{"id":"https://openalex.org/W7166869438","doi":"https://doi.org/10.18653/v1/2026.acl-long.1483","title":"Why Do LLM-based Web Agents Fail? A Hierarchical Planning Perspective","display_name":"Why Do LLM-based Web Agents Fail? A Hierarchical Planning Perspective","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7166869438","doi":"https://doi.org/10.18653/v1/2026.acl-long.1483"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2026.acl-long.1483","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.1483","pdf_url":"https://aclanthology.org/2026.acl-long.1483.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":"Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2026.acl-long.1483.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5061950213","display_name":"Mohamed Aghzal","orcid":null},"institutions":[{"id":"https://openalex.org/I162714631","display_name":"George Mason University","ror":"https://ror.org/02jqj7156","country_code":"US","type":"education","lineage":["https://openalex.org/I162714631"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mohamed Aghzal","raw_affiliation_strings":["Department of Computer Science , George Mason University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science , George Mason University","institution_ids":["https://openalex.org/I162714631"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042000667","display_name":"G. Stein","orcid":"https://orcid.org/0000-0003-1981-4154"},"institutions":[{"id":"https://openalex.org/I162714631","display_name":"George Mason University","ror":"https://ror.org/02jqj7156","country_code":"US","type":"education","lineage":["https://openalex.org/I162714631"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Gregory J. Stein","raw_affiliation_strings":["Department of Computer Science , George Mason University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science , George Mason University","institution_ids":["https://openalex.org/I162714631"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101616607","display_name":"Ziyu Yao","orcid":"https://orcid.org/0009-0007-4571-3505"},"institutions":[{"id":"https://openalex.org/I162714631","display_name":"George Mason University","ror":"https://ror.org/02jqj7156","country_code":"US","type":"education","lineage":["https://openalex.org/I162714631"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ziyu Yao","raw_affiliation_strings":["Department of Computer Science , George Mason University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science , George Mason University","institution_ids":["https://openalex.org/I162714631"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I162714631"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.8582296,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"32157","last_page":"32180"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10456","display_name":"Multi-Agent Systems and Negotiation","score":0.4876999855041504,"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":0.4876999855041504,"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/T10927","display_name":"Access Control and Trust","score":0.12389999628067017,"subfield":{"id":"https://openalex.org/subfields/3312","display_name":"Sociology and Political Science"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T12203","display_name":"Mobile Agent-Based Network Management","score":0.07209999859333038,"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/perspective","display_name":"Perspective (graphical)","score":0.6607000231742859},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.32820001244544983},{"id":"https://openalex.org/keywords/the-internet","display_name":"The Internet","score":0.29260000586509705},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.27489998936653137},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.2623000144958496}],"concepts":[{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.6607000231742859},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5361999869346619},{"id":"https://openalex.org/C56739046","wikidata":"https://www.wikidata.org/wiki/Q192060","display_name":"Knowledge management","level":1,"score":0.36880001425743103},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.32820001244544983},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.32420000433921814},{"id":"https://openalex.org/C110875604","wikidata":"https://www.wikidata.org/wiki/Q75","display_name":"The Internet","level":2,"score":0.29260000586509705},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.2849000096321106},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.27489998936653137},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.2623000144958496},{"id":"https://openalex.org/C180198813","wikidata":"https://www.wikidata.org/wiki/Q121182","display_name":"Information system","level":2,"score":0.2581999897956848}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2026.acl-long.1483","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.1483","pdf_url":"https://aclanthology.org/2026.acl-long.1483.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":"Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.acl-long.1483","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.1483","pdf_url":"https://aclanthology.org/2026.acl-long.1483.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":"Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.5988706946372986,"id":"https://metadata.un.org/sdg/11","display_name":"Sustainable cities and communities"}],"awards":[{"id":"https://openalex.org/G5127146977","display_name":null,"funder_award_id":"W911NF2520011","funder_id":"https://openalex.org/F4320338295","funder_display_name":"Army Research Laboratory"},{"id":"https://openalex.org/G8228225833","display_name":"Collaborative Research: Fostering Mathematical Modeling Competencies through Collaborative Learning in a Large Language Model (LLM) Simulated Virtual Classroom","funder_award_id":"2418580","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G8408111621","display_name":"Fast and Reliable Online Retraining and Adaptation for Robot Planning Despite Missing World Knowledge","funder_award_id":"2232733","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320309029","display_name":"George Mason University","ror":"https://ror.org/02jqj7156"},{"id":"https://openalex.org/F4320338295","display_name":"Army Research Laboratory","ror":"https://ror.org/011hc8f90"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7166869438.pdf","grobid_xml":"https://content.openalex.org/works/W7166869438.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Large":[0],"language":[1,80],"model":[2],"(LLM)":[3],"web":[4,10,42,120],"agents":[5,43],"are":[6],"increasingly":[7],"used":[8],"for":[9,105,115],"navigation":[11],"but":[12,83,152],"remain":[13],"far":[14],"from":[15],"human":[16],"reliability":[17],"on":[18,25],"realistic,":[19],"long-horizon":[20],"tasks.Existing":[21],"evaluations":[22],"focus":[23],"primarily":[24],"end-to-end":[26],"success,":[27],"offering":[28],"limited":[29],"insight":[30],"into":[31],"where":[32],"failures":[33],"arise.We":[34],"propose":[35],"a":[36,112],"hierarchical":[37,109],"planning":[38],"framework":[39],"to":[40],"analyze":[41],"across":[44],"three":[45],"layers":[46],"(i.e.,":[47],"high-level":[48,101],"planning,":[49],"low-level":[50],"execution,":[51],"and":[52,60,75,96,117],"replanning),":[53],"enabling":[54],"process-based":[55],"evaluation":[56],"of":[57],"reasoning,":[58,102],"grounding,":[59],"recovery.Our":[61],"experiments":[62],"show":[63],"that":[64,92],"structured":[65],"Planning":[66],"Domain":[67,124],"Definition":[68],"Language":[69],"(PDDL)":[70],"plans":[71],"produce":[72],"more":[73],"concise":[74],"goal-directed":[76],"strategies":[77],"than":[78],"natural":[79],"(NL)":[81],"plans,":[82],"lowlevel":[84],"execution":[85],"remains":[86],"the":[87],"dominant":[88],"bottleneck.These":[89],"results":[90,154],"indicate":[91],"improving":[93],"perceptual":[94],"grounding":[95],"adaptive":[97],"control,":[98],"not":[99,144],"only":[100],"is":[103,143],"critical":[104],"achieving":[106],"human-level":[107],"reliability.This":[108],"perspective":[110],"provides":[111],"principled":[113],"foundation":[114],"diagnosing":[116],"advancing":[118],"LLM":[119,128,131,134],"agents.PDDL":[121],"Plan":[122],"PDDL":[123],"File":[125],"Postcondition":[126,142],"Checker":[127],"High-level":[129],"Planner":[130,133],"Low-level":[132],"1.":[135],"google_search":[136],"\"Gamestop":[137],"store":[138],"locator":[139],"near":[140],"90028\"":[141],"yet":[145],"satistified":[146],"because":[147],"google":[148],"search":[149],"was":[150],"performed":[151],"no":[153],"have":[155],"been":[156],"accessed":[157],"yet.":[158]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-07-02T00:00:00"}