{"paper":{"title":"Dream-RSI: Recursive Self-Improvement through Evolving Worlds","arxiv_id":"2609.14858","primary_cat":"cs.CL","submitted_at":"2026-09-14T00:10:47+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":"Recursive self-improvement is becoming increasingly vital for autonomous AI agents, where progress hinges on discovering high-value solutions across complex domains.","hedge":{"p":0.98,"label":"asserted"},"own_p":0.05,"main_claim_p":0.03,"quantitative":false,"quantitative_p":0.09,"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":0.69,"id":"s1","own":false,"role":"background","text":"The driver of this process is effective exploration, however, managing and improving exploration strategies remains a major bottleneck.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.08,"main_claim_p":0.03,"quantitative":false,"quantitative_p":0.06,"role_probabilities":{"gap":0.31,"method":0.0,"result":0.0,"background":0.69,"limitation":0.0,"future_work":0.0,"contribution":0.0,"interpretation":0.0}},{"i":2,"p":0.55,"id":"s2","own":false,"role":"background","text":"Current systems face a fundamental dilemma: fixed strategies fail to adapt as search spaces scale, while online policy optimization requires navigating vast meta-search spaces under delayed and expensive feedback over long-horizon rollouts.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.06,"main_claim_p":0.03,"quantitative":false,"quantitative_p":0.23,"role_probabilities":{"gap":0.45,"method":0.0,"result":0.0,"background":0.55,"limitation":0.0,"future_work":0.0,"contribution":0.0,"interpretation":0.0}},{"i":3,"p":1.0,"id":"s3","own":true,"role":"contribution","text":"We introduce \\textsc{Dream-RSI}, a framework for scalable and recursively self-improving exploration.","hedge":{"p":0.99,"label":"asserted"},"own_p":0.85,"main_claim_p":0.1,"quantitative":false,"quantitative_p":0.02,"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":4,"p":0.84,"id":"s4","own":true,"role":"method","text":"A lightweight orchestration layer makes exploration explicit and programmable while leaving the underlying coding agent unchanged.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.76,"main_claim_p":0.04,"quantitative":false,"quantitative_p":0.08,"role_probabilities":{"gap":0.0,"method":0.84,"result":0.0,"background":0.0,"limitation":0.0,"future_work":0.0,"contribution":0.16,"interpretation":0.0}},{"i":5,"p":0.5,"id":"s5","own":true,"role":"method","text":"Our key insight is that accumulated discovery history can serve as a replay simulator over the realized search space.","hedge":{"p":0.96,"label":"asserted"},"own_p":0.52,"main_claim_p":0.12,"quantitative":false,"quantitative_p":0.03,"role_probabilities":{"gap":0.0,"method":0.5,"result":0.0,"background":0.0,"limitation":0.0,"future_work":0.0,"contribution":0.49,"interpretation":0.01}},{"i":6,"p":0.98,"id":"s6","own":true,"role":"method","text":"By performing dreaming in the replay simulator constructed from historical discovery trees, \\textsc{Dream-RSI} secures immediate, low-cost off-policy feedback to evaluate and refine exploration policies without invoking repetitive, expensive online evaluations.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.85,"main_claim_p":0.19,"quantitative":false,"quantitative_p":0.32,"role_probabilities":{"gap":0.0,"method":0.98,"result":0.0,"background":0.0,"limitation":0.0,"future_work":0.0,"contribution":0.02,"interpretation":0.0}},{"i":7,"p":0.99,"id":"s7","own":true,"role":"method","text":"The improved policy is subsequently redeployed online to drive further discovery, continuously expanding the simulator pool in a self-improving loop.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.76,"main_claim_p":0.1,"quantitative":false,"quantitative_p":0.03,"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":8,"p":1.0,"id":"s8","own":true,"role":"result","text":"Across algorithm engineering, mathematical optimization, and GPU kernel engineering, \\textsc{Dream-RSI} achieves competitive or improved discovery quality while substantially reducing discovery cost in several settings.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.94,"main_claim_p":0.76,"quantitative":true,"quantitative_p":0.76,"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":"Across algorithm engineering, mathematical optimization, and GPU kernel engineering, \\textsc{Dream-RSI} achieves competitive or improved discovery quality while substantially reducing discovery cost in several settings.","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":6881,"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":0.11,"human_participants":0.03,"controlled_comparison":0.18,"randomized_assignment":0.01,"states_quantitative_result":0.06,"compares_with_prior_results":0.68,"mentions_code_or_data_availability":0.04},"evidential_basis":{"p":0.73,"value":"observation or experiment","probabilities":{"argument":0.01,"literature":0.0,"proof_or_derivation":0.0,"analysis_of_existing_data":0.0,"observation_or_experiment":0.73,"simulation_or_computation":0.26}},"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":0.91,"text":"We introduce \\textsc{Dream-RSI}, a framework for scalable and recursively self-improving exploration.","location":"abstract s3"}},"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"}}}