{"id":"https://openalex.org/W7214723760","doi":"https://doi.org/10.48550/arxiv.2609.34805","title":"SIPO: Selective-Inference Policy Optimization for Tree-Structured Agentic RL","display_name":"SIPO: Selective-Inference Policy Optimization for Tree-Structured Agentic RL","publication_year":2026,"publication_date":"2026-09-28","ids":{"openalex":"https://openalex.org/W7214723760","doi":"https://doi.org/10.48550/arxiv.2609.34805"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2609.34805","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.34805","pdf_url":"https://arxiv.org/pdf/2609.34805","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/2609.34805","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5125683832","display_name":"Zenghuang Fu","orcid":"https://orcid.org/0009-0006-0363-7148","observed_orcids":["https://orcid.org/0009-0006-0363-7148"]},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fu, Zenghuang","raw_affiliation_strings":["Institute of Automation , Chinese Academy of Sciences","University of Chinese Academy of Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Automation , Chinese Academy of Sciences","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]},{"raw_affiliation_string":"University of Chinese Academy of Sciences","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5153486753","display_name":"Ningqi Chen","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Chen, Ningqi","raw_affiliation_strings":["The University of Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Hong Kong","institution_ids":["https://openalex.org/I889458895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5099478071","display_name":"Mingda Jia","orcid":"https://orcid.org/0009-0001-7558-4720","observed_orcids":["https://orcid.org/0009-0001-7558-4720"]},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jia, Mingda","raw_affiliation_strings":["Institute of Automation , Chinese Academy of Sciences","University of Chinese Academy of Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Automation , Chinese Academy of Sciences","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]},{"raw_affiliation_string":"University of Chinese Academy of Sciences","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5153480576","display_name":"Xiaofeng Han","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Han, Xiaofeng","raw_affiliation_strings":["Institute of Automation , Chinese Academy of Sciences","University of Chinese Academy of Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Automation , Chinese Academy of Sciences","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]},{"raw_affiliation_string":"University of Chinese Academy of Sciences","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5153526423","display_name":"Zhaoyang Li","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li, Zhaoyang","raw_affiliation_strings":["Peking University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Peking University","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139773949","display_name":"Qiuyuan Ai","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ai, Qiuyuan","raw_affiliation_strings":["Peking University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Peking University","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124024100","display_name":"Zelong Zheng","orcid":"https://orcid.org/0009-0006-2372-6586","observed_orcids":["https://orcid.org/0009-0006-2372-6586"]},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zheng, Zelong","raw_affiliation_strings":["Institute of Automation , Chinese Academy of Sciences","University of Chinese Academy of Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Automation , Chinese Academy of Sciences","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]},{"raw_affiliation_string":"University of Chinese Academy of Sciences","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5152351570","display_name":"HaoYu Wu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4401726980","display_name":"Mininglamp (China)","ror":"https://ror.org/04tb90x61","country_code":"CN","type":"company","lineage":["https://openalex.org/I4401726980"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wu, Haoyu","raw_affiliation_strings":["Mininglamp Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mininglamp Technology","institution_ids":["https://openalex.org/I4401726980"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101765987","display_name":"Tianyu Fu","orcid":"https://orcid.org/0000-0002-5441-9750","observed_orcids":["https://orcid.org/0000-0002-5441-9750"]},"institutions":[{"id":"https://openalex.org/I4401726980","display_name":"Mininglamp (China)","ror":"https://ror.org/04tb90x61","country_code":"CN","type":"company","lineage":["https://openalex.org/I4401726980"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fu, Tianyu","raw_affiliation_strings":["Mininglamp Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mininglamp Technology","institution_ids":["https://openalex.org/I4401726980"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5144340214","display_name":"Chenxu Zhao","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4401726980","display_name":"Mininglamp (China)","ror":"https://ror.org/04tb90x61","country_code":"CN","type":"company","lineage":["https://openalex.org/I4401726980"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhao, Chenxu","raw_affiliation_strings":["Mininglamp Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mininglamp Technology","institution_ids":["https://openalex.org/I4401726980"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5144317658","display_name":"Minghui