{"id":"https://openalex.org/W4415427913","doi":"https://doi.org/10.3233/faia251390","title":"From Grounding to Planning: Benchmarking Bottlenecks in Web Agents","display_name":"From Grounding to Planning: Benchmarking Bottlenecks in Web Agents","publication_year":2025,"publication_date":"2025-10-21","ids":{"openalex":"https://openalex.org/W4415427913","doi":"https://doi.org/10.3233/faia251390"},"language":null,"primary_location":{"id":"doi:10.3233/faia251390","is_oa":true,"landing_page_url":"https://doi.org/10.3233/faia251390","pdf_url":null,"source":{"id":"https://openalex.org/S4210201731","display_name":"Frontiers in artificial intelligence and applications","issn_l":"0922-6389","issn":["0922-6389","1879-8314"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"},"type":"book-chapter","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.3233/faia251390","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5107555313","display_name":"Segev Shlomov","orcid":null},"institutions":[{"id":"https://openalex.org/I4210167297","display_name":"IBM Research - Haifa","ror":"https://ror.org/05rw9t746","country_code":"IL","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115","https://openalex.org/I4210167297"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Segev Shlomov","raw_affiliation_strings":["IBM Research, Israel"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research, Israel","institution_ids":["https://openalex.org/I4210167297"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5107649410","display_name":"Ben Wiesel","orcid":null},"institutions":[{"id":"https://openalex.org/I4210167297","display_name":"IBM Research - Haifa","ror":"https://ror.org/05rw9t746","country_code":"IL","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115","https://openalex.org/I4210167297"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Ben Wiesel","raw_affiliation_strings":["IBM Research, Israel"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research, Israel","institution_ids":["https://openalex.org/I4210167297"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028782222","display_name":"Aviad Sela","orcid":"https://orcid.org/0000-0001-7813-7160"},"institutions":[{"id":"https://openalex.org/I4210167297","display_name":"IBM Research - Haifa","ror":"https://ror.org/05rw9t746","country_code":"IL","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115","https://openalex.org/I4210167297"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Aviad Sela","raw_affiliation_strings":["IBM Research, Israel"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research, Israel","institution_ids":["https://openalex.org/I4210167297"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108490147","display_name":"I. A. Levy","orcid":null},"institutions":[{"id":"https://openalex.org/I4210167297","display_name":"IBM Research - Haifa","ror":"https://ror.org/05rw9t746","country_code":"IL","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115","https://openalex.org/I4210167297"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Ido Levy","raw_affiliation_strings":["IBM Research, Israel"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research, Israel","institution_ids":["https://openalex.org/I4210167297"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5107628810","display_name":"Liane Galanti","orcid":null},"institutions":[{"id":"https://openalex.org/I4210167297","display_name":"IBM Research - Haifa","ror":"https://ror.org/05rw9t746","country_code":"IL","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115","https://openalex.org/I4210167297"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Liane Galanti","raw_affiliation_strings":["IBM Research, Israel"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research, Israel","institution_ids":["https://openalex.org/I4210167297"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5107628811","display_name":"Roy Abitbol","orcid":null},"institutions":[{"id":"https://openalex.org/I4210167297","display_name":"IBM Research - Haifa","ror":"https://ror.org/05rw9t746","country_code":"IL","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115","https://openalex.org/I4210167297"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Roy Abitbol","raw_affiliation_strings":["IBM Research, Israel"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research, Israel","institution_ids":["https://openalex.org/I4210167297"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210167297"],"apc_list":null,"apc_paid":null,"fwci":9.5436,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.98182624,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":99},"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/T10456","display_name":"Multi-Agent Systems and Negotiation","score":0.9980000257492065,"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/T10456","display_name":"Multi-Agent Systems and Negotiation","score":0.9980000257492065,"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/T11010","display_name":"Logic, Reasoning, and Knowledge","score":0.9797000288963318,"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/T12203","display_name":"Mobile Agent-Based Network Management","score":0.9667999744415283,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/bottleneck","display_name":"Bottleneck","score":0.8021000027656555},{"id":"https://openalex.org/keywords/benchmarking","display_name":"Benchmarking","score":0.7777000069618225},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5593000054359436},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.40630000829696655},{"id":"https://openalex.org/keywords/plan","display_name":"Plan (archaeology)","score":0.39590001106262207},{"id":"https://openalex.org/keywords/work","display_name":"Work (physics)","score":0.3732999861240387},{"id":"https://openalex.org/keywords/web-application","display_name":"Web application","score":0.36629998683929443}],"concepts":[{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.8021000027656555},{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.7777000069618225},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5677000284194946},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5593000054359436},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.40630000829696655},{"id":"https://openalex.org/C2776505523","wikidata":"https://www.wikidata.org/wiki/Q4785468","display_name":"Plan (archaeology)","level":2,"score":0.39590001106262207},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.3732999861240387},{"id":"https://openalex.org/C118643609","wikidata":"https://www.wikidata.org/wiki/Q189210","display_name":"Web application","level":2,"score":0.36629998683929443},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.349700003862381},{"id":"https://openalex.org/C151201525","wikidata":"https://www.wikidata.org/wiki/Q177239","display_name":"Limit (mathematics)","level":2,"score":0.3434000015258789},{"id":"https://openalex.org/C168993435","wikidata":"https://www.wikidata.org/wiki/Q6501125","display_name":"Ground","level":2,"score":0.3391999900341034},{"id":"https://openalex.org/C112930515","wikidata":"https://www.wikidata.org/wiki/Q4389547","display_name":"Risk analysis (engineering)","level":1,"score":0.31439998745918274},{"id":"https://openalex.org/C41550386","wikidata":"https://www.wikidata.org/wiki/Q529909","display_name":"Multi-agent system","level":2,"score":0.30300000309944153},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.3021000027656555},{"id":"https://openalex.org/C2777093003","wikidata":"https://www.wikidata.org/wiki/Q6508345","display_name":"Lead (geology)","level":2,"score":0.27730000019073486},{"id":"https://openalex.org/C2778571376","wikidata":"https://www.wikidata.org/wiki/Q1355821","display_name":"Frontier","level":2,"score":0.2678999900817871},{"id":"https://openalex.org/C2776544517","wikidata":"https://www.wikidata.org/wiki/Q189447","display_name":"Unexpected events","level":2,"score":0.26030001044273376}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.3233/faia251390","is_oa":true,"landing_page_url":"https://doi.org/10.3233/faia251390","pdf_url":null,"source":{"id":"https://openalex.org/S4210201731","display_name":"Frontiers in artificial intelligence and applications","issn_l":"0922-6389","issn":["0922-6389","1879-8314"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"}],"best_oa_location":{"id":"doi:10.3233/faia251390","is_oa":true,"landing_page_url":"https://doi.org/10.3233/faia251390","pdf_url":null,"source":{"id":"https://openalex.org/S4210201731","display_name":"Frontiers in artificial intelligence and applications","issn_l":"0922-6389","issn":["0922-6389","1879-8314"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"},"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":{"General":[0],"web-based":[1],"agents":[2,34,51],"are":[3],"increasingly":[4],"essential":[5],"for":[6,91,157,167],"interacting":[7],"with":[8,26,126],"complex":[9],"web":[10,17,162],"environments,":[11],"yet":[12],"their":[13],"performance":[14,144],"in":[15,134],"real-world":[16],"applications":[18],"remains":[19],"poor,":[20],"yielding":[21],"extremely":[22],"low":[23],"accuracy":[24],"even":[25],"state-of-the-art":[27],"frontier":[28],"models.":[29],"We":[30,63],"observe":[31],"that":[32,103,114],"these":[33,50],"can":[35,122],"be":[36,123],"decomposed":[37],"into":[38],"two":[39,95],"primary":[40,131],"components:":[41],"Planning":[42],"and":[43,70,73,100,121,153],"Grounding.":[44],"Yet,":[45],"most":[46],"existing":[47],"research":[48],"treats":[49],"as":[52],"black":[53],"boxes,":[54],"focusing":[55],"on":[56,81],"end-to-end":[57],"evaluations":[58],"which":[59,138],"hinder":[60],"meaningful":[61],"improvements.":[62],"sharpen":[64],"the":[65,68,82,94,98,130,135,140,159,165],"distinction":[66],"between":[67],"planning":[69,136],"grounding":[71,115],"components":[72],"conduct":[74],"a":[75,88,118],"novel":[76],"analysis":[77],"by":[78],"refining":[79],"experiments":[80],"Mind2Web":[83],"dataset.":[84],"Our":[85],"work":[86],"proposes":[87],"new":[89,151],"benchmark":[90],"each":[92],"of":[93,143,161],"components,":[96],"identifying":[97],"bottlenecks":[99],"pain":[101],"points":[102],"limit":[104],"agent":[105],"performance.":[106],"Contrary":[107],"to":[108],"prevalent":[109],"assumptions,":[110],"our":[111],"findings":[112],"suggest":[113],"is":[116,139],"not":[117],"significant":[119],"bottleneck":[120],"effectively":[124],"addressed":[125],"current":[127],"techniques.":[128],"Instead,":[129],"challenge":[132],"lies":[133],"component,":[137],"main":[141],"source":[142],"degradation.":[145],"Through":[146],"this":[147],"analysis,":[148],"we":[149],"offer":[150],"insights":[152],"demonstrate":[154],"practical":[155],"suggestions":[156],"improving":[158],"capabilities":[160],"agents,":[163],"paving":[164],"way":[166],"more":[168],"reliable":[169],"agents.":[170]},"counts_by_year":[{"year":2026,"cited_by_count":3}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-24T00:00:00"}
