{"paper":{"title":"From Interaction Traces to Persistent Skills: Online Evolution for Computer-Use Agents","arxiv_id":"2609.04869","primary_cat":"cs.AI","submitted_at":"2026-09-04T08:29:45+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":0.81,"id":"s0","own":false,"role":"background","text":"Computer-use agents can execute increasingly complex tasks in graphical interfaces, but their interaction experience is typically transient: procedural knowledge acquired from one rollout is not systematically retained, refined, and reused in later tasks.","hedge":{"p":0.98,"label":"asserted"},"own_p":0.07,"main_claim_p":0.04,"quantitative":false,"quantitative_p":0.07,"role_probabilities":{"gap":0.19,"method":0.0,"result":0.0,"background":0.81,"limitation":0.0,"future_work":0.0,"contribution":0.0,"interpretation":0.0}},{"i":1,"p":0.99,"id":"s1","own":false,"role":"gap","text":"Existing skill libraries provide external procedural knowledge, yet their incremental value over the same agent operating without skills, as well as their longitudinal dynamics under repeated interaction, remain insufficiently characterized.","hedge":{"p":0.95,"label":"asserted"},"own_p":0.04,"main_claim_p":0.03,"quantitative":false,"quantitative_p":0.14,"role_probabilities":{"gap":0.99,"method":0.0,"result":0.0,"background":0.01,"limitation":0.0,"future_work":0.0,"contribution":0.0,"interpretation":0.0}},{"i":2,"p":0.91,"id":"s2","own":true,"role":"contribution","text":"We present an online skill-evolution framework that converts interaction trajectories and evaluator feedback into a persistent, versioned library of reusable procedures.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.93,"main_claim_p":0.09,"quantitative":false,"quantitative_p":0.03,"role_probabilities":{"gap":0.0,"method":0.09,"result":0.0,"background":0.0,"limitation":0.0,"future_work":0.0,"contribution":0.91,"interpretation":0.0}},{"i":3,"p":0.99,"id":"s3","own":true,"role":"method","text":"Each iteration executes against a frozen library snapshot, and evidence-guided skill updates become available in subsequent iterations without changing model parameters.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.78,"main_claim_p":0.06,"quantitative":false,"quantitative_p":0.07,"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":0.97,"id":"s4","own":true,"role":"method","text":"We compare the full evolving-library system with a configuration-matched empty-library control across four OSWorld application domains under the same fixed action-generation and GUI-grounding stack, task sets, and iteration horizons.","hedge":{"p":0.91,"label":"asserted"},"own_p":0.93,"main_claim_p":0.03,"quantitative":true,"quantitative_p":0.78,"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":5,"p":1.0,"id":"s5","own":true,"role":"result","text":"Following a five-iteration empty-library warm-up, Full attains a higher post-warm-up mean evaluator score in all four observed domain runs, with mean differences ranging from 5.7 to 18.6 percentage points and domain-dependent temporal stability.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.97,"main_claim_p":0.27,"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":6,"p":0.98,"id":"s6","own":true,"role":"result","text":"In GIMP, provenance-aware analysis reveals retrieval across task-of-origin boundaries and revision churn, where repeated accepted edits fail to recover the originating task.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.92,"main_claim_p":0.07,"quantitative":false,"quantitative_p":0.06,"role_probabilities":{"gap":0.0,"method":0.0,"result":0.98,"background":0.0,"limitation":0.02,"future_work":0.0,"contribution":0.0,"interpretation":0.0}},{"i":7,"p":1.0,"id":"s7","own":true,"role":"interpretation","text":"These findings characterize evolving skill libraries as auditable, shared procedural memory that can improve a fixed computer-use stack, while showing that their benefits are conditional and repeated revision does not guarantee recovery.","hedge":{"p":0.98,"label":"asserted"},"own_p":0.91,"main_claim_p":0.87,"quantitative":false,"quantitative_p":0.06,"role_probabilities":{"gap":0.0,"method":0.0,"result":0.0,"background":0.0,"limitation":0.0,"future_work":0.0,"contribution":0.0,"interpretation":1.0}},{"i":8,"p":0.72,"id":"s8","own":false,"role":"contribution","text":"Code is released at https://github.com/LongtaoHu/Skill-Evo4GUI.","hedge":{"p":0.79,"label":"asserted"},"own_p":0.48,"main_claim_p":0.02,"quantitative":false,"quantitative_p":0.03,"role_probabilities":{"gap":0.0,"method":0.05,"result":0.01,"background":0.02,"limitation":0.0,"future_work":0.2,"contribution":0.72,"interpretation":0.0}}]},"compiled":{"main_claim":{"p":1.0,"text":"These findings characterize evolving skill libraries as auditable, shared procedural memory that can improve a fixed computer-use stack, while showing that their benefits are conditional and repeated revision does not guarantee recovery.","location":"abstract s7","hedge_strength":{"p":0.98,"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":7050,"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":0.07,"states_limitation":0.95,"human_participants":0.09,"controlled_comparison":0.99,"randomized_assignment":0.03,"states_quantitative_result":0.99,"compares_with_prior_results":0.93,"mentions_code_or_data_availability":0.98},"evidential_basis":{"p":0.99,"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":0.99,"simulation_or_computation":0.01}},"contribution_type":{"p":0.96,"value":"method or tool","probabilities":{"review":0.0,"method_or_tool":0.96,"empirical_study":0.04,"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 an online skill-evolution framework that converts interaction trajectories and evaluator feedback into a persistent, versioned library of reusable procedures.","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"}}}