{"id":"https://openalex.org/W7155049688","doi":"https://doi.org/10.48550/arxiv.2604.17337","title":"AutoSearch: Adaptive Search Depth for Efficient Agentic RAG via Reinforcement Learning","display_name":"AutoSearch: Adaptive Search Depth for Efficient Agentic RAG via Reinforcement Learning","publication_year":2026,"publication_date":"2026-04-19","ids":{"openalex":"https://openalex.org/W7155049688","doi":"https://doi.org/10.48550/arxiv.2604.17337"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2604.17337","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.17337","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":"article"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2604.17337","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5134203534","display_name":"Jingbo Sun","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sun, Jingbo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134133942","display_name":"Wenyue Chong","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chong, Wenyue","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134116434","display_name":"Songjun Tu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tu, Songjun","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134111747","display_name":"Qichao Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Qichao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134128978","display_name":"Yaocheng Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Yaocheng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134163547","display_name":"Jiajun Chai","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chai, Jiajun","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134150151","display_name":"Xiaohan Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Xiaohan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134106072","display_name":"Wei Lin","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lin, Wei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134120977","display_name":"Guojun Yin","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yin, Guojun","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5134212393","display_name":"Dongbin Zhao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhao, Dongbin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":10,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"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/T10028","display_name":"Topic Modeling","score":0.7224000096321106,"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/T10028","display_name":"Topic Modeling","score":0.7224000096321106,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.07509999722242355,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T13274","display_name":"Expert finding and Q&A systems","score":0.028999999165534973,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.691100001335144},{"id":"https://openalex.org/keywords/beam-search","display_name":"Beam search","score":0.5608000159263611},{"id":"https://openalex.org/keywords/search-algorithm","display_name":"Search algorithm","score":0.5504999756813049},{"id":"https://openalex.org/keywords/bidirectional-search","display_name":"Bidirectional search","score":0.5493999719619751},{"id":"https://openalex.org/keywords/incremental-heuristic-search","display_name":"Incremental heuristic search","score":0.519599974155426},{"id":"https://openalex.org/keywords/search-cost","display_name":"Search cost","score":0.5131999850273132},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.49790000915527344}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.691100001335144},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6301000118255615},{"id":"https://openalex.org/C19889080","wikidata":"https://www.wikidata.org/wiki/Q2835852","display_name":"Beam search","level":3,"score":0.5608000159263611},{"id":"https://openalex.org/C125583679","wikidata":"https://www.wikidata.org/wiki/Q755673","display_name":"Search algorithm","level":2,"score":0.5504999756813049},{"id":"https://openalex.org/C831591","wikidata":"https://www.wikidata.org/wiki/Q59750","display_name":"Bidirectional search","level":5,"score":0.5493999719619751},{"id":"https://openalex.org/C139979381","wikidata":"https://www.wikidata.org/wiki/Q17056021","display_name":"Incremental heuristic search","level":4,"score":0.519599974155426},{"id":"https://openalex.org/C21782646","wikidata":"https://www.wikidata.org/wiki/Q841666","display_name":"Search cost","level":2,"score":0.5131999850273132},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5034999847412109},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.49790000915527344},{"id":"https://openalex.org/C201789804","wikidata":"https://www.wikidata.org/wiki/Q2362762","display_name":"Search problem","level":2,"score":0.4846999943256378},{"id":"https://openalex.org/C14362708","wikidata":"https://www.wikidata.org/wiki/Q1675274","display_name":"Iterative deepening depth-first search","level":5,"score":0.4544999897480011},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.40709999203681946},{"id":"https://openalex.org/C46011968","wikidata":"https://www.wikidata.org/wiki/Q830527","display_name":"Best-first search","level":4,"score":0.38359999656677246},{"id":"https://openalex.org/C126661757","wikidata":"https://www.wikidata.org/wiki/Q4925641","display_name":"Random search","level":2,"score":0.3091000020503998},{"id":"https://openalex.org/C97854310","wikidata":"https://www.wikidata.org/wiki/Q19541","display_name":"Search engine","level":2,"score":0.30000001192092896},{"id":"https://openalex.org/C179799912","wikidata":"https://www.wikidata.org/wiki/Q205084","display_name":"Computational complexity theory","level":2,"score":0.2838999927043915},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.2590999901294708}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2604.17337","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.17337","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2604.17337","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.17337","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":"article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Agentic":[0],"retrieval-augmented":[1],"generation":[2],"(RAG)":[3],"systems":[4],"enable":[5],"large":[6],"language":[7],"models":[8],"(LLMs)":[9],"to":[10,47,54,137],"solve":[11],"complex":[12,57,146],"tasks":[13],"through":[14],"multi-step":[15,23],"interaction":[16,24],"with":[17],"external":[18],"retrieval":[19],"tools.":[20],"However,":[21],"such":[22],"often":[25,52],"involves":[26],"redundant":[27],"search":[28,39,45,66,75,103,118,123,139,165],"steps,":[29],"incurring":[30],"substantial":[31],"computational":[32],"cost":[33],"and":[34,70,87,120,141],"latency.":[35],"Prior":[36],"work":[37],"limits":[38],"depth":[40,67,76,119],"(i.e.,":[41],"the":[42,88,115],"number":[43],"of":[44,56],"steps)":[46],"reduce":[48],"cost,":[49],"but":[50],"this":[51],"leads":[53],"underexploration":[55],"questions.":[58,147],"To":[59],"address":[60],"this,":[61],"we":[62,92],"first":[63],"investigate":[64],"how":[65],"affects":[68],"accuracy":[69],"find":[71],"a":[72,95,110,157],"minimal":[73,116],"sufficient":[74,117],"that":[77,100,154],"defines":[78],"an":[79],"accuracy-efficiency":[80,159],"trade-off,":[81,160],"jointly":[82],"determined":[83],"by":[84,124],"question":[85],"complexity":[86],"agent's":[89],"capability.":[90],"Furthermore,":[91],"propose":[93],"AutoSearch,":[94],"reinforcement":[96],"learning":[97],"(RL)":[98],"framework":[99],"evaluates":[101],"each":[102],"step":[104],"via":[105],"self-generated":[106],"intermediate":[107],"answers.":[108],"By":[109],"self-answering":[111],"mechanism,":[112],"AutoSearch":[113,155],"identifies":[114],"promotes":[121],"efficient":[122],"rewarding":[125],"its":[126],"attainment":[127],"while":[128,163],"penalizing":[129],"over-searching.":[130],"In":[131],"addition,":[132],"reward":[133],"mechanisms":[134],"are":[135],"introduced":[136],"stabilize":[138],"behavior":[140],"improve":[142],"answer":[143],"quality":[144],"on":[145,150],"Extensive":[148],"experiments":[149],"multiple":[151],"benchmarks":[152],"show":[153],"achieves":[156],"superior":[158],"alleviating":[161],"over-searching":[162],"preserving":[164],"quality.":[166]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-04-22T00:00:00"}