{"id":"https://openalex.org/W7166862435","doi":"https://doi.org/10.18653/v1/2026.acl-long.1","title":"OctoTools: A Multi-Agent Framework with Extensible Tools for Complex Reasoning","display_name":"OctoTools: A Multi-Agent Framework with Extensible Tools for Complex Reasoning","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7166862435","doi":"https://doi.org/10.18653/v1/2026.acl-long.1"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2026.acl-long.1","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.1","pdf_url":"https://aclanthology.org/2026.acl-long.1.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.1.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5139852782","display_name":"Lu Pan","orcid":null},"institutions":[{"id":"https://openalex.org/I4210125814","display_name":"Equilibrium Research","ror":"https://ror.org/03gcx9p86","country_code":"GB","type":"facility","lineage":["https://openalex.org/I4210125814"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Pan Lu","raw_affiliation_strings":["Equal contribution Stanford University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Equal contribution Stanford University","institution_ids":["https://openalex.org/I4210125814"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139757551","display_name":"Bowen Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I4210125814","display_name":"Equilibrium Research","ror":"https://ror.org/03gcx9p86","country_code":"GB","type":"facility","lineage":["https://openalex.org/I4210125814"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Bowen Chen","raw_affiliation_strings":["Equal contribution Stanford University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Equal contribution Stanford University","institution_ids":["https://openalex.org/I4210125814"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139799496","display_name":"Sheng Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210125814","display_name":"Equilibrium Research","ror":"https://ror.org/03gcx9p86","country_code":"GB","type":"facility","lineage":["https://openalex.org/I4210125814"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Sheng Liu","raw_affiliation_strings":["Equal contribution Stanford University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Equal contribution Stanford University","institution_ids":["https://openalex.org/I4210125814"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026274141","display_name":"Rahul Thapa","orcid":"https://orcid.org/0000-0002-1137-955X"},"institutions":[{"id":"https://openalex.org/I4210125814","display_name":"Equilibrium Research","ror":"https://ror.org/03gcx9p86","country_code":"GB","type":"facility","lineage":["https://openalex.org/I4210125814"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Rahul Thapa","raw_affiliation_strings":["Equal contribution Stanford University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Equal contribution Stanford University","institution_ids":["https://openalex.org/I4210125814"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5116310253","display_name":"Joseph Boen","orcid":null},"institutions":[{"id":"https://openalex.org/I4210125814","display_name":"Equilibrium Research","ror":"https://ror.org/03gcx9p86","country_code":"GB","type":"facility","lineage":["https://openalex.org/I4210125814"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Joseph Boen","raw_affiliation_strings":["Equal contribution Stanford University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Equal contribution Stanford University","institution_ids":["https://openalex.org/I4210125814"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5139799938","display_name":"James Zou","orcid":null},"institutions":[{"id":"https://openalex.org/I4210125814","display_name":"Equilibrium Research","ror":"https://ror.org/03gcx9p86","country_code":"GB","type":"facility","lineage":["https://openalex.org/I4210125814"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"James Zou","raw_affiliation_strings":["Equal contribution Stanford University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Equal contribution Stanford University","institution_ids":["https://openalex.org/I4210125814"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210125814"],"apc_list":null,"apc_paid":null,"fwci":21.2894,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.99295138,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"86"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10906","display_name":"AI-based Problem Solving and Planning","score":0.23749999701976776,"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/T10906","display_name":"AI-based Problem Solving and Planning","score":0.23749999701976776,"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/T10456","display_name":"Multi-Agent Systems and