{"id":"https://openalex.org/W4416232959","doi":"https://doi.org/10.1145/3768292.3770364","title":"FinResearchBench: A Logic Tree based Agent-as-a-Judge Evaluation Framework for Financial Research Agents","display_name":"FinResearchBench: A Logic Tree based Agent-as-a-Judge Evaluation Framework for Financial Research Agents","publication_year":2025,"publication_date":"2025-11-14","ids":{"openalex":"https://openalex.org/W4416232959","doi":"https://doi.org/10.1145/3768292.3770364"},"language":null,"primary_location":{"id":"doi:10.1145/3768292.3770364","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3768292.3770364","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 6th ACM International Conference on AI in Finance","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100591006","display_name":"Rui Sun","orcid":"https://orcid.org/0009-0005-6031-5770"},"institutions":[{"id":"https://openalex.org/I4210140476","display_name":"Shanghai Zhaozhan Metal Materials","ror":"https://ror.org/03wtw1749","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210140476"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Rui Sun","raw_affiliation_strings":["Stepfun, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Stepfun, Shanghai, China","institution_ids":["https://openalex.org/I4210140476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008300079","display_name":"Zuo Bai","orcid":"https://orcid.org/0000-0001-5349-9739"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zuo Bai","raw_affiliation_strings":["FinStep, Shanghai, China and Stepfun, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"FinStep, Shanghai, China and Stepfun, Shanghai, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5092049528","display_name":"Wentao Zhang","orcid":"https://orcid.org/0009-0009-0903-8260"},"institutions":[{"id":"https://openalex.org/I4210140476","display_name":"Shanghai Zhaozhan Metal Materials","ror":"https://ror.org/03wtw1749","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210140476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wentao Zhang","raw_affiliation_strings":["Stepfun, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Stepfun, Shanghai, China","institution_ids":["https://openalex.org/I4210140476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043883875","display_name":"Yuxiang Zhang","orcid":"https://orcid.org/0009-0002-9221-7284"},"institutions":[{"id":"https://openalex.org/I4210140476","display_name":"Shanghai Zhaozhan Metal Materials","ror":"https://ror.org/03wtw1749","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210140476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuxiang Zhang","raw_affiliation_strings":["Stepfun, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Stepfun, Shanghai, China","institution_ids":["https://openalex.org/I4210140476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044631895","display_name":"Zhao Li","orcid":"https://orcid.org/0000-0002-9538-358X"},"institutions":[{"id":"https://openalex.org/I4210140476","display_name":"Shanghai Zhaozhan Metal Materials","ror":"https://ror.org/03wtw1749","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210140476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li Zhao","raw_affiliation_strings":["Stepfun, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Stepfun, Shanghai, China","institution_ids":["https://openalex.org/I4210140476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110374330","display_name":"Shan Sun","orcid":"https://orcid.org/0009-0004-8853-0352"},"institutions":[{"id":"https://openalex.org/I908609501","display_name":"Finisar (United States)","ror":"https://ror.org/01jqh6j63","country_code":"US","type":"company","lineage":["https://openalex.org/I908609501"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shan Sun","raw_affiliation_strings":["FinStep, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"FinStep, Shanghai, China","institution_ids":["https://openalex.org/I908609501"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5023643209","display_name":"Zhu Qiu","orcid":"https://orcid.org/0009-0009-2937-8799"},"institutions":[{"id":"https://openalex.org/I908609501","display_name":"Finisar (United States)","ror":"https://ror.org/01jqh6j63","country_code":"US","type":"company","lineage":["https://openalex.org/I908609501"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhengwen Qiu","raw_affiliation_strings":["FinStep, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"FinStep, Shanghai, China","institution_ids":["https://openalex.org/I908609501"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5100591006"],"corresponding_institution_ids":["https://openalex.org/I4210140476"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.40135264,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"656","last_page":"664"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11326","display_name":"Stock Market Forecasting Methods","score":0.41179999709129333,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T11326","display_name":"Stock Market Forecasting Methods","score":0.41179999709129333,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.08869999647140503,"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/T11653","display_name":"Financial Distress and Bankruptcy