{"paper":{"title":"Distilling Agentic Systems: A Roadmap across Models, Artifacts, and Harnesses","arxiv_id":"2609.36630","primary_cat":"cs.AI","submitted_at":"2026-09-29T03:38:17+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":"Modern agents increasingly rely on memories, tools, and execution logic, so their competence extends beyond model parameters.","hedge":{"p":0.98,"label":"asserted"},"own_p":0.07,"main_claim_p":0.04,"quantitative":false,"quantitative_p":0.06,"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":0.48,"id":"s1","own":false,"role":"background","text":"This shift exposes a limitation of conventional knowledge distillation, which asks how a student model imitates a teacher model.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.09,"main_claim_p":0.05,"quantitative":false,"quantitative_p":0.14,"role_probabilities":{"gap":0.48,"method":0.0,"result":0.0,"background":0.48,"limitation":0.04,"future_work":0.0,"contribution":0.0,"interpretation":0.0}},{"i":2,"p":0.99,"id":"s2","own":true,"role":"contribution","text":"We define Agent Distillation as the persistent transfer of task-solving knowledge from a teacher agent to a student agent.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.59,"main_claim_p":0.12,"quantitative":false,"quantitative_p":0.04,"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":3,"p":0.94,"id":"s3","own":true,"role":"contribution","text":"Our study organizes the field by where transferred knowledge is retained: within the model, as artifacts, through the execution harness, or across substrates.","hedge":{"p":0.98,"label":"asserted"},"own_p":0.78,"main_claim_p":0.08,"quantitative":false,"quantitative_p":0.08,"role_probabilities":{"gap":0.0,"method":0.06,"result":0.0,"background":0.0,"limitation":0.0,"future_work":0.0,"contribution":0.94,"interpretation":0.0}},{"i":4,"p":0.61,"id":"s4","own":true,"role":"contribution","text":"This perspective separates transfer evidence from its outcome and clarifies how knowledge moves between agent components.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.67,"main_claim_p":0.1,"quantitative":false,"quantitative_p":0.08,"role_probabilities":{"gap":0.0,"method":0.02,"result":0.01,"background":0.0,"limitation":0.0,"future_work":0.0,"contribution":0.61,"interpretation":0.36}},{"i":5,"p":0.78,"id":"s5","own":true,"role":"contribution","text":"We develop an evaluation framework that relates retention to causal contribution and deployed utility.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.93,"main_claim_p":0.09,"quantitative":false,"quantitative_p":0.04,"role_probabilities":{"gap":0.0,"method":0.22,"result":0.0,"background":0.0,"limitation":0.0,"future_work":0.0,"contribution":0.78,"interpretation":0.0}},{"i":6,"p":0.63,"id":"s6","own":false,"role":"interpretation","text":"Together, these contributions establish a foundation for the reliable, maintainable, and safe development of increasingly complex agentic systems.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.49,"main_claim_p":0.71,"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":0.02,"contribution":0.35,"interpretation":0.63}}]},"compiled":{"main_claim":{"p":1.0,"text":"Together, these contributions establish a foundation for the reliable, maintainable, and safe development of increasingly complex agentic systems.","location":"abstract s6","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":5434,"cost_usd_reported":0.0},"compiled_at":"2026-09-30","bank_version":"abstract-p1-20260923","model_version":"classifier-1.13.0","abstract_states":{"claims_first":0.06,"states_limitation":0.1,"human_participants":0.05,"controlled_comparison":0.04,"randomized_assignment":0.01,"states_quantitative_result":0.03,"compares_with_prior_results":0.1,"mentions_code_or_data_availability":0.03},"evidential_basis":{"p":0.91,"value":"argument","probabilities":{"argument":0.91,"literature":0.09,"proof_or_derivation":0.0,"analysis_of_existing_data":0.0,"observation_or_experiment":0.0,"simulation_or_computation":0.0}},"contribution_type":{"p":0.58,"value":"position or commentary","probabilities":{"review":0.18,"method_or_tool":0.24,"empirical_study":0.0,"simulation_study":0.0,"theoretical_result":0.0,"dataset_or_benchmark":0.0,"position_or_commentary":0.58}},"contribution_statement":{"p":0.41,"text":"Our study organizes the field by where transferred knowledge is retained: within the model, as artifacts, through the execution harness, or across substrates.","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":7,"sentences_in_abstract":7},"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"}}}