Negotiation","score":0.23270000517368317,"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/T11596","display_name":"Constraint Satisfaction and Optimization","score":0.15729999542236328,"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/extensibility","display_name":"Extensibility","score":0.3668000102043152},{"id":"https://openalex.org/keywords/automated-reasoning","display_name":"Automated reasoning","score":0.3589000105857849},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.2962999939918518},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.2727999985218048},{"id":"https://openalex.org/keywords/complex-system","display_name":"Complex system","score":0.272599995136261}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6617000102996826},{"id":"https://openalex.org/C32833848","wikidata":"https://www.wikidata.org/wiki/Q4115054","display_name":"Extensibility","level":2,"score":0.3668000102043152},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.3617999851703644},{"id":"https://openalex.org/C195344581","wikidata":"https://www.wikidata.org/wiki/Q2555318","display_name":"Automated reasoning","level":2,"score":0.3589000105857849},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3450999855995178},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.2962999939918518},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.28839999437332153},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2727999985218048},{"id":"https://openalex.org/C47822265","wikidata":"https://www.wikidata.org/wiki/Q854457","display_name":"Complex system","level":2,"score":0.272599995136261},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.2700999975204468},{"id":"https://openalex.org/C124304363","wikidata":"https://www.wikidata.org/wiki/Q673661","display_name":"Abstraction","level":2,"score":0.25850000977516174},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.2502000033855438}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2026.acl-long.1","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.1","pdf_url":"https://aclanthology.org/2026.acl-long.1.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.1","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.1","pdf_url":"https://aclanthology.org/2026.acl-long.1.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":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7166862435.pdf","grobid_xml":"https://content.openalex.org/works/W7166862435.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Solving":[0],"complex":[1,55],"reasoning":[2,56],"tasks":[3,90],"may":[4],"involve":[5],"visual":[6],"understanding,":[7],"domain":[8],"knowledge":[9],"retrieval,":[10],"numerical":[11],"calculation,":[12],"and":[13,47,73,76,95,111,127,133,146],"multi-step":[14,147],"reasoning.Existing":[15],"methods":[16],"augment":[17],"large":[18],"language":[19],"models":[20],"(LLMs)":[21],"with":[22,130],"external":[23],"tools":[24],"but":[25],"are":[26,153,165],"restricted":[27],"to":[28,53,64,79,115],"specialized":[29],"domains,":[30],"limited":[31],"tool":[32,62,66,82,135,144],"types,":[33],"or":[34],"require":[35],"additional":[36],"training":[37],"data.In":[38],"this":[39],"paper,":[40],"we":[41],"introduce":[42],"OctoTools,":[43],"a":[44,68,166],"training-free,":[45],"user-friendly,":[46],"easily":[48],"extensible":[49],"multi-agent":[50],"framework":[51],"designed":[52],"tackle":[54],"across":[57,87],"diverse":[58,89],"domains.Oc-toTools":[59],"introduces":[60],"standardized":[61],"cards":[63],"encapsulate":[65],"functionality,":[67],"planner":[69],"for":[70],"both":[71],"high-level":[72],"low-level":[74],"planning,":[75,142],"an":[77],"executor":[78],"carry":[80],"out":[81],"usage.We":[83],"validate":[84],"OctoTools'":[85],"generality":[86],"16":[88],"(including":[91],"MathVista,":[92],"MMLU-Pro,":[93],"MedQA,":[94],"GAIA-Text),":[96],"achieving":[97],"substantial":[98],"average":[99],"accuracy":[100],"gains":[101],"of":[102,122,168],"9.3%":[103],"over":[104],"GPT-4o.Furthermore,":[105],"OctoTools":[106,137],"also":[107],"outperforms":[108],"AutoGen,":[109],"GPT-Functions,":[110],"LangChain":[112],"by":[113],"up":[114],"10.6%":[116],"when":[117],"given":[118],"the":[119],"same":[120],"set":[121],"tools.Through":[123],"comprehensive":[124],"analysi,":[125],"ablations,":[126],"robustness":[128],"tests":[129],"compact":[131],"backbones":[132],"noisy":[134],"environments,":[136],"demonstrates":[138],"advantages":[139],"in":[140],"task":[141],"effective":[143],"usage,":[145],"problem":[148],"solving.Q:":[149],"How":[150],"many":[151],"baseballs":[152],"there?The":[154],"image":[155],"shows":[156],"four":[157],"blue":[158],"buckets,":[159],"each":[160],"containing":[161],"five":[162],"baseballs.Therefore,":[163],"there":[164],"total":[167],"20":[169],"baseballs.":[170],"Solution":[171],"Summarizer":[172]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-07-02T00:00:00"}