{"paper":{"title":"AutoMaster: Autonomous Post-Training by Making the Same Model a Better Teacher","arxiv_id":"2611.26510","primary_cat":"cs.CL","submitted_at":"2026-11-19T17:57:59+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":0.6,"id":"s0","own":false,"role":"background","text":"Task success alone does not specify which behaviors post-training should reinforce.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.1,"main_claim_p":0.03,"quantitative":false,"quantitative_p":0.04,"role_probabilities":{"gap":0.4,"method":0.0,"result":0.0,"background":0.6,"limitation":0.0,"future_work":0.0,"contribution":0.0,"interpretation":0.0}},{"i":1,"p":0.74,"id":"s1","own":false,"role":"background","text":"Even successful teacher trajectories can contain unsupported assumptions, unproductive repetition, or superficial verification.","hedge":{"p":0.89,"label":"asserted"},"own_p":0.18,"main_claim_p":0.03,"quantitative":false,"quantitative_p":0.03,"role_probabilities":{"gap":0.26,"method":0.0,"result":0.0,"background":0.74,"limitation":0.0,"future_work":0.0,"contribution":0.0,"interpretation":0.0}},{"i":2,"p":0.81,"id":"s2","own":true,"role":"method","text":"We propose Skill-FT (Skill-Guided Fine-Tuning), which uses natural-language skills to suppress undesirable habits and elicit underrepresented effective behaviors during teacher rollouts, then fine-tunes a target model on the resulting trajectories.","hedge":{"p":0.99,"label":"asserted"},"own_p":0.78,"main_claim_p":0.11,"quantitative":false,"quantitative_p":0.03,"role_probabilities":{"gap":0.0,"method":0.81,"result":0.0,"background":0.0,"limitation":0.0,"future_work":0.0,"contribution":0.19,"interpretation":0.0}},{"i":3,"p":0.67,"id":"s3","own":true,"role":"contribution","text":"We introduce AutoMaster, an autonomous post-training system in which an LLM agent develops these interventions through trajectory analysis, skill design, data selection, and feedback from rollouts and target-model evaluation.","hedge":{"p":0.99,"label":"asserted"},"own_p":0.92,"main_claim_p":0.08,"quantitative":false,"quantitative_p":0.04,"role_probabilities":{"gap":0.0,"method":0.33,"result":0.0,"background":0.0,"limitation":0.0,"future_work":0.0,"contribution":0.67,"interpretation":0.0}},{"i":4,"p":1.0,"id":"s4","own":true,"role":"result","text":"Across Terminal, Search, and software engineering tasks with 4B and 9B target models, AutoMaster improves mean performance over Vanilla SFT on successful unguided teacher trajectories by 1.42-8.99 percentage points, with the teacher, task pool, training set size, and SFT recipe held fixed.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.97,"main_claim_p":0.24,"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":5,"p":1.0,"id":"s5","own":true,"role":"interpretation","text":"Together with the ablations and trajectory analyses, these results suggest that behavioral shaping can make a fixed model a more effective teacher.","hedge":{"p":0.99,"label":"hedged_possibility"},"own_p":0.88,"main_claim_p":0.62,"quantitative":false,"quantitative_p":0.05,"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":6,"p":1.0,"id":"s6","own":true,"role":"result","text":"We further find that retaining skill instructions during SFT yields higher mean performance than removing them across all six settings, despite their absence at evaluation and identical supervised outputs.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.97,"main_claim_p":0.11,"quantitative":true,"quantitative_p":0.95,"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":7,"p":1.0,"id":"s7","own":true,"role":"interpretation","text":"These findings suggest that preserving skill context as part of a training demonstration can support better behavioral internalization.","hedge":{"p":1.0,"label":"hedged_possibility"},"own_p":0.86,"main_claim_p":0.17,"quantitative":false,"quantitative_p":0.05,"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}}]},"compiled":{"main_claim":{"p":0.99,"text":"Together with the ablations and trajectory analyses, these results suggest that behavioral shaping can make a fixed model a more effective teacher.","location":"abstract s5","hedge_strength":{"p":0.99,"label":"hedged possibility"}},"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":6335,"cost_usd_reported":0.0},"compiled_at":"2026-11-20","bank_version":"abstract-p1-20260923","model_version":"classifier-1.13.0","abstract_states":{"claims_first":0.05,"states_limitation":0.32,"human_participants":0.06,"controlled_comparison":0.96,"randomized_assignment":0.02,"states_quantitative_result":0.99,"compares_with_prior_results":0.95,"mentions_code_or_data_availability":0.03},"evidential_basis":{"p":0.96,"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":0.96,"simulation_or_computation":0.04}},"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":0.83,"text":"We introduce AutoMaster, an autonomous post-training system in which an LLM agent develops these interventions through trajectory analysis, skill design, data selection, and feedback from rollouts and target-model evaluation.","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":8,"sentences_in_abstract":8},"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"}}}