{"paper":{"title":"SkillSentry: Reliable Skill Execution for LLM Agents via Runtime Assurance","arxiv_id":"2608.09253","primary_cat":"cs.AI","submitted_at":"2026-08-10T08:13:52+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 are increasingly equipped with skills to perform complex tasks through multi-step reasoning and tool use.","hedge":{"p":0.99,"label":"asserted"},"own_p":0.05,"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":0.77,"id":"s1","own":false,"role":"background","text":"Although skills provide reusable procedural knowledge, agents may still execute them unreliably.","hedge":{"p":0.99,"label":"hedged_possibility"},"own_p":0.07,"main_claim_p":0.02,"quantitative":false,"quantitative_p":0.03,"role_probabilities":{"gap":0.23,"method":0.0,"result":0.0,"background":0.77,"limitation":0.0,"future_work":0.0,"contribution":0.0,"interpretation":0.0}},{"i":2,"p":0.94,"id":"s2","own":false,"role":"background","text":"Even when an agent has demonstrated the capability to complete tasks under the guidance of a skill, it may fail to do so consistently across similar tasks or repeated runs due to deviations from the skill procedure or incorrect execution of individual steps.","hedge":{"p":0.97,"label":"hedged_possibility"},"own_p":0.1,"main_claim_p":0.03,"quantitative":false,"quantitative_p":0.09,"role_probabilities":{"gap":0.06,"method":0.0,"result":0.0,"background":0.94,"limitation":0.0,"future_work":0.0,"contribution":0.0,"interpretation":0.0}},{"i":3,"p":0.91,"id":"s3","own":false,"role":"background","text":"Such instability limits the practical reliability of LLM agents.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.06,"main_claim_p":0.03,"quantitative":false,"quantitative_p":0.02,"role_probabilities":{"gap":0.05,"method":0.0,"result":0.0,"background":0.91,"limitation":0.01,"future_work":0.0,"contribution":0.0,"interpretation":0.03}},{"i":4,"p":0.96,"id":"s4","own":true,"role":"contribution","text":"To address this problem, we propose SkillSentry, a skill-oriented runtime assurance framework built upon a new domain-specific language (DSL) for representing runtime guidance for skill execution.","hedge":{"p":0.99,"label":"asserted"},"own_p":0.86,"main_claim_p":0.07,"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":5,"p":0.99,"id":"s5","own":true,"role":"method","text":"SkillSentry initializes the runtime guidance by combining a skill specification extracted from the corresponding skill document with execution experience mined from historical successful and failed traces.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.87,"main_claim_p":0.03,"quantitative":false,"quantitative_p":0.04,"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":6,"p":1.0,"id":"s6","own":true,"role":"method","text":"It then wraps around the agent execution loop to monitor and guide skill execution under the current guidance, while iteratively refining the guidance using newly collected traces.","hedge":{"p":0.99,"label":"asserted"},"own_p":0.78,"main_claim_p":0.03,"quantitative":false,"quantitative_p":0.03,"role_probabilities":{"gap":0.0,"method":1.0,"result":0.0,"background":0.0,"limitation":0.0,"future_work":0.0,"contribution":0.0,"interpretation":0.0}},{"i":7,"p":0.95,"id":"s7","own":true,"role":"method","text":"We evaluate SkillSentry on 15 skills across two LLM agents, each paired with two backbone models, i.e., Claude Code with Claude-Haiku-4.5 and Claude-Opus-4.6, and Codex with GPT-5.2 and GPT-5.4.","hedge":{"p":0.86,"label":"asserted"},"own_p":0.95,"main_claim_p":0.03,"quantitative":true,"quantitative_p":0.93,"role_probabilities":{"gap":0.0,"method":0.95,"result":0.01,"background":0.0,"limitation":0.0,"future_work":0.0,"contribution":0.04,"interpretation":0.0}},{"i":8,"p":1.0,"id":"s8","own":true,"role":"result","text":"Our results show that SkillSentry improves the task success rate of LLM agents by 24.1% across skills, on average, while exhibiting lower variability across repeated runs.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.97,"main_claim_p":0.9,"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":1.0,"text":"Our results show that SkillSentry improves the task success rate of LLM agents by 24.1% across skills, on average, while exhibiting lower variability across repeated runs.","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":6975,"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":0.05,"states_limitation":0.11,"human_participants":0.04,"controlled_comparison":0.35,"randomized_assignment":0.02,"states_quantitative_result":0.99,"compares_with_prior_results":0.33,"mentions_code_or_data_availability":0.03},"evidential_basis":{"p":1.0,"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":1.0,"simulation_or_computation":0.0}},"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 address this problem, we propose SkillSentry, a skill-oriented runtime assurance framework built upon a new domain-specific language (DSL) for representing runtime guidance for skill execution.","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":9,"sentences_in_abstract":9},"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"}}}