{"id":"https://openalex.org/W7127299652","doi":"https://doi.org/10.48550/arxiv.2602.02488","title":"RLAnything: Forge Environment, Policy, and Reward Model in Completely Dynamic RL System","display_name":"RLAnything: Forge Environment, Policy, and Reward Model in Completely Dynamic RL System","publication_year":2026,"publication_date":"2026-02-02","ids":{"openalex":"https://openalex.org/W7127299652","doi":"https://doi.org/10.48550/arxiv.2602.02488"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2602.02488","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2602.02488","pdf_url":"https://arxiv.org/pdf/2602.02488","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2602.02488","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5128856129","display_name":"Yinjie Wang","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Yinjie","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5122247320","display_name":"Tianbao Xie","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xie, Tianbao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125699539","display_name":"Ke Shen","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shen, Ke","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125037424","display_name":"Mengdi Wang","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Mengdi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5124934452","display_name":"Ling Yang","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yang, Ling","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":21,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9961000084877014,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9961000084877014,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10906","display_name":"AI-based Problem Solving and Planning","score":0.0006000000284984708,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.0003000000142492354,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"reinforcement learning","score":0.5099999904632568},{"id":"https://openalex.org/keywords/reward-modeling","display_name":"reward modeling","score":0.593999981880188},{"id":"https://openalex.org/keywords/dynamic-environment-adaptation","display_name":"dynamic environment adaptation","score":0.4959999918937683},{"id":"https://openalex.org/keywords/closed-loop-optimization","display_name":"closed-loop optimization","score":0.8550000190734863},{"id":"https://openalex.org/keywords/policy-training","display_name":"policy training","score":0.4059999883174896},{"id":"https://openalex.org/keywords/large-language-models","display_name":"large language models","score":0.8349999785423279},{"id":"https://openalex.org/keywords/agentic-agents","display_name":"agentic agents","score":0.6230000257492065},{"id":"https://openalex.org/keywords/qwen","display_name":"Qwen","score":0.3880000114440918},{"id":"https://openalex.org/keywords/alfworld","display_name":"ALFWorld","score":0.9829999804496765}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7886999845504761},{"id":"https://openalex.org/C46686674","wikidata":"https://www.wikidata.org/wiki/Q466303","display_name":"Boosting (machine learning)","level":2,"score":0.6650999784469604},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6582000255584717},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.5595999956130981},{"id":"https://openalex.org/C148220186","wikidata":"https://www.wikidata.org/wiki/Q7111912","display_name":"Outcome (game theory)","level":2,"score":0.5325999855995178},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4749999940395355},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.45669999718666077},{"id":"https://openalex.org/C2779436431","wikidata":"https://www.wikidata.org/wiki/Q30672407","display_name":"Policy learning","level":2,"score":0.45179998874664307},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.38260000944137573},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.3801000118255615},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.35670000314712524},{"id":"https://openalex.org/C196340769","wikidata":"https://www.wikidata.org/wiki/Q7698910","display_name":"Temporal difference learning","level":3,"score":0.33489999175071716},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.29350000619888306},{"id":"https://openalex.org/C2778157309","wikidata":"https://www.wikidata.org/wiki/Q40558","display_name":"Forge","level":3,"score":0.26899999380111694},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.2653000056743622},{"id":"https://openalex.org/C70153297","wikidata":"https://www.wikidata.org/wiki/Q5591907","display_name":"Gradient