Prediction","score":0.051899999380111694,"subfield":{"id":"https://openalex.org/subfields/1402","display_name":"Accounting"},"field":{"id":"https://openalex.org/fields/14","display_name":"Business, Management and Accounting"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.6662999987602234},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6334999799728394},{"id":"https://openalex.org/keywords/tree","display_name":"Tree (set theory)","score":0.5236999988555908},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.36500000953674316},{"id":"https://openalex.org/keywords/outcome","display_name":"Outcome (game theory)","score":0.3626999855041504},{"id":"https://openalex.org/keywords/intelligent-agent","display_name":"Intelligent agent","score":0.30070000886917114}],"concepts":[{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.6662999987602234},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6589000225067139},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6334999799728394},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.5236999988555908},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4867999851703644},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3856000006198883},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3732999861240387},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.36500000953674316},{"id":"https://openalex.org/C148220186","wikidata":"https://www.wikidata.org/wiki/Q7111912","display_name":"Outcome (game theory)","level":2,"score":0.3626999855041504},{"id":"https://openalex.org/C56739046","wikidata":"https://www.wikidata.org/wiki/Q192060","display_name":"Knowledge management","level":1,"score":0.36149999499320984},{"id":"https://openalex.org/C74072328","wikidata":"https://www.wikidata.org/wiki/Q1142726","display_name":"Intelligent agent","level":2,"score":0.30070000886917114},{"id":"https://openalex.org/C5894958","wikidata":"https://www.wikidata.org/wiki/Q2297769","display_name":"Software agent","level":2,"score":0.2883000075817108},{"id":"https://openalex.org/C2775940519","wikidata":"https://www.wikidata.org/wiki/Q17067742","display_name":"Logic model","level":2,"score":0.27480000257492065},{"id":"https://openalex.org/C539667460","wikidata":"https://www.wikidata.org/wiki/Q2414942","display_name":"Management science","level":1,"score":0.2712000012397766},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.2669999897480011},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.26669999957084656},{"id":"https://openalex.org/C10138342","wikidata":"https://www.wikidata.org/wiki/Q43015","display_name":"Finance","level":1,"score":0.2612000107765198},{"id":"https://openalex.org/C58328972","wikidata":"https://www.wikidata.org/wiki/Q184609","display_name":"Expert system","level":2,"score":0.2551000118255615},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.25189998745918274}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3768292.3770364","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3768292.3770364","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 6th ACM International Conference on AI in Finance","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":3,"referenced_works":["https://openalex.org/W4381104068","https://openalex.org/W4399082786","https://openalex.org/W4401042286"],"related_works":[],"abstract_inverted_index":{"Recently,":[0],"AI":[1,25],"agents":[2,107],"are":[3,9,48,124],"rapidly":[4],"evolving":[5],"in":[6,12,77,114,174],"intelligence":[7],"and":[8,21,40,52,56,73,89,101,129,142,154],"widely":[10],"used":[11],"professional":[13],"research":[14,28,63,68,95,106,117,140,165],"applications,":[15],"such":[16],"as":[17,34,145],"STEM,":[18],"software":[19],"development,":[20],"finance.":[22],"Among":[23],"these":[24,62],"agents,":[26],"deep":[27],"agent":[29],"is":[30,84],"a":[31,85,99,151],"key":[32,110],"category":[33],"it":[35,144,160],"can":[36],"perform":[37],"long-horizon":[38],"tasks":[39,113],"solve":[41],"problems":[42,69],"of":[43,61,104,112,121,138,172],"greater":[44],"complexity.":[45],"However,":[46],"there":[47],"few":[49],"evaluation":[50],"frameworks":[51],"benchmarks":[53],"that":[54,133,159],"systematically":[55],"automatically":[57],"investigate":[58],"the":[59,78,93,105,115,127,135,139,146,175],"capabilities":[60],"agents.":[64,96],"In":[65],"addition,":[66],"financial":[67,94,116,164],"have":[70],"distinct":[71],"complexity":[72],"subtlety.":[74],"To":[75],"fill":[76],"gap,":[79],"we":[80],"propose":[81],"FinResearchBench,":[82],"which":[83],"logic":[86,136],"tree-based":[87],"Agent-as-a-Judge":[88,131],"targets":[90],"specifically":[91],"for":[92],"It":[97],"provides":[98],"comprehensive":[100],"automatic":[102],"assessment":[103],"across":[108,168],"7":[109,169],"types":[111,171],"domain.":[118,176],"The":[119],"contributions":[120],"this":[122],"work":[123],"two-folded:":[125],"(1)":[126],"first":[128],"innovative":[130],"system":[132],"extracts":[134],"tree":[137],"outcome":[141],"uses":[143],"intermediate":[147],"information":[148],"to":[149],"present":[150],"comprehensive,":[152],"reliable,":[153],"robust":[155],"evaluation;":[156],"(2)":[157],"finance-oriented":[158],"covers":[161],"70":[162],"typical":[163],"questions,":[166],"spreading":[167],"frequently-encountered":[170],"task":[173]},"counts_by_year":[],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-11-14T00:00:00"}