{"id":"https://openalex.org/W7152655394","doi":"https://doi.org/10.1145/3774904.3792738","title":"TRACE: Trajectory-Aware Comprehensive Evaluation for Deep Research Agents","display_name":"TRACE: Trajectory-Aware Comprehensive Evaluation for Deep Research Agents","publication_year":2026,"publication_date":"2026-04-09","ids":{"openalex":"https://openalex.org/W7152655394","doi":"https://doi.org/10.1145/3774904.3792738"},"language":null,"primary_location":{"id":"doi:10.1145/3774904.3792738","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3774904.3792738","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM Web Conference 2026","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3774904.3792738","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5129655968","display_name":"Yanyu Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Yanyu Chen","raw_affiliation_strings":["The Chinese University of Hong Kong, Hong Kong, Hong Kong"],"raw_orcid":"https://orcid.org/0009-0004-5382-3622","affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong, Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038913434","display_name":"Jiyue Jiang","orcid":null},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Jiyue Jiang","raw_affiliation_strings":["The Chinese University of Hong Kong, Hong Kong, Hong Kong"],"raw_orcid":"https://orcid.org/0009-0004-7318-6659","affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong, Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5122882694","display_name":"Jiahong Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Jiahong Liu","raw_affiliation_strings":["The Chinese University of Hong Kong, Hong Kong, China"],"raw_orcid":"https://orcid.org/0000-0002-8551-120X","affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong, Hong Kong, China","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088642353","display_name":"Y. X. Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Yifei Zhang","raw_affiliation_strings":["The Chinese University of Hong Kong, Singapore, China"],"raw_orcid":"https://orcid.org/0000-0003-4185-8663","affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong, Singapore, China","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Xiao Guo","orcid":"https://orcid.org/0009-0009-2816-8976"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Xiao Guo","raw_affiliation_strings":["The Chinese University of Hong Kong, Hong Kong, Hong Kong"],"raw_orcid":"https://orcid.org/0009-0009-2816-8976","affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong, Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5042251906","display_name":"Irwin King","orcid":"https://orcid.org/0000-0001-8106-6447"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Irwin King","raw_affiliation_strings":["The Chinese University of Hong Kong, Hong Kong, Hong Kong"],"raw_orcid":"https://orcid.org/0000-0001-8106-6447","affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong, Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I177725633"],"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":"2524","last_page":"2534"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.11219999939203262,"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"}},"topics":[{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.11219999939203262,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.08959999680519104,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.07240000367164612,"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/identification","display_name":"Identification (biology)","score":0.2827000021934509},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.2639000117778778},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.263700008392334},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.2354000061750412},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.2345999926328659}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.42410001158714294},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.2827000021934509},{"id":"https://openalex.org/C112930515","wikidata":"https://www.wikidata.org/wiki/Q4389547","display_name":"Risk analysis (engineering)","level":1,"score":0.2662999927997589},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2639000117778778},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.263700008392334},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2538999915122986},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.2354000061750412},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.2345999926328659},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.2345999926328659},{"id":"https://openalex.org/C133462117","wikidata":"https://www.wikidata.org/wiki/Q4929239","display_name":"Data collection","level":2,"score":0.2305999994277954}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3774904.3792738","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3774904.3792738","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM Web Conference 2026","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3774904.3792738","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3774904.3792738","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM Web Conference 2026","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":3,"referenced_works":["https://openalex.org/W2889787757","https://openalex.org/W4411120157","https://openalex.org/W4416059045"],"related_works":[],"abstract_inverted_index":{"The":[0],"evaluation":[1,24],"of":[2,19,48,56],"Deep":[3],"Research":[4],"Agents":[5],"is":[6],"a":[7,30,38,78,94,117,155],"critical":[8,160],"challenge,":[9],"as":[10],"conventional":[11],"outcome-based":[12],"metrics":[13,34],"fail":[14],"to":[15,59],"capture":[16],"the":[17,43,49,54,83,89,129,138,145],"nuances":[18],"their":[20],"complex":[21],"reasoning.":[22],"Current":[23],"faces":[25],"two":[26],"primary":[27],"challenges:":[28],"1)":[29],"reliance":[31],"on":[32],"singular":[33,171],"like":[35,63],"Pass@1,":[36],"creating":[37],"''high-score":[39,90],"illusion''":[40],"that":[41,80,99,158],"ignores":[42],"quality,":[44,105],"efficiency,":[45,165],"and":[46,52,65,103,144,166],"soundness":[47],"reasoning":[50],"process;":[51],"2)":[53],"failure":[55],"static":[57],"benchmarks":[58],"quantify":[60],"crucial":[61],"attributes":[62],"robustness":[64,167],"latent":[66,125],"capability.":[67],"To":[68,87,111],"address":[69],"these":[70],"gaps,":[71],"we":[72,92],"introduce":[73],"TRACE":[74,115,139,153],"(Trajectory-Aware":[75],"Comprehensive":[76],"Evaluation),":[77],"framework":[79],"holistically":[81],"assesses":[82],"entire":[84],"problem-solving":[85],"trajectory.":[86],"counter":[88],"illusion'',":[91],"propose":[93],"Hierarchical":[95],"Trajectory":[96],"Utility":[97],"Function":[98],"quantifies":[100],"process":[101],"efficiency":[102],"cognitive":[104],"including":[106],"evidence":[107],"grounding,":[108],"alongside":[109],"accuracy.":[110],"measure":[112],"deeper":[113],"attributes,":[114],"introduces":[116],"Scaffolded":[118],"Capability":[119],"Assessment":[120],"protocol,":[121],"quantifying":[122],"an":[123],"agent's":[124],"ability":[126],"by":[127,170],"determining":[128],"minimum":[130],"guidance":[131],"needed":[132],"for":[133],"success.":[134],"Our":[135],"contributions":[136],"include":[137],"framework,":[140],"its":[141],"novel":[142],"metrics,":[143],"accompanying":[146],"DeepResearch-Bench":[147],"with":[148],"controllable":[149],"complexity.":[150],"Experiments":[151],"show":[152],"delivers":[154],"granular":[156],"ranking":[157],"uncovers":[159],"trade-offs":[161],"between":[162],"agent":[163],"accuracy,":[164],"entirely":[168],"missed":[169],"metrics.":[172]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2026-04-10T00:00:00"}