boosting","level":3,"score":0.2572999894618988}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2602.02488","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2602.02488","pdf_url":"https://arxiv.org/pdf/2602.02488","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2602.02488","doi":"https://doi.org/10.48550/arxiv.2602.02488","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2602.02488","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2602.02488","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2602.02488","pdf_url":"https://arxiv.org/pdf/2602.02488","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7127299652.pdf","grobid_xml":"https://content.openalex.org/works/W7127299652.grobid-xml"},"referenced_works_count":50,"referenced_works":["https://openalex.org/W2736601468","https://openalex.org/W2908510526","https://openalex.org/W3126325318","https://openalex.org/W3185826690","https://openalex.org/W4226287673","https://openalex.org/W4385327683","https://openalex.org/W4390963096","https://openalex.org/W4391631327","https://openalex.org/W4391710008","https://openalex.org/W4392822190","https://openalex.org/W4392974124","https://openalex.org/W4400141990","https://openalex.org/W4402705340","https://openalex.org/W4404783749","https://openalex.org/W4405655184","https://openalex.org/W4405767809","https://openalex.org/W4406755521","https://openalex.org/W4406774573","https://openalex.org/W4407248372","https://openalex.org/W4414281281","https://openalex.org/W4414757783","https://openalex.org/W4414939355","https://openalex.org/W4415057817","https://openalex.org/W4415136385","https://openalex.org/W4415277533","https://openalex.org/W4415317947","https://openalex.org/W4415327992","https://openalex.org/W4415334781","https://openalex.org/W4416021968","https://openalex.org/W4416034026","https://openalex.org/W4416123545","https://openalex.org/W4416123555","https://openalex.org/W4416159291","https://openalex.org/W4416190659","https://openalex.org/W4416374533","https://openalex.org/W4416780398","https://openalex.org/W4417055076","https://openalex.org/W4417065331","https://openalex.org/W4417100144","https://openalex.org/W4417422257","https://openalex.org/W6891877852","https://openalex.org/W7081987674","https://openalex.org/W7117126565","https://openalex.org/W7117567362","https://openalex.org/W7117716024","https://openalex.org/W7123291603","https://openalex.org/W7125497175","https://openalex.org/W7138024215","https://openalex.org/W7196953391","https://openalex.org/W7197047016"],"related_works":["https://openalex.org/W7165037346","https://openalex.org/W7165033905","https://openalex.org/W7133342563","https://openalex.org/W4407632903","https://openalex.org/W4412489912","https://openalex.org/W4414760658","https://openalex.org/W4392974124","https://openalex.org/W4415037845","https://openalex.org/W4377927976","https://openalex.org/W7115575239"],"abstract_inverted_index":{"We":[0,126],"propose":[1],"RLAnything,":[2],"a":[3],"reinforcement":[4],"learning":[5,19,85],"framework":[6],"that":[7,128,134],"dynamically":[8],"forges":[9],"environment,":[10],"policy,":[11],"and":[12,21,43,75,97,106,115,119,123],"reward":[13,48,74],"models":[14,77],"through":[15],"closed-loop":[16],"optimization,":[17],"amplifying":[18],"signals":[20,131],"strengthening":[22],"the":[23,34,47,73,94],"overall":[24,95],"RL":[25],"system":[26],"for":[27,71],"any":[28],"LLM":[29,105],"or":[30],"agentic":[31,107],"scenarios.":[32],"Specifically,":[33],"policy":[35,61,76],"is":[36,50],"trained":[37],"with":[38],"integrated":[39],"feedback":[40,81],"from":[41,82,86],"step-wise":[42],"outcome":[44],"signals,":[45],"while":[46],"model":[49],"jointly":[51],"optimized":[52,129],"via":[53],"consistency":[54],"feedback,":[55],"which":[56],"in":[57],"turn":[58],"further":[59],"improves":[60,69,93],"training.":[62],"Moreover,":[63],"our":[64],"theory-motivated":[65],"automatic":[66],"environment":[67],"adaptation":[68],"training":[70],"both":[72],"by":[78,111,117],"leveraging":[79],"critic":[80],"each,":[83],"enabling":[84],"experience.":[87],"Empirically,":[88],"each":[89],"added":[90],"component":[91],"consistently":[92],"system,":[96],"RLAnything":[98],"yields":[99],"substantial":[100],"gains":[101],"across":[102],"various":[103],"representative":[104],"tasks,":[108],"boosting":[109],"Qwen3-VL-8B-Thinking":[110],"9.1%":[112],"on":[113,121,136],"OSWorld":[114],"Qwen2.5-7B-Instruct":[116],"18.7%":[118],"11.9%":[120],"AlfWorld":[122],"LiveBench,":[124],"respectively.":[125],"also":[127],"reward-model":[130],"outperform":[132],"outcomes":[133],"rely":[135],"human":[137],"labels.":[138],"Code:":[139],"https://github.com/Gen-Verse/Open-AgentRL":[140]},"counts_by_year":[{"year":2026,"cited_by_count":21}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-02-04T00:00:00"}