{"paper":{"title":"MultiEvoSkill: Structure-Aware Multi-Agent Skill Evolution for Generalizable Skill Artifacts","arxiv_id":"2610.34260","primary_cat":"cs.AI","submitted_at":"2026-10-25T12:43:01+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":0.9,"id":"s0","own":false,"role":"background","text":"Skill documents are becoming the default adaptation surface for frozen large language model (LLM) agents, but current skill generators face two key limitations.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.06,"main_claim_p":0.03,"quantitative":false,"quantitative_p":0.24,"role_probabilities":{"gap":0.1,"method":0.0,"result":0.0,"background":0.9,"limitation":0.0,"future_work":0.0,"contribution":0.0,"interpretation":0.0}},{"i":1,"p":0.8,"id":"s1","own":false,"role":"background","text":"First, humans and different LLMs differ in how they organize procedural knowledge and approach task solving.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.09,"main_claim_p":0.02,"quantitative":false,"quantitative_p":0.26,"role_probabilities":{"gap":0.12,"method":0.0,"result":0.0,"background":0.8,"limitation":0.08,"future_work":0.0,"contribution":0.0,"interpretation":0.0}},{"i":2,"p":0.49,"id":"s2","own":false,"role":"background","text":"Skills authored from a human or single-model perspective may therefore fail to align with the reasoning behaviors of other backbones, limiting cross-model generalization.","hedge":{"p":1.0,"label":"hedged_possibility"},"own_p":0.07,"main_claim_p":0.03,"quantitative":false,"quantitative_p":0.15,"role_probabilities":{"gap":0.43,"method":0.0,"result":0.0,"background":0.49,"limitation":0.07,"future_work":0.0,"contribution":0.0,"interpretation":0.01}},{"i":3,"p":0.77,"id":"s3","own":false,"role":"gap","text":"Second, sequential skill descriptions inadequately represent procedures with parallel branches and explicit dependencies, while existing skill optimizers primarily operate on prose and lack explicit support for graph-structured skill evolution.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.07,"main_claim_p":0.03,"quantitative":false,"quantitative_p":0.24,"role_probabilities":{"gap":0.77,"method":0.0,"result":0.0,"background":0.15,"limitation":0.08,"future_work":0.0,"contribution":0.0,"interpretation":0.0}},{"i":4,"p":0.54,"id":"s4","own":true,"role":"method","text":"We introduce MultiEvoSkill, a skill-optimization framework comprising three core components: 1) Skill compiler casts the skill as a typed graph with tailored operators, producing a compact, informative representation with explicit procedural topology; 2) Heterogeneous agent system proposes revision advices using collective intelligence, where minimal and informative issues are identified based on multiple sets of experiences. 3) Structure-aware debate and evolution mechanism organizes candidate edits into a heterogeneous graph, resolves them under dependency and importance constraints, and distills the collective proposal into the artifact.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.88,"main_claim_p":0.12,"quantitative":true,"quantitative_p":0.66,"role_probabilities":{"gap":0.0,"method":0.54,"result":0.0,"background":0.0,"limitation":0.0,"future_work":0.0,"contribution":0.46,"interpretation":0.0}},{"i":5,"p":0.98,"id":"s5","own":true,"role":"method","text":"Multi-dimensional gating ensures the information gain and topological correctness of each evolution.","hedge":{"p":0.99,"label":"asserted"},"own_p":0.77,"main_claim_p":0.05,"quantitative":false,"quantitative_p":0.11,"role_probabilities":{"gap":0.0,"method":0.98,"result":0.0,"background":0.0,"limitation":0.0,"future_work":0.0,"contribution":0.02,"interpretation":0.0}},{"i":6,"p":0.91,"id":"s6","own":true,"role":"method","text":"Optimal skills are then obtained when the system converges at a consistent state.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.55,"main_claim_p":0.12,"quantitative":false,"quantitative_p":0.04,"role_probabilities":{"gap":0.0,"method":0.91,"result":0.07,"background":0.0,"limitation":0.0,"future_work":0.0,"contribution":0.01,"interpretation":0.01}},{"i":7,"p":0.94,"id":"s7","own":true,"role":"result","text":"Various experiments and ablations against SOTA methods validate the effectiveness and generalization of MultiEvoSkill.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.93,"main_claim_p":0.48,"quantitative":false,"quantitative_p":0.36,"role_probabilities":{"gap":0.0,"method":0.02,"result":0.94,"background":0.0,"limitation":0.0,"future_work":0.0,"contribution":0.03,"interpretation":0.01}}]},"compiled":{"main_claim":{"p":1.0,"text":"Various experiments and ablations against SOTA methods validate the effectiveness and generalization of MultiEvoSkill.","location":"abstract s7","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":6288,"cost_usd_reported":0.0},"compiled_at":"2026-10-27","bank_version":"abstract-p1-20260923","model_version":"classifier-1.13.0","abstract_states":{"claims_first":0.09,"states_limitation":0.1,"human_participants":0.15,"controlled_comparison":0.71,"randomized_assignment":0.01,"states_quantitative_result":0.04,"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":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":1.0,"text":"We introduce MultiEvoSkill, a skill-optimization framework comprising three core components: 1) Skill compiler casts the skill as a typed graph with tailored operators, producing a compact, informative representation with explicit procedural topology; 2) Heterogeneous agent system proposes revision advices using collective intelligence, where minimal and informative issues are identified based on multiple sets of experiences. 3) Structure-aware debate and evolution mechanism organizes candidate edits into a heterogeneous graph, resolves them under dependency and importance constraints, and distills the collective proposal into the artifact.","location":"abstract s4"}},"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"}}}