{"paper":{"title":"HEXIS: Compiling Skills into Extended Finite State Machines","arxiv_id":"2609.30123","primary_cat":"cs.AI","submitted_at":"2026-09-24T16:58:18+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":0.93,"id":"s0","own":false,"role":"background","text":"Agent skills provide reusable knowledge and instructions, yet agents must repeatedly infer how to apply them and which operation should follow.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.07,"main_claim_p":0.03,"quantitative":false,"quantitative_p":0.02,"role_probabilities":{"gap":0.07,"method":0.0,"result":0.0,"background":0.93,"limitation":0.0,"future_work":0.0,"contribution":0.0,"interpretation":0.0}},{"i":1,"p":0.87,"id":"s1","own":false,"role":"background","text":"This couples task reasoning with control decisions, allowing prescribed steps to be omitted or applied incorrectly.","hedge":{"p":0.98,"label":"asserted"},"own_p":0.05,"main_claim_p":0.02,"quantitative":false,"quantitative_p":0.02,"role_probabilities":{"gap":0.13,"method":0.0,"result":0.0,"background":0.87,"limitation":0.0,"future_work":0.0,"contribution":0.0,"interpretation":0.0}},{"i":2,"p":1.0,"id":"s2","own":true,"role":"contribution","text":"We introduce HEXIS, which compiles agent skills into extended finite state machines that separate knowledge from control flow.","hedge":{"p":0.99,"label":"asserted"},"own_p":0.89,"main_claim_p":0.27,"quantitative":false,"quantitative_p":0.02,"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":3,"p":0.97,"id":"s3","own":true,"role":"method","text":"Skill knowledge is incorporated into local instructions that guide reasoning and generation within states.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.64,"main_claim_p":0.06,"quantitative":false,"quantitative_p":0.02,"role_probabilities":{"gap":0.0,"method":0.97,"result":0.0,"background":0.0,"limitation":0.0,"future_work":0.0,"contribution":0.03,"interpretation":0.0}},{"i":4,"p":0.98,"id":"s4","own":true,"role":"method","text":"The machine records execution progress and intermediate results, while explicit transition conditions determine subsequent operations.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.57,"main_claim_p":0.05,"quantitative":false,"quantitative_p":0.03,"role_probabilities":{"gap":0.0,"method":0.98,"result":0.0,"background":0.0,"limitation":0.0,"future_work":0.0,"contribution":0.02,"interpretation":0.0}},{"i":5,"p":0.99,"id":"s5","own":true,"role":"method","text":"Our incremental compiler first maps skill clauses and tool interfaces to state operations, local instructions, data bindings, and transitions.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.91,"main_claim_p":0.04,"quantitative":false,"quantitative_p":0.03,"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":6,"p":1.0,"id":"s6","own":true,"role":"method","text":"It then aligns development traces with existing states to identify missing operations and dependencies.","hedge":{"p":0.98,"label":"asserted"},"own_p":0.82,"main_claim_p":0.02,"quantitative":false,"quantitative_p":0.03,"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":7,"p":0.99,"id":"s7","own":true,"role":"method","text":"These are incorporated by adding or reusing states and refining their connections.","hedge":{"p":0.98,"label":"asserted"},"own_p":0.71,"main_claim_p":0.03,"quantitative":false,"quantitative_p":0.02,"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":8,"p":1.0,"id":"s8","own":true,"role":"method","text":"Updates are accepted only after static checks and replay of the current and all previously accepted traces.","hedge":{"p":0.99,"label":"asserted"},"own_p":0.8,"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":9,"p":1.0,"id":"s9","own":true,"role":"result","text":"Across four benchmarks and four executors, HEXIS improves success over Skill + ReAct by 16.1 percentage points on average.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.95,"main_claim_p":0.56,"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":10,"p":1.0,"id":"s10","own":true,"role":"result","text":"Qwen3.8-27B reduces execution tokens by 38.4-88.9% across benchmarks.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.85,"main_claim_p":0.15,"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":0.97,"text":"Across four benchmarks and four executors, HEXIS improves success over Skill + ReAct by 16.1 percentage points on average.","location":"abstract s9","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":7913,"cost_usd_reported":0.0},"compiled_at":"2026-09-25","bank_version":"abstract-p1-20260923","model_version":"classifier-1.13.0","abstract_states":{"claims_first":0.06,"states_limitation":0.11,"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":0.04},"evidential_basis":{"p":0.95,"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":0.95,"simulation_or_computation":0.05}},"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 introduce HEXIS, which compiles agent skills into extended finite state machines that separate knowledge from control flow.","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":11,"sentences_in_abstract":11},"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"}}}