{"id":"https://openalex.org/W4416353973","doi":"https://doi.org/10.18653/v1/2026.findings-acl.596","title":"CriticSearch: Fine-Grained Credit Assignment for Search Agents via a Retrospective Critic","display_name":"CriticSearch: Fine-Grained Credit Assignment for Search Agents via a Retrospective Critic","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W4416353973","doi":"https://doi.org/10.18653/v1/2026.findings-acl.596"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2026.findings-acl.596","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.596","pdf_url":"https://aclanthology.org/2026.findings-acl.596.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: ACL 2026","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2026.findings-acl.596.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5075511044","display_name":"Yaocheng Zhang","orcid":"https://orcid.org/0000-0001-7201-6368"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yaocheng Zhang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Haohuan Huang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Haohuan Huang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102004420","display_name":"Zijun Song","orcid":"https://orcid.org/0000-0003-3201-0556"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zijun Song","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100553643","display_name":"Zijie Zhao","orcid":"https://orcid.org/0009-0004-9482-8315"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zijie Zhao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049454999","display_name":"Qichao Zhang","orcid":"https://orcid.org/0000-0001-9747-391X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qichao Zhang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Yuanheng Zhu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yuanheng Zhu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5100624298","display_name":"Dongbin Zhao","orcid":"https://orcid.org/0000-0001-8218-9633"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dongbin Zhao","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":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.02467536,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"12272","last_page":"12290"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.4814000129699707,"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":0.4814000129699707,"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":0.2775000035762787,"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/T11273","display_name":"Advanced Graph Neural Networks","score":0.02199999988079071,"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":0.6256999969482422},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.5741999745368958},{"id":"https://openalex.org/keywords/outcome","display_name":"Outcome (game theory)","score":0.5462999939918518},{"id":"https://openalex.org/keywords/trajectory","display_name":"Trajectory","score":0.5166000127792358},{"id":"https://openalex.org/keywords/adaptability","display_name":"Adaptability","score":0.42910000681877136},{"id":"https://openalex.org/keywords/complete-information","display_name":"Complete information","score":0.35910001397132874}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6794000267982483},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6256999969482422},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5996999740600586},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.5741999745368958},{"id":"https://openalex.org/C148220186","wikidata":"https://www.wikidata.org/wiki/Q7111912","display_name":"Outcome (game theory)","level":2,"score":0.5462999939918518},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.5166000127792358},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5113999843597412},{"id":"https://openalex.org/C177606310","wikidata":"https://www.wikidata.org/wiki/Q5674297","display_name":"Adaptability","level":2,"score":0.42910000681877136},{"id":"https://openalex.org/C113336015","wikidata":"https://www.wikidata.org/wiki/Q574010","display_name":"Complete information","level":2,"score":0.35910001397132874},{"id":"https://openalex.org/C125583679","wikidata":"https://www.wikidata.org/wiki/Q755673","display_name":"Search algorithm","level":2,"score":0.319599986076355},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.31200000643730164},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.2985000014305115},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.2847000062465668},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.25600001215934753},{"id":"https://openalex.org/C175309249","wikidata":"https://www.wikidata.org/wiki/Q725864","display_name":"Pipeline transport","level":2,"score":0.251800000667572}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.18653/v1/2026.findings-acl.596","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.596","pdf_url":"https://aclanthology.org/2026.findings-acl.596.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: ACL 2026","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2511.12159","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2511.12159","pdf_url":"https://arxiv.org/pdf/2511.12159","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,"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.2511.12159","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2511.12159","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,"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":"Preprint"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.findings-acl.596","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.596","pdf_url":"https://aclanthology.org/2026.findings-acl.596.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: ACL 2026","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G7285338662","display_name":null,"funder_award_id":"20240484514","funder_id":"https://openalex.org/F4320334978","funder_display_name":"Beijing Nova Program"},{"id":"https://openalex.org/G800914696","display_name":null,"funder_award_id":"62136008","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8179479325","display_name":null,"funder_award_id":"62293541","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320321133","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35"},{"id":"https://openalex.org/F4320334978","display_name":"Beijing Nova Program","ror":"https://ror.org/034k14f91"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4416353973.pdf","grobid_xml":"https://content.openalex.org/works/W4416353973.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Tool-Integrated":[0],"Reasoning":[1],"(TIR)":[2],"with":[3],"search":[4,25],"engines":[5],"enables":[6],"large":[7],"language":[8],"models":[9],"to":[10,43],"iteratively":[11],"retrieve":[12],"up-to-date":[13],"external":[14],"knowledge,":[15],"enhancing":[16],"adaptability":[17],"and":[18,45,81,114],"generalization":[19],"in":[20],"complex":[21],"question-answering":[22],"tasks.However,":[23],"existing":[24,106],"agent":[26],"pipelines":[27],"typically":[28],"depend":[29],"on":[30],"reinforcement":[31],"learning":[32],"based":[33],"optimization,":[34],"which":[35],"often":[36],"suffers":[37],"from":[38,77],"sparse":[39],"outcome":[40],"rewards,":[41],"leading":[42],"inefficient":[44],"unstable":[46],"training.We":[47],"introduce":[48],"CriticSearch,":[49],"a":[50,60,65],"fine-grained":[51],"credit-assignment":[52],"framework":[53],"that":[54,91,102],"supplies":[55],"dense,":[56],"turn-level":[57],"feedback":[58],"via":[59],"retrospective":[61],"critic":[62],"mechanism.During":[63],"training,":[64],"frozen,":[66],"asymmetric":[67],"critique":[68],"LLM":[69],"retrospectively":[70],"evaluates":[71],"each":[72],"turn":[73],"using":[74],"privileged":[75],"information":[76],"the":[78],"full":[79],"trajectory":[80],"gold":[82],"answers,":[83],"converting":[84],"these":[85],"assessments":[86],"into":[87],"stable,":[88],"dense":[89],"rewards":[90],"guide":[92],"policy":[93],"improvement.Experimental":[94],"results":[95],"across":[96],"diverse":[97],"multi-hop":[98],"reasoning":[99],"benchmarks":[100],"demonstrate":[101],"Critic-Search":[103],"consistently":[104],"outperforms":[105],"baselines,":[107],"achieving":[108],"faster":[109],"convergence,":[110],"improved":[111],"training":[112],"stability,":[113],"higher":[115],"performance.":[116]},"counts_by_year":[],"updated_date":"2026-08-05T07:39:15.569665","created_date":"2025-11-19T00:00:00"}