{"paper":{"title":"GraphSkillEvo: Evolutionary Optimization of Graph-Structured Agent Skills","arxiv_id":"2609.21749","primary_cat":"cs.LG","submitted_at":"2026-09-18T13:24:33+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":"Skills can improve the performance of Large Language Model (LLM) agents by providing task-specific procedural guidance, while skill optimization further improves their effectiveness through iterative refinement.","hedge":{"p":0.99,"label":"asserted"},"own_p":0.05,"main_claim_p":0.03,"quantitative":false,"quantitative_p":0.05,"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":0.67,"id":"s1","own":false,"role":"gap","text":"However, existing skill optimization methods typically represent skills as unstructured natural-language instructions, creating two key challenges: 1) Unstructured skills often lack explicit workflow-level guidance and contain substantial redundancy, making them difficult for LLMs to execute; 2) the vast search space of unconstrained natural-language skills makes skill optimization ineffective.","hedge":{"p":0.99,"label":"asserted"},"own_p":0.06,"main_claim_p":0.02,"quantitative":false,"quantitative_p":0.4,"role_probabilities":{"gap":0.67,"method":0.0,"result":0.0,"background":0.32,"limitation":0.01,"future_work":0.0,"contribution":0.0,"interpretation":0.0}},{"i":2,"p":0.89,"id":"s2","own":true,"role":"contribution","text":"To address these challenges, we propose representing skills as graph-structured natural-language artifacts.","hedge":{"p":0.95,"label":"asserted"},"own_p":0.62,"main_claim_p":0.07,"quantitative":false,"quantitative_p":0.03,"role_probabilities":{"gap":0.0,"method":0.11,"result":0.0,"background":0.0,"limitation":0.0,"future_work":0.0,"contribution":0.89,"interpretation":0.0}},{"i":3,"p":0.87,"id":"s3","own":false,"role":"method","text":"In graph-structured skills, each node represents an execution step together with its operational guidance, while directed edges encode context-dependent transitions between steps.","hedge":{"p":0.99,"label":"asserted"},"own_p":0.35,"main_claim_p":0.04,"quantitative":false,"quantitative_p":0.05,"role_probabilities":{"gap":0.0,"method":0.87,"result":0.0,"background":0.0,"limitation":0.0,"future_work":0.0,"contribution":0.13,"interpretation":0.0}},{"i":4,"p":0.65,"id":"s4","own":false,"role":"contribution","text":"Compared to unstructured skills, graph-structured skills can provide clear workflow-level guidance.","hedge":{"p":0.61,"label":"asserted"},"own_p":0.27,"main_claim_p":0.07,"quantitative":true,"quantitative_p":0.68,"role_probabilities":{"gap":0.0,"method":0.11,"result":0.02,"background":0.01,"limitation":0.0,"future_work":0.0,"contribution":0.65,"interpretation":0.21}},{"i":5,"p":0.67,"id":"s5","own":false,"role":"contribution","text":"Moreover, the proposed graph-structured skill can also facilitate skill optimization.","hedge":{"p":0.67,"label":"hedged_possibility"},"own_p":0.25,"main_claim_p":0.06,"quantitative":false,"quantitative_p":0.04,"role_probabilities":{"gap":0.0,"method":0.05,"result":0.0,"background":0.03,"limitation":0.0,"future_work":0.0,"contribution":0.67,"interpretation":0.25}},{"i":6,"p":0.55,"id":"s6","own":true,"role":"method","text":"Building on this structured representation, we introduce GraphSkillEvo, a population-based evolutionary optimization framework with mutation and crossover operators for graph-structured skills.","hedge":{"p":0.98,"label":"asserted"},"own_p":0.89,"main_claim_p":0.06,"quantitative":false,"quantitative_p":0.04,"role_probabilities":{"gap":0.0,"method":0.55,"result":0.0,"background":0.0,"limitation":0.0,"future_work":0.0,"contribution":0.45,"interpretation":0.0}},{"i":7,"p":0.8,"id":"s7","own":true,"role":"method","text":"By maintaining multiple candidate skills and combining effective components, GraphSkillEvo enables broader and more comprehensive exploration of the structured skill space than purely LLM-based iterative self-refinement.","hedge":{"p":0.98,"label":"asserted"},"own_p":0.65,"main_claim_p":0.09,"quantitative":true,"quantitative_p":0.84,"role_probabilities":{"gap":0.0,"method":0.8,"result":0.0,"background":0.0,"limitation":0.0,"future_work":0.0,"contribution":0.17,"interpretation":0.03}},{"i":8,"p":1.0,"id":"s8","own":true,"role":"result","text":"Extensive experiments across five agent benchmarks demonstrate that GraphSkillEvo consistently outperforms the strong skill optimization baseline SkillOpt, improving average accuracy by 4.01% on GPT-5.4-nano and 1.76% on GPT-5.4.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.97,"main_claim_p":0.79,"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":9,"p":0.64,"id":"s9","own":false,"role":"contribution","text":"Our code is available at https://github.com/ruisun7/GraphSkillEvo.","hedge":{"p":0.93,"label":"asserted"},"own_p":0.48,"main_claim_p":0.02,"quantitative":false,"quantitative_p":0.03,"role_probabilities":{"gap":0.0,"method":0.03,"result":0.03,"background":0.01,"limitation":0.0,"future_work":0.29,"contribution":0.64,"interpretation":0.0}}]},"compiled":{"main_claim":{"p":1.0,"text":"Extensive experiments across five agent benchmarks demonstrate that GraphSkillEvo consistently outperforms the strong skill optimization baseline SkillOpt, improving average accuracy by 4.01% on GPT-5.4-nano and 1.76% on GPT-5.4.","location":"abstract s8","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":7658,"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":0.07,"states_limitation":0.07,"human_participants":0.04,"controlled_comparison":0.95,"randomized_assignment":0.02,"states_quantitative_result":0.99,"compares_with_prior_results":0.98,"mentions_code_or_data_availability":0.99},"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":0.96,"text":"Building on this structured representation, we introduce GraphSkillEvo, a population-based evolutionary optimization framework with mutation and crossover operators for graph-structured skills.","location":"abstract s6"}},"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"}}}