{"paper":{"title":"EvoHarnessBench: Can Your Agents Keep Pace with an Evolving Harness?","arxiv_id":"2609.04280","primary_cat":"cs.MA","submitted_at":"2026-09-03T03:24:02+00:00","version_compiled":"v2"},"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 v2","sentences":[{"i":0,"p":1.0,"id":"s0","own":false,"role":"background","text":"Modern LLM-based agents operate through a harness of tools, reusable skills, and specialist agents that shapes what they observe and what they can do.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.05,"main_claim_p":0.02,"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":"In practice, this harness continually evolves as new capabilities are added.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.07,"main_claim_p":0.02,"quantitative":false,"quantitative_p":0.03,"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":1.0,"id":"s2","own":true,"role":"contribution","text":"We introduce EVOHARNESSBENCH, a benchmark for evaluating agents under controlled harness evolution across three axes (tools, skills, and agents).","hedge":{"p":0.99,"label":"asserted"},"own_p":0.92,"main_claim_p":0.05,"quantitative":false,"quantitative_p":0.08,"role_probabilities":{"gap":0.0,"method":0.0,"result":0.0,"background":0.0,"limitation":0.0,"future_work":0.0,"contribution":1.0,"interpretation":0.0}},{"i":3,"p":0.84,"id":"s3","own":false,"role":"contribution","text":"Unlike existing continual-learning benchmarks for agents, which typically place non-stationarity (i.e., what changes over time) in the task stream while keeping the harness fixed, EVOHARNESSBENCH places non-stationarity in the externally supplied harness itself.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.44,"main_claim_p":0.05,"quantitative":true,"quantitative_p":0.5,"role_probabilities":{"gap":0.13,"method":0.02,"result":0.0,"background":0.01,"limitation":0.0,"future_work":0.0,"contribution":0.84,"interpretation":0.0}},{"i":4,"p":0.85,"id":"s4","own":true,"role":"method","text":"It contains 17 multi-stage harness streams constructed deterministically from verifier-based benchmarks, comprising 802 tasks, 520 tools, 42 skills, and 62 agents.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.9,"main_claim_p":0.03,"quantitative":true,"quantitative_p":0.99,"role_probabilities":{"gap":0.0,"method":0.85,"result":0.0,"background":0.0,"limitation":0.0,"future_work":0.0,"contribution":0.15,"interpretation":0.0}},{"i":5,"p":0.82,"id":"s5","own":true,"role":"method","text":"We evaluate two complementary settings corresponding to the central challenges of harness evolution: deployment evaluation, which isolates retention of previously accessible competence as the harness expands, and self-evolving adaptation evaluation, which tests whether accumulated experience remains useful as new capabilities are introduced.","hedge":{"p":0.97,"label":"asserted"},"own_p":0.82,"main_claim_p":0.05,"quantitative":false,"quantitative_p":0.14,"role_probabilities":{"gap":0.0,"method":0.82,"result":0.0,"background":0.0,"limitation":0.0,"future_work":0.0,"contribution":0.18,"interpretation":0.0}},{"i":6,"p":0.98,"id":"s6","own":true,"role":"result","text":"Our results reveal three persistent gaps.","hedge":{"p":0.98,"label":"asserted"},"own_p":0.92,"main_claim_p":0.08,"quantitative":true,"quantitative_p":0.6,"role_probabilities":{"gap":0.0,"method":0.0,"result":0.98,"background":0.0,"limitation":0.0,"future_work":0.0,"contribution":0.01,"interpretation":0.01}},{"i":7,"p":0.99,"id":"s7","own":true,"role":"result","text":"First, harness expansion alone can degrade performance on previously solved tasks, producing harness-induced forgetting.","hedge":{"p":0.89,"label":"asserted"},"own_p":0.91,"main_claim_p":0.13,"quantitative":false,"quantitative_p":0.13,"role_probabilities":{"gap":0.01,"method":0.0,"result":0.99,"background":0.0,"limitation":0.0,"future_work":0.0,"contribution":0.0,"interpretation":0.0}},{"i":8,"p":0.96,"id":"s8","own":true,"role":"result","text":"Second, gains from self-evolving adaptation remain inconsistent across stages of harness evolution, capability axes, and environments.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.93,"main_claim_p":0.09,"quantitative":false,"quantitative_p":0.13,"role_probabilities":{"gap":0.04,"method":0.0,"result":0.96,"background":0.0,"limitation":0.0,"future_work":0.0,"contribution":0.0,"interpretation":0.0}},{"i":9,"p":0.93,"id":"s9","own":true,"role":"result","text":"Third, retention and adaptation can pull in different directions: preserving earlier competence does not necessarily improve adaptation to newly introduced capabilities, and vice versa.","hedge":{"p":0.88,"label":"asserted"},"own_p":0.92,"main_claim_p":0.17,"quantitative":false,"quantitative_p":0.36,"role_probabilities":{"gap":0.01,"method":0.0,"result":0.93,"background":0.0,"limitation":0.0,"future_work":0.0,"contribution":0.0,"interpretation":0.06}},{"i":10,"p":1.0,"id":"s10","own":true,"role":"interpretation","text":"These results establish harness evolution as a distinct challenge for building agents that can keep pace with an evolving harness while preserving previously effective behavior.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.8,"main_claim_p":0.9,"quantitative":false,"quantitative_p":0.05,"role_probabilities":{"gap":0.0,"method":0.0,"result":0.0,"background":0.0,"limitation":0.0,"future_work":0.0,"contribution":0.0,"interpretation":1.0}}]},"compiled":{"main_claim":{"p":1.0,"text":"These results establish harness evolution as a distinct challenge for building agents that can keep pace with an evolving harness while preserving previously effective behavior.","location":"abstract s10","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":8198,"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":0.26,"states_limitation":0.34,"human_participants":0.03,"controlled_comparison":0.23,"randomized_assignment":0.02,"states_quantitative_result":0.83,"compares_with_prior_results":0.37,"mentions_code_or_data_availability":0.05},"evidential_basis":{"p":0.98,"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":0.98,"simulation_or_computation":0.02}},"contribution_type":{"p":1.0,"value":"dataset or benchmark","probabilities":{"review":0.0,"method_or_tool":0.0,"empirical_study":0.0,"simulation_study":0.0,"theoretical_result":0.0,"dataset_or_benchmark":1.0,"position_or_commentary":0.0}},"contribution_statement":{"p":0.97,"text":"We introduce EVOHARNESSBENCH, a benchmark for evaluating agents under controlled harness evolution across three axes (tools, skills, and agents).","location":"abstract s2"}},"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 v2"],"levels_not_run":["S sections","T body sentences","C citations","R cross-paper relations"],"sentences_examined":11,"sentences_in_abstract":11},"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"}}}