Wu","orcid":"https://orcid.org/0009-0001-4577-3002","observed_orcids":["https://orcid.org/0009-0001-4577-3002"]},"institutions":[{"id":"https://openalex.org/I4401726980","display_name":"Mininglamp (China)","ror":"https://ror.org/04tb90x61","country_code":"CN","type":"company","lineage":["https://openalex.org/I4401726980"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wu, Minghui","raw_affiliation_strings":["Mininglamp Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mininglamp Technology","institution_ids":["https://openalex.org/I4401726980"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078098542","display_name":"Guannan He","orcid":"https://orcid.org/0000-0002-5055-076X","observed_orcids":["https://orcid.org/0000-0002-5055-076X"]},"institutions":[{"id":"https://openalex.org/I152269853","display_name":"Qilu University of Technology","ror":"https://ror.org/04hyzq608","country_code":"CN","type":"education","lineage":["https://openalex.org/I152269853"]},{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]},{"id":"https://openalex.org/I4210142748","display_name":"Shandong Academy of Sciences","ror":"https://ror.org/04y8d6y55","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210142748"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"He, Guannan","raw_affiliation_strings":["Peking University","Shandong Computer Science Center , Qilu University of Technology (Shandong Academy of Sciences )"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Peking University","institution_ids":["https://openalex.org/I20231570"]},{"raw_affiliation_string":"Shandong Computer Science Center , Qilu University of Technology (Shandong Academy of Sciences )","institution_ids":["https://openalex.org/I152269853","https://openalex.org/I4210142748"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5079585098","display_name":"Changwei Wang","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Changwei","raw_affiliation_strings":["Key Laboratory of Computing Power Internet and Service Computing , Shandong Fundamental Research Center for Computer Science","Key Laboratory of Computing Power Network and Information Security , Ministry of Education ;"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Key Laboratory of Computing Power Internet and Service Computing , Shandong Fundamental Research Center for Computer Science","institution_ids":[]},{"raw_affiliation_string":"Key Laboratory of Computing Power Network and Information Security , Ministry of Education ;","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":8,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":1,"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":0.9229000210762024,"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":0.9229000210762024,"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/T10286","display_name":"Information Retrieval and Search Behavior","score":0.02410000003874302,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T11574","display_name":"Artificial Intelligence in Games","score":0.014399999752640724,"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/agentic-reinforcement-learning","display_name":"agentic reinforcement learning","score":0.7910000085830688},{"id":"https://openalex.org/keywords/search-agents","display_name":"search agents","score":0.5849999785423279},{"id":"https://openalex.org/keywords/credit-assignment","display_name":"credit assignment","score":0.5419999957084656},{"id":"https://openalex.org/keywords/selective-inference","display_name":"selective inference","score":0.5490000247955322},{"id":"https://openalex.org/keywords/multi-hop-question-answering","display_name":"multi-hop question answering","score":0.7279999852180481},{"id":"https://openalex.org/keywords/large-language-models","display_name":"large language models","score":0.6660000085830688},{"id":"https://openalex.org/keywords/qwen","display_name":"Qwen","score":0.3700000047683716}],"concepts":[{"id":"https://openalex.org/C89128539","wikidata":"https://www.wikidata.org/wiki/Q1949963","display_name":"Statistic","level":2,"score":0.6370000243186951},{"id":"https://openalex.org/C88626702","wikidata":"https://www.wikidata.org/wiki/Q1128903","display_name":"Continuation","level":2,"score":0.5967000126838684},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.588100016117096},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4634000062942505},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.45249998569488525},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.39480000734329224},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3894999921321869},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.37959998846054077},{"id":"https://openalex.org/C164226766","wikidata":"https://www.wikidata.org/wiki/Q7293202","display_name":"Rank (graph theory)","level":2,"score":0.35899999737739563},{"id":"https://openalex.org/C206175624","wikidata":"https://www.wikidata.org/wiki/Q595731","display_name":"Branching (polymer chemistry)","level":2,"score":0.33340001106262207},{"id":"https://openalex.org/C2776291640","wikidata":"https://www.wikidata.org/wiki/Q2912517","display_name":"Value (mathematics)","level":2,"score":0.3278999924659729},{"id":"https://openalex.org/C46686674","wikidata":"https://www.wikidata.org/wiki/Q466303","display_name":"Boosting (machine learning)","level":2,"score":0.3240000009536743},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.31520000100135803},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.3100000023841858},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.2946999967098236},{"id":"https://openalex.org/C2778334786","wikidata":"https://www.wikidata.org/wiki/Q1586270","display_name":"Variation (astronomy)","level":2,"score":0.2928999960422516},{"id":"https://openalex.org/C17648541","wikidata":"https://www.wikidata.org/wiki/Q2265984","display_name":"Efficiency","level":3,"score":0.26420000195503235},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.25619998574256897},{"id":"https://openalex.org/C2779664074","wikidata":"https://www.wikidata.org/wiki/Q3518405","display_name":"Terminal (telecommunication)","level":2,"score":0.2554999887943268},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.2513999938964844}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2609.34805","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.34805","pdf_url":"https://arxiv.org/pdf/2609.34805","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.2609.34805","doi":"https://doi.org/10.48550/arxiv.2609.34805","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2609.34805","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2609.34805","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.34805","pdf_url":"https://arxiv.org/pdf/2609.34805","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/W7214723760.pdf","grobid_xml":"https://content.openalex.org/works/W7214723760.grobid-xml"},"referenced_works_count":28,"referenced_works":["https://openalex.org/W2117897510","https://openalex.org/W4206653471","https://openalex.org/W4391631327","https://openalex.org/W4412945254","https://openalex.org/W4414281281","https://openalex.org/W4417422257","https://openalex.org/W7092298665","https://openalex.org/W7127190146","https://openalex.org/W7128775868","https://openalex.org/W7134953399","https://openalex.org/W7140304544","https://openalex.org/W7154470573","https://openalex.org/W7160662643","https://openalex.org/W7161154181","https://openalex.org/W7164204658","https://openalex.org/W7164422112","https://openalex.org/W7165655450","https://openalex.org/W7165936402","https://openalex.org/W7166809132","https://openalex.org/W7166814628","https://openalex.org/W7166890043","https://openalex.org/W7167709631","https://openalex.org/W7169608443","https://openalex.org/W7169806788","https://openalex.org/W7171778161","https://openalex.org/W7172262398","https://openalex.org/W7172417946","https://openalex.org/W7196957469"],"related_works":["https://openalex.org/W7167709631","https://openalex.org/W7160662643","https://openalex.org/W7077869697","https://openalex.org/W7083493645","https://openalex.org/W7204018933","https://openalex.org/W7215117224","https://openalex.org/W7213583322","https://openalex.org/W7221537839","https://openalex.org/W7204227196","https://openalex.org/W7164235203"],"abstract_inverted_index":{"Tree-structured":[0],"reinforcement":[1],"learning":[2],"trains":[3],"search":[4],"agents":[5],"by":[6,159],"comparing":[7],"alternative":[8],"continuations":[9,97],"and":[10,84,102,112,123,136,144,161,166,179,206],"propagating":[11],"terminal":[12],"rewards":[13],"to":[14],"intermediate":[15],"decisions.":[16],"Adaptive":[17],"expansion,":[18],"however,":[19],"creates":[20],"a":[21,60,88,187,192],"statistical":[22],"asymmetry:":[23],"an":[24],"incumbent":[25,107],"is":[26,43,212],"selected":[27,100],"using":[28,109,133],"its":[29],"own":[30],"generation":[31,82],"statistic,":[32],"whereas":[33],"fresh":[34,96],"siblings":[35],"are":[36],"sampled":[37],"after":[38],"selection.":[39],"When":[40],"that":[41],"statistic":[42],"associated":[44],"with":[45],"return,":[46],"branch":[47,79],"values":[48,108],"can":[49],"reflect":[50],"selection":[51,110,202],"history":[52,203],"as":[53,55],"well":[54],"continuation":[56],"quality,":[57],"even":[58],"for":[59,201],"shared":[61],"parent.":[62],"We":[63],"propose":[64],"Selective-Inference":[65],"Policy":[66],"Optimization":[67],"(\\SIPO{}),":[68],"which":[69],"incorporates":[70],"this":[71],"distinction":[72],"into":[73],"tree-based":[74],"credit":[75],"estimation.":[76],"Its":[77],"scale-free":[78],"criterion":[80],"keeps":[81],"scores":[83],"sibling":[85],"penalties":[86],"on":[87,169],"consistent":[89],"relative":[90],"scale;":[91],"exchangeable":[92],"branching":[93],"supplies":[94],"multiple":[95],"from":[98],"each":[99],"parent;":[101],"order-statistic":[103],"correction":[104],"adjusts":[105],"retained":[106],"rank":[111],"the":[113,120,124,140,148,177],"estimated":[114],"score--outcome":[115],"association.":[116],"These":[117],"mechanisms":[118],"preserve":[119],"leaf":[121],"budget":[122],"host":[125],"policy":[126],"optimisation":[127],"objective.":[128],"Across":[129],"seven":[130,172],"QA":[131],"benchmarks":[132],"Qwen3-4B,":[134],"Qwen3-8B,":[135,152],"Qwen2.5-7B,":[137],"\\SIPO{}":[138],"achieves":[139],"highest":[141],"reported":[142],"multi-hop":[143],"single-hop":[145],"averages":[146,156],"among":[147],"compared":[149],"methods.":[150],"On":[151],"it":[153],"improves":[154],"these":[155,197],"over":[157],"AT\\textsuperscript{2}PO":[158],"$1.31$":[160],"$1.07$":[162],"percentage":[163],"points,":[164],"respectively,":[165],"ranks":[167],"first":[168],"six":[170],"of":[171],"benchmarks.":[173],"Component":[174],"ablations":[175],"evaluate":[176],"individual":[178],"combined":[180],"changes,":[181],"while":[182],"early-training":[183],"paired":[184],"diagnostics":[185],"show":[186],"selected--fresh":[188],"value":[189],"gap":[190],"alongside":[191],"near-zero":[193],"fresh--fresh":[194],"reference.":[195],"Together,":[196],"results":[198],"support":[199],"accounting":[200],"when":[204],"constructing":[205],"evaluating":[207],"search-agent":[208],"rollouts.":[209],"Our":[210],"code":[211],"available":[213],"at":[214],"https://github.com/Zenghuang-Fu/SIPO":[215]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-09-30T00:00:00"}