{"paper":{"title":"Break It Down, Pass It On: Cross-Task Skill Transfer in LLM Agents","arxiv_id":"2608.20274","primary_cat":"cs.AI","submitted_at":"2026-08-20T17:12:08+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":1.0,"id":"s0","own":false,"role":"background","text":"Large language model (LLM) agents can induce skills from completed tasks and reuse them later to grow more capable with experience.","hedge":{"p":0.76,"label":"asserted"},"own_p":0.07,"main_claim_p":0.03,"quantitative":false,"quantitative_p":0.04,"role_probabilities":{"gap":0.0,"method":0.0,"result":0.0,"background":1.0,"limitation":0.0,"future_work":0.0,"contribution":0.0,"interpretation":0.0}},{"i":1,"p":0.94,"id":"s1","own":false,"role":"background","text":"In practice, induced skills may transfer unreliably and can even harm the agent that retrieves them.","hedge":{"p":0.98,"label":"hedged_possibility"},"own_p":0.11,"main_claim_p":0.03,"quantitative":false,"quantitative_p":0.08,"role_probabilities":{"gap":0.05,"method":0.0,"result":0.0,"background":0.94,"limitation":0.01,"future_work":0.0,"contribution":0.0,"interpretation":0.0}},{"i":2,"p":1.0,"id":"s2","own":false,"role":"gap","text":"When agent-induced skills transfer reliably across tasks remains an open question.","hedge":{"p":0.91,"label":"asserted"},"own_p":0.04,"main_claim_p":0.02,"quantitative":false,"quantitative_p":0.03,"role_probabilities":{"gap":1.0,"method":0.0,"result":0.0,"background":0.0,"limitation":0.0,"future_work":0.0,"contribution":0.0,"interpretation":0.0}},{"i":3,"p":0.97,"id":"s3","own":true,"role":"contribution","text":"We conduct a comprehensive and controlled study of how the way skills are induced shapes their transfer across tasks.","hedge":{"p":0.94,"label":"asserted"},"own_p":0.93,"main_claim_p":0.03,"quantitative":false,"quantitative_p":0.04,"role_probabilities":{"gap":0.0,"method":0.03,"result":0.0,"background":0.0,"limitation":0.0,"future_work":0.0,"contribution":0.97,"interpretation":0.0}},{"i":4,"p":0.83,"id":"s4","own":false,"role":"method","text":"Specifically, we compare task-level with subtask-level skill induction and text with code skill formats, the two axes along which existing methods differ.","hedge":{"p":0.89,"label":"asserted"},"own_p":0.45,"main_claim_p":0.05,"quantitative":false,"quantitative_p":0.34,"role_probabilities":{"gap":0.0,"method":0.83,"result":0.0,"background":0.0,"limitation":0.0,"future_work":0.0,"contribution":0.17,"interpretation":0.0}},{"i":5,"p":1.0,"id":"s5","own":true,"role":"result","text":"Task-level skills mostly reduce the agent's performance below its no-memory baseline while subtask-level skills raise it above on average, and text skills transfer better than code skills.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.95,"main_claim_p":0.71,"quantitative":true,"quantitative_p":0.97,"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":0.63,"id":"s6","own":true,"role":"method","text":"To further understand our findings, we examine two complementary properties of the induced skills: specificity, which measures how closely a skill matches real tasks, and abstractness, which measures how evenly its relevance spreads across tasks.","hedge":{"p":0.98,"label":"asserted"},"own_p":0.84,"main_claim_p":0.05,"quantitative":false,"quantitative_p":0.09,"role_probabilities":{"gap":0.0,"method":0.63,"result":0.0,"background":0.0,"limitation":0.0,"future_work":0.0,"contribution":0.26,"interpretation":0.11}},{"i":7,"p":0.39,"id":"s7","own":true,"role":"result","text":"Neither property alone predicts task success, but their combined effect does, which we propose as a skill utility score.","hedge":{"p":0.94,"label":"asserted"},"own_p":0.93,"main_claim_p":0.24,"quantitative":false,"quantitative_p":0.27,"role_probabilities":{"gap":0.0,"method":0.06,"result":0.39,"background":0.0,"limitation":0.0,"future_work":0.0,"contribution":0.28,"interpretation":0.27}},{"i":8,"p":0.99,"id":"s8","own":true,"role":"result","text":"The score correlates consistently with task success when skills are transferred, and subtask-level and text skills score higher.","hedge":{"p":0.99,"label":"asserted"},"own_p":0.95,"main_claim_p":0.25,"quantitative":true,"quantitative_p":0.87,"role_probabilities":{"gap":0.0,"method":0.0,"result":0.99,"background":0.0,"limitation":0.0,"future_work":0.0,"contribution":0.0,"interpretation":0.01}},{"i":9,"p":0.58,"id":"s9","own":true,"role":"interpretation","text":"Computing skill utility only needs the skills and task descriptions but not any task execution, so our score serves as a practical diagnostic of a skill memory before any new task runs.","hedge":{"p":0.96,"label":"asserted"},"own_p":0.88,"main_claim_p":0.1,"quantitative":false,"quantitative_p":0.09,"role_probabilities":{"gap":0.0,"method":0.08,"result":0.06,"background":0.0,"limitation":0.0,"future_work":0.01,"contribution":0.27,"interpretation":0.58}}]},"compiled":{"main_claim":{"p":0.93,"text":"Task-level skills mostly reduce the agent's performance below its no-memory baseline while subtask-level skills raise it above on average, and text skills transfer better than code skills.","location":"abstract s5","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":7481,"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":0.48,"human_participants":0.04,"controlled_comparison":0.95,"randomized_assignment":0.03,"states_quantitative_result":0.09,"compares_with_prior_results":0.9,"mentions_code_or_data_availability":0.03},"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":0.99,"value":"empirical study","probabilities":{"review":0.0,"method_or_tool":0.01,"empirical_study":0.99,"simulation_study":0.0,"theoretical_result":0.0,"dataset_or_benchmark":0.0,"position_or_commentary":0.0}},"contribution_statement":{"p":0.92,"text":"We conduct a comprehensive and controlled study of how the way skills are induced shapes their transfer across tasks.","location":"abstract s3"}},"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"}}}