{"paper":{"title":"Skill is Not One-Size-Fits-All: Model-Aware Skill Alignment for LLM Agents","arxiv_id":"2605.30723","primary_cat":"cs.CL","submitted_at":"2026-05-29T01:34:42+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":"LLM agents increasingly retrieve externally curated skills-procedural instructions retrieved at decision time-to improve performance on long-horizon interactive tasks.","hedge":{"p":0.99,"label":"asserted"},"own_p":0.06,"main_claim_p":0.02,"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":0.66,"id":"s1","own":false,"role":"background","text":"Existing skill libraries are typically treated as model-agnostic, reusing the same skill formulations across backbones with substantially different capacities and behaviors.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.05,"main_claim_p":0.03,"quantitative":false,"quantitative_p":0.17,"role_probabilities":{"gap":0.34,"method":0.0,"result":0.0,"background":0.66,"limitation":0.0,"future_work":0.0,"contribution":0.0,"interpretation":0.0}},{"i":2,"p":0.87,"id":"s2","own":true,"role":"result","text":"However, our controlled experiments across multiple model scales show that skill effectiveness is strongly model-dependent: a skill that benefits one backbone can harm another.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.94,"main_claim_p":0.48,"quantitative":true,"quantitative_p":0.51,"role_probabilities":{"gap":0.1,"method":0.0,"result":0.87,"background":0.01,"limitation":0.0,"future_work":0.0,"contribution":0.01,"interpretation":0.01}},{"i":3,"p":0.96,"id":"s3","own":true,"role":"contribution","text":"Motivated by this observation, we propose MASA Model-Aware Skill Alignment, a framework that adapts skills to each target backbone without modifying agent weights.","hedge":{"p":0.99,"label":"asserted"},"own_p":0.63,"main_claim_p":0.17,"quantitative":false,"quantitative_p":0.04,"role_probabilities":{"gap":0.0,"method":0.04,"result":0.0,"background":0.0,"limitation":0.0,"future_work":0.0,"contribution":0.96,"interpretation":0.0}},{"i":4,"p":0.99,"id":"s4","own":true,"role":"method","text":"MASA operates in two stages: (1) a hierarchical skill evolution pipeline that iteratively rewrites general and task-specific skills using hill climbing and UCB-driven tree search, guided by environment feedback and model capability profiles; and (2) a lightweight model-conditioned skill rewriter trained on evolution trajectories to reproduce the adaptation in a single forward pass.","hedge":{"p":0.99,"label":"asserted"},"own_p":0.82,"main_claim_p":0.06,"quantitative":false,"quantitative_p":0.45,"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":5,"p":1.0,"id":"s5","own":true,"role":"result","text":"Experiments across three interactive environments and four backbones show that MASA consistently achieves the best overall performance, with gains of up to 25.8 points over the strongest baseline.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.96,"main_claim_p":0.51,"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":1.0,"id":"s6","own":true,"role":"result","text":"The learned rewriter further generalizes to unseen tasks and environments without additional search, consistently outperforming a much larger teacher LLM at a fraction of the inference cost.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.94,"main_claim_p":0.23,"quantitative":true,"quantitative_p":0.92,"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":0.61,"text":"However, our controlled experiments across multiple model scales show that skill effectiveness is strongly model-dependent: a skill that benefits one backbone can harm another.","location":"abstract s2","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":5714,"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":0.08,"states_limitation":0.12,"human_participants":0.04,"controlled_comparison":0.94,"randomized_assignment":0.02,"states_quantitative_result":0.99,"compares_with_prior_results":0.98,"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":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":0.93,"text":"Motivated by this observation, we propose MASA Model-Aware Skill Alignment, a framework that adapts skills to each target backbone without modifying agent weights.","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"}}}