{"id":"https://openalex.org/W7163218199","doi":"https://doi.org/10.48550/arxiv.2606.00590","title":"Critic-R: Improving Agentic Search using Instruction-tuned Retrievers with Natural Language Introspective Feedback","display_name":"Critic-R: Improving Agentic Search using Instruction-tuned Retrievers with Natural Language Introspective Feedback","publication_year":2026,"publication_date":"2026-05-30","ids":{"openalex":"https://openalex.org/W7163218199","doi":"https://doi.org/10.48550/arxiv.2606.00590"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2606.00590","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.00590","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":"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"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2606.00590","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5137620343","display_name":"Md Zarif Ul Alam","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Alam, Md Zarif Ul","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082594835","display_name":"Alireza Salemi","orcid":"https://orcid.org/0009-0006-1937-2615"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Salemi, Alireza","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5137667914","display_name":"Hamed Zamani","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zamani, Hamed","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":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/T10286","display_name":"Information Retrieval and Search Behavior","score":0.7333999872207642,"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"}},"topics":[{"id":"https://openalex.org/T10286","display_name":"Information Retrieval and Search Behavior","score":0.7333999872207642,"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/T10028","display_name":"Topic Modeling","score":0.10570000112056732,"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":0.09210000187158585,"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/inference","display_name":"Inference","score":0.6765000224113464},{"id":"https://openalex.org/keywords/relevance","display_name":"Relevance (law)","score":0.6136000156402588},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5637999773025513},{"id":"https://openalex.org/keywords/introspection","display_name":"Introspection","score":0.5001000165939331},{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.49779999256134033},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.45019999146461487},{"id":"https://openalex.org/keywords/query-expansion","display_name":"Query expansion","score":0.40220001339912415},{"id":"https://openalex.org/keywords/relevance-feedback","display_name":"Relevance feedback","score":0.37529999017715454}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7745000123977661},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6765000224113464},{"id":"https://openalex.org/C158154518","wikidata":"https://www.wikidata.org/wiki/Q7310970","display_name":"Relevance (law)","level":2,"score":0.6136000156402588},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5637999773025513},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5400999784469604},{"id":"https://openalex.org/C129671850","wikidata":"https://www.wikidata.org/wiki/Q210501","display_name":"Introspection","level":2,"score":0.5001000165939331},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.49779999256134033},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.45019999146461487},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.44600000977516174},{"id":"https://openalex.org/C99016210","wikidata":"https://www.wikidata.org/wiki/Q5488129","display_name":"Query expansion","level":2,"score":0.40220001339912415},{"id":"https://openalex.org/C2779532271","wikidata":"https://www.wikidata.org/wiki/Q445558","display_name":"Relevance feedback","level":4,"score":0.37529999017715454},{"id":"https://openalex.org/C75291252","wikidata":"https://www.wikidata.org/wiki/Q1315756","display_name":"TRACE (psycholinguistics)","level":2,"score":0.34940001368522644},{"id":"https://openalex.org/C151201525","wikidata":"https://www.wikidata.org/wiki/Q177239","display_name":"Limit (mathematics)","level":2,"score":0.3452000021934509},{"id":"https://openalex.org/C90288658","wikidata":"https://www.wikidata.org/wiki/Q3318149","display_name":"Human\u2013computer information retrieval","level":3,"score":0.34119999408721924},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.335999995470047},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.33500000834465027},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.32440000772476196},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.32109999656677246},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.30219998955726624},{"id":"https://openalex.org/C21025794","wikidata":"https://www.wikidata.org/wiki/Q5141219","display_name":"Cognitive models of information retrieval","level":4,"score":0.28450000286102295},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.27230000495910645},{"id":"https://openalex.org/C2776608160","wikidata":"https://www.wikidata.org/wiki/Q4785462","display_name":"Natural (archaeology)","level":2,"score":0.25189998745918274}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2606.00590","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.00590","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2606.00590","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.00590","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":"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"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.5082250237464905}],"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],"search":[1,19],"systems":[2],"iteratively":[3,97],"interact":[4],"with":[5],"retrieval":[6,50,101,109,142],"models":[7,110],"to":[8,73],"answer":[9,146],"complex":[10],"queries.":[11],"Despite":[12],"substantial":[13],"progress,":[14],"optimizing":[15],"retrievers":[16],"for":[17,108],"agentic":[18],"remains":[20],"challenging,":[21],"often":[22],"requiring":[23,122],"heavy":[24],"co-training":[25],"or":[26],"gold-standard":[27],"annotations":[28],"that":[29,38,62,96,111,137],"limit":[30],"real-world":[31],"applicability.":[32],"We":[33,126],"propose":[34],"Critic-R,":[35],"a":[36,59],"framework":[37],"explicitly":[39],"closes":[40],"the":[41,45,49,64,76,81],"feedback":[42],"loop":[43,95],"between":[44],"reasoning":[46,67,83],"agent":[47],"and":[48,55,100,103,114,133,144],"model":[51,61],"during":[52],"both":[53,141],"inference":[54],"training.":[56],"Critic-R":[57,85,128,138],"introduces":[58],"critic":[60],"evaluates":[63],"agent's":[65],"introspective":[66],"trace":[68],"after":[69],"consuming":[70],"retrieved":[71,77],"evidence":[72],"determine":[74],"whether":[75],"context":[78],"sufficiently":[79],"supports":[80],"next":[82],"step.":[84],"has":[86],"two":[87],"complementary":[88],"mechanisms:":[89],"Critic-R-Zero,":[90],"an":[91,105],"inference-time":[92],"query":[93],"refinement":[94,116],"rewrites":[98],"queries":[99],"instructions,":[102],"Critic-Embed,":[104],"optimization":[106],"approach":[107],"leverages":[112],"successful":[113],"failed":[115],"trajectories":[117],"as":[118],"automatic":[119],"supervision":[120],"without":[121],"manual":[123],"relevance":[124],"annotation.":[125],"evaluate":[127],"on":[129],"HotpotQA,":[130],"2WikiMultihopQA,":[131],"MuSiQue,":[132],"Bamboogle.":[134],"Results":[135],"show":[136],"significantly":[139],"improves":[140],"quality":[143],"downstream":[145],"accuracy.":[147]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2026-06-03T00:00:00"}