{"paper":{"title":"When Not to Imitate: Boundary-Aware Skill Memory for Reliable Tool-Use LLM Agents","arxiv_id":"2608.22339","primary_cat":"cs.CL","submitted_at":"2026-08-23T10:16:06+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":"Extracting skills from past successes is critical for the efficient evolution of Large Language Model (LLM) agents.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.07,"main_claim_p":0.03,"quantitative":false,"quantitative_p":0.03,"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":0.99,"id":"s1","own":false,"role":"background","text":"Prevailing agent self-evolution paradigms typically rely on a core assumption: equipping LLMs with skill memories derived from successful trajectories will monotonically improve their problem-solving capabilities.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.05,"main_claim_p":0.04,"quantitative":false,"quantitative_p":0.04,"role_probabilities":{"gap":0.01,"method":0.0,"result":0.0,"background":0.99,"limitation":0.0,"future_work":0.0,"contribution":0.0,"interpretation":0.0}},{"i":2,"p":0.61,"id":"s2","own":true,"role":"result","text":"However, probe analyses reveal that extracting skills solely from successful trajectories traps the model in a \\textbf{Skill Imitation Trap}.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.84,"main_claim_p":0.29,"quantitative":false,"quantitative_p":0.05,"role_probabilities":{"gap":0.28,"method":0.0,"result":0.61,"background":0.02,"limitation":0.01,"future_work":0.0,"contribution":0.01,"interpretation":0.07}},{"i":3,"p":0.96,"id":"s3","own":true,"role":"result","text":"For tasks that resemble past successes but require different tools, retrieving more skills paradoxically increases the model's confidence in wrong tool calls---procedure skills raise the wrong-tool margin by $47\\%$ over a memory-free baseline.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.85,"main_claim_p":0.17,"quantitative":true,"quantitative_p":0.99,"role_probabilities":{"gap":0.02,"method":0.0,"result":0.96,"background":0.01,"limitation":0.0,"future_work":0.0,"contribution":0.0,"interpretation":0.01}},{"i":4,"p":0.57,"id":"s4","own":true,"role":"method","text":"To overcome this limitation, we propose \\textbf{Boundary-Aware Skill Memory} (BASM), which augments each skill with explicit boundary fields---applicability conditions, risk cues, avoidance rules, and recovery notes.","hedge":{"p":0.98,"label":"asserted"},"own_p":0.85,"main_claim_p":0.12,"quantitative":false,"quantitative_p":0.14,"role_probabilities":{"gap":0.0,"method":0.57,"result":0.0,"background":0.0,"limitation":0.0,"future_work":0.0,"contribution":0.43,"interpretation":0.0}},{"i":5,"p":0.97,"id":"s5","own":true,"role":"method","text":"These fields transform each retrieved skill from an unconditional action template into state-conditioned guidance: the agent applies the skill when its conditions hold, suppresses inapplicable tool calls when they do not, and issues targeted repairs when execution fails.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.71,"main_claim_p":0.17,"quantitative":false,"quantitative_p":0.04,"role_probabilities":{"gap":0.0,"method":0.97,"result":0.0,"background":0.0,"limitation":0.0,"future_work":0.0,"contribution":0.03,"interpretation":0.0}},{"i":6,"p":1.0,"id":"s6","own":true,"role":"result","text":"Across three agent benchmarks and four model scales, BASM consistently outperforms success-distilled skill-memory baselines: it improves task success rate by up to $23.8\\%$ on AppWorld, accuracy by up to $5.0\\%$ on BFCL, and reduces attack success rate by $4.6\\%$ on AgentDojo, while simultaneously reducing average AppWorld steps by up to $6.6\\%$ relative to the memory-free baseline.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.95,"main_claim_p":0.64,"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}}]},"compiled":{"main_claim":{"p":0.9,"text":"Across three agent benchmarks and four model scales, BASM consistently outperforms success-distilled skill-memory baselines: it improves task success rate by up to $23.8\\%$ on AppWorld, accuracy by up to $5.0\\%$ on BFCL, and reduces attack success rate by $4.6\\%$ on AgentDojo, while simultaneously reducing average AppWorld steps by up to $6.6\\%$ relative to the memory-free baseline.","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":5938,"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":0.06,"states_limitation":0.12,"human_participants":0.04,"controlled_comparison":0.97,"randomized_assignment":0.02,"states_quantitative_result":0.99,"compares_with_prior_results":0.98,"mentions_code_or_data_availability":0.02},"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":1.0,"text":"To overcome this limitation, we propose \\textbf{Boundary-Aware Skill Memory} (BASM), which augments each skill with explicit boundary fields---applicability conditions, risk cues, avoidance rules, and recovery notes.","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":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"}}}