{"paper":{"title":"Position: Agentic Evolution is the Path to Evolving LLMs","arxiv_id":"2602.00359","primary_cat":"cs.AI","submitted_at":"2026-01-30T22:15:58+00:00","version_compiled":"v3"},"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 v3","sentences":[{"i":0,"p":0.93,"id":"s0","own":false,"role":"background","text":"As Large Language Models (LLMs) move from curated training sets into open-ended real-world environments, a fundamental limitation emerges: static training cannot keep pace with continual deployment environment change.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.1,"main_claim_p":0.04,"quantitative":false,"quantitative_p":0.07,"role_probabilities":{"gap":0.06,"method":0.0,"result":0.0,"background":0.93,"limitation":0.01,"future_work":0.0,"contribution":0.0,"interpretation":0.0}},{"i":1,"p":0.8,"id":"s1","own":false,"role":"background","text":"Scaling training-time and inference-time compute improves static capability but does not close this train-deploy gap.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.14,"main_claim_p":0.03,"quantitative":false,"quantitative_p":0.24,"role_probabilities":{"gap":0.14,"method":0.0,"result":0.02,"background":0.8,"limitation":0.03,"future_work":0.0,"contribution":0.0,"interpretation":0.01}},{"i":2,"p":0.3,"id":"s2","own":false,"role":"gap","text":"We argue that addressing this limitation requires a new scaling axis-evolution.","hedge":{"p":0.98,"label":"asserted"},"own_p":0.11,"main_claim_p":0.18,"quantitative":false,"quantitative_p":0.04,"role_probabilities":{"gap":0.3,"method":0.01,"result":0.0,"background":0.13,"limitation":0.0,"future_work":0.12,"contribution":0.29,"interpretation":0.15}},{"i":3,"p":0.68,"id":"s3","own":false,"role":"gap","text":"Existing deployment-time adaptation methods, whether parametric fine-tuning or heuristic memory accumulation, lack the strategic agency needed to diagnose failures and produce durable improvements.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.06,"main_claim_p":0.05,"quantitative":false,"quantitative_p":0.09,"role_probabilities":{"gap":0.68,"method":0.0,"result":0.0,"background":0.3,"limitation":0.02,"future_work":0.0,"contribution":0.0,"interpretation":0.0}},{"i":4,"p":0.53,"id":"s4","own":false,"role":"contribution","text":"Our position is that agentic evolution represents the inevitable future of LLM adaptation, elevating evolution itself from a fixed pipeline to an autonomous evolver agent.","hedge":{"p":0.99,"label":"asserted"},"own_p":0.13,"main_claim_p":0.84,"quantitative":false,"quantitative_p":0.05,"role_probabilities":{"gap":0.01,"method":0.01,"result":0.0,"background":0.01,"limitation":0.0,"future_work":0.18,"contribution":0.53,"interpretation":0.26}},{"i":5,"p":0.66,"id":"s5","own":true,"role":"contribution","text":"We instantiate this vision in a general framework, A-Evolve, which treats deployment-time improvement as a deliberate, goal-directed optimization process over persistent system state.","hedge":{"p":0.99,"label":"asserted"},"own_p":0.88,"main_claim_p":0.12,"quantitative":false,"quantitative_p":0.03,"role_probabilities":{"gap":0.0,"method":0.34,"result":0.0,"background":0.0,"limitation":0.0,"future_work":0.0,"contribution":0.66,"interpretation":0.0}},{"i":6,"p":0.7,"id":"s6","own":false,"role":"interpretation","text":"We further propose the evolution-scaling hypothesis: the capacity for adaptation scales with the compute allocated to evolution, positioning agentic evolution as a scalable path toward sustained, open-ended adaptation in the real world.","hedge":{"p":0.72,"label":"asserted"},"own_p":0.17,"main_claim_p":0.32,"quantitative":false,"quantitative_p":0.14,"role_probabilities":{"gap":0.0,"method":0.01,"result":0.01,"background":0.0,"limitation":0.0,"future_work":0.01,"contribution":0.27,"interpretation":0.7}},{"i":7,"p":0.9,"id":"s7","own":false,"role":"contribution","text":"Our code is publicly available at https://github.com/A-EVO-Lab/a-evolve.","hedge":{"p":0.55,"label":"asserted"},"own_p":0.49,"main_claim_p":0.02,"quantitative":false,"quantitative_p":0.03,"role_probabilities":{"gap":0.0,"method":0.05,"result":0.0,"background":0.01,"limitation":0.0,"future_work":0.04,"contribution":0.9,"interpretation":0.0}}]},"compiled":{"main_claim":{"p":0.96,"text":"Our position is that agentic evolution represents the inevitable future of LLM adaptation, elevating evolution itself from a fixed pipeline to an autonomous evolver agent.","location":"abstract s4","hedge_strength":{"p":0.99,"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":6198,"cost_usd_reported":0.0},"compiled_at":"2026-11-06","bank_version":"abstract-p1-20260923","model_version":"classifier-1.13.0","abstract_states":{"claims_first":0.09,"states_limitation":0.1,"human_participants":0.04,"controlled_comparison":0.05,"randomized_assignment":0.01,"states_quantitative_result":0.02,"compares_with_prior_results":0.29,"mentions_code_or_data_availability":0.98},"evidential_basis":{"p":1.0,"value":"argument","probabilities":{"argument":1.0,"literature":0.0,"proof_or_derivation":0.0,"analysis_of_existing_data":0.0,"observation_or_experiment":0.0,"simulation_or_computation":0.0}},"contribution_type":{"p":0.97,"value":"position or commentary","probabilities":{"review":0.0,"method_or_tool":0.03,"empirical_study":0.0,"simulation_study":0.0,"theoretical_result":0.0,"dataset_or_benchmark":0.0,"position_or_commentary":0.97}},"contribution_statement":{"p":1.0,"text":"We instantiate this vision in a general framework, A-Evolve, which treats deployment-time improvement as a deliberate, goal-directed optimization process over persistent system state.","location":"abstract s5"}},"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 v3"],"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"}}}