{"id":"https://openalex.org/W7128767543","doi":"https://doi.org/10.48550/arxiv.2602.11551","title":"SIGHT: Reinforcement Learning with Self-Evidence and Information-Gain Diverse Branching for Search Agent","display_name":"SIGHT: Reinforcement Learning with Self-Evidence and Information-Gain Diverse Branching for Search Agent","publication_year":2026,"publication_date":"2026-02-12","ids":{"openalex":"https://openalex.org/W7128767543","doi":"https://doi.org/10.48550/arxiv.2602.11551"},"language":null,"primary_location":{"id":"pmh:doi:10.48550/arxiv.2602.11551","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"publisher-specific-oa","license_id":"https://openalex.org/licenses/publisher-specific-oa","version":"submittedVersion","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":null,"any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5124221044","display_name":"Wenlin Zhong","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Zhong, Wenlin","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125923675","display_name":"Jinluan Yang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yang, Jinluan","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125943119","display_name":"Yiquan Wu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wu, Yiquan","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125981363","display_name":"Yi Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Yi","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125904303","display_name":"Jianhang Yao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yao, Jianhang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5125953477","display_name":"Kun Kuang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kuang, Kun","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5124221044"],"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":0.7767000198364258,"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":0.7767000198364258,"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/T13274","display_name":"Expert finding and Q&A systems","score":0.04529999941587448,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.03550000116229057,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7229999899864197},{"id":"https://openalex.org/keywords/correctness","display_name":"Correctness","score":0.6191999912261963},{"id":"https://openalex.org/keywords/sight","display_name":"Sight","score":0.5065000057220459},{"id":"https://openalex.org/keywords/redundancy","display_name":"Redundancy (engineering)","score":0.41940000653266907},{"id":"https://openalex.org/keywords/search-algorithm","display_name":"Search algorithm","score":0.4169999957084656},{"id":"https://openalex.org/keywords/autonomous-agent","display_name":"Autonomous agent","score":0.3765000104904175},{"id":"https://openalex.org/keywords/branching","display_name":"Branching (polymer chemistry)","score":0.3059000074863434}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7229999899864197},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6330999732017517},{"id":"https://openalex.org/C55439883","wikidata":"https://www.wikidata.org/wiki/Q360812","display_name":"Correctness","level":2,"score":0.6191999912261963},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5618000030517578},{"id":"https://openalex.org/C1517167","wikidata":"https://www.wikidata.org/wiki/Q1134322","display_name":"Sight","level":2,"score":0.5065000057220459},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.46779999136924744},{"id":"https://openalex.org/C152124472","wikidata":"https://www.wikidata.org/wiki/Q1204361","display_name":"Redundancy (engineering)","level":2,"score":0.41940000653266907},{"id":"https://openalex.org/C125583679","wikidata":"https://www.wikidata.org/wiki/Q755673","display_name":"Search algorithm","level":2,"score":0.4169999957084656},{"id":"https://openalex.org/C13687954","wikidata":"https://www.wikidata.org/wiki/Q4826847","display_name":"Autonomous agent","level":2,"score":0.3765000104904175},{"id":"https://openalex.org/C206175624","wikidata":"https://www.wikidata.org/wiki/Q595731","display_name":"Branching (polymer chemistry)","level":2,"score":0.3059000074863434},{"id":"https://openalex.org/C46686674","wikidata":"https://www.wikidata.org/wiki/Q466303","display_name":"Boosting (machine learning)","level":2,"score":0.2948000133037567},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.2935999929904938},{"id":"https://openalex.org/C201789804","wikidata":"https://www.wikidata.org/wiki/Q2362762","display_name":"Search problem","level":2,"score":0.2847000062465668},{"id":"https://openalex.org/C19889080","wikidata":"https://www.wikidata.org/wiki/Q2835852","display_name":"Beam search","level":3,"score":0.27869999408721924},{"id":"https://openalex.org/C527412718","wikidata":"https://www.wikidata.org/wiki/Q855395","display_name":"Interpretation (philosophy)","level":2,"score":0.2635999917984009},{"id":"https://openalex.org/C46011968","wikidata":"https://www.wikidata.org/wiki/Q830527","display_name":"Best-first search","level":4,"score":0.25529998540878296}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:doi:10.48550/arxiv.2602.11551","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"publisher-specific-oa","license_id":"https://openalex.org/licenses/publisher-specific-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"},{"id":"doi:10.48550/arxiv.2602.11551","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2602.11551","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":"pmh:doi:10.48550/arxiv.2602.11551","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"publisher-specific-oa","license_id":"https://openalex.org/licenses/publisher-specific-oa","version":"submittedVersion","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":{"Reinforcement":[0],"Learning":[1],"(RL)":[2],"has":[3],"empowered":[4],"Large":[5],"Language":[6],"Models":[7],"(LLMs)":[8],"to":[9,56,97,120],"master":[10],"autonomous":[11],"search":[12,21,29,84,167],"for":[13],"complex":[14,162],"question":[15],"answering.":[16],"However,":[17],"particularly":[18,160],"within":[19],"multi-turn":[20],"scenarios,":[22,164],"this":[23],"interaction":[24],"introduces":[25],"a":[26,67],"critical":[27],"challenge:":[28],"results":[30,85],"often":[31],"suffer":[32],"from":[33],"high":[34],"redundancy":[35],"and":[36,77,91,130,149],"low":[37],"signal-to-noise":[38],"ratios.":[39],"Consequently,":[40],"agents":[41],"easily":[42],"fall":[43],"into":[44,86],"\"Tunnel":[45],"Vision,\"":[46],"where":[47,101],"the":[48],"forced":[49],"interpretation":[50],"of":[51],"early":[52],"noisy":[53],"retrievals":[54],"leads":[55],"irreversible":[57],"error":[58],"accumulation.":[59],"To":[60],"address":[61],"these":[62],"challenges,":[63],"we":[64],"propose":[65],"SIGHT,":[66],"framework":[68],"that":[69,154],"enhances":[70],"search-based":[71],"reasoning":[72,163],"through":[73],"Self-Evidence":[74],"Support":[75],"(SES)":[76],"Information-Gain":[78],"Driven":[79],"Diverse":[80],"Branching.":[81],"SIGHT":[82,138,155],"distills":[83],"high-fidelity":[87],"evidence":[88],"via":[89,133],"SES":[90,129],"calculates":[92],"an":[93],"Information":[94],"Gain":[95],"score":[96,107],"pinpoint":[98],"pivotal":[99],"states":[100],"observations":[102],"maximally":[103],"reduce":[104],"uncertainty.":[105],"This":[106],"guides":[108],"Dynamic":[109],"Prompting":[110],"Interventions":[111],"-":[112,119],"including":[113],"de-duplication,":[114],"reflection,":[115],"or":[116],"adaptive":[117],"branching":[118],"spawn":[121],"new":[122],"branches":[123],"with":[124],"SES.":[125],"Finally,":[126],"by":[127],"integrating":[128],"correctness":[131],"rewards":[132],"Group":[134],"Relative":[135],"Policy":[136],"Optimization,":[137],"internalizes":[139],"robust":[140],"exploration":[141],"strategies":[142],"without":[143],"external":[144],"verifiers.":[145],"Experiments":[146],"on":[147],"single-hop":[148],"multi-hop":[150],"QA":[151],"benchmarks":[152],"demonstrate":[153],"significantly":[156],"outperforms":[157],"existing":[158],"approaches,":[159],"in":[161],"using":[165],"fewer":[166],"steps.":[168]},"counts_by_year":[],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2026-02-14T00:00:00"}