"method_or_tool":0.98,"empirical_study":0.02,"simulation_study":0.0,"theoretical_result":0.0,"dataset_or_benchmark":0.0,"position_or_commentary":0.0}},"contribution_statement":{"p":0.83,"text":"We present RecSys Factory, an LLM-agent platform deployed for 78 days across three heterogeneous Tencent recommender business lines.","location":"abstract s2"}},"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":9,"sentences_in_abstract":9},"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"}}}