{"id":"https://openalex.org/W7128492425","doi":"https://doi.org/10.48550/arxiv.2602.07359","title":"W&D:Scaling Parallel Tool Calling for Efficient Deep Research Agents","display_name":"W&D:Scaling Parallel Tool Calling for Efficient Deep Research Agents","publication_year":2026,"publication_date":"2026-02-07","ids":{"openalex":"https://openalex.org/W7128492425","doi":"https://doi.org/10.48550/arxiv.2602.07359"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2602.07359","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2602.07359","pdf_url":"https://arxiv.org/pdf/2602.07359","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2602.07359","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101211925","display_name":"Xiaoqiang Lin","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210155268","display_name":"Salesforce (United States)","ror":"https://ror.org/057315g56","country_code":"US","type":"company","lineage":["https://openalex.org/I4210155268"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lin, Xiaoqiang","raw_affiliation_strings":["Salesforce AI Research SalesforceAIResearch/MCP-Universe/deepresearch Website"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Salesforce AI Research SalesforceAIResearch/MCP-Universe/deepresearch Website","institution_ids":["https://openalex.org/I4210155268"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014937540","display_name":"Jun Hao Liew","orcid":"https://orcid.org/0000-0002-7538-6759","observed_orcids":["https://orcid.org/0000-0002-7538-6759"]},"institutions":[{"id":"https://openalex.org/I4210155268","display_name":"Salesforce (United States)","ror":"https://ror.org/057315g56","country_code":"US","type":"company","lineage":["https://openalex.org/I4210155268"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Liew, Jun Hao","raw_affiliation_strings":["Salesforce AI Research SalesforceAIResearch/MCP-Universe/deepresearch Website"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Salesforce AI Research SalesforceAIResearch/MCP-Universe/deepresearch Website","institution_ids":["https://openalex.org/I4210155268"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042646536","display_name":"Silvio Savarese","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210155268","display_name":"Salesforce (United States)","ror":"https://ror.org/057315g56","country_code":"US","type":"company","lineage":["https://openalex.org/I4210155268"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Savarese, Silvio","raw_affiliation_strings":["Salesforce AI Research SalesforceAIResearch/MCP-Universe/deepresearch Website"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Salesforce AI Research SalesforceAIResearch/MCP-Universe/deepresearch Website","institution_ids":["https://openalex.org/I4210155268"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5125514534","display_name":"Junnan Li","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210155268","display_name":"Salesforce (United States)","ror":"https://ror.org/057315g56","country_code":"US","type":"company","lineage":["https://openalex.org/I4210155268"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Li, Junnan","raw_affiliation_strings":["Salesforce AI Research SalesforceAIResearch/MCP-Universe/deepresearch Website"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Salesforce AI Research SalesforceAIResearch/MCP-Universe/deepresearch Website","institution_ids":["https://openalex.org/I4210155268"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210155268"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":6,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"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/T10286","display_name":"Information Retrieval and Search Behavior","score":0.576200008392334,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T10286","display_name":"Information Retrieval and Search Behavior","score":0.576200008392334,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T10906","display_name":"AI-based Problem Solving and Planning","score":0.17829999327659607,"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/T10028","display_name":"Topic Modeling","score":0.0674000009894371,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/deep-research-agents","display_name":"deep research agents","score":0.9100000262260437},{"id":"https://openalex.org/keywords/multi-step-reasoning","display_name":"multi-step reasoning","score":0.7160000205039978},{"id":"https://openalex.org/keywords/gpt-5","display_name":"GPT-5","score":0.6460000276565552},{"id":"https://openalex.org/keywords/context-management","display_name":"context management","score":0.33000001311302185}],"concepts":[{"id":"https://openalex.org/C199168358","wikidata":"https://www.wikidata.org/wiki/Q3367000","display_name":"Orchestration","level":3,"score":0.7856000065803528},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7782999873161316},{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.7077999711036682},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5917999744415283},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5303999781608582},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.5167999863624573},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.32499998807907104},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3165999948978424},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.31520000100135803},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.27309998869895935},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.2694999873638153},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.25920000672340393}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2602.07359","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2602.07359","pdf_url":"https://arxiv.org/pdf/2602.07359","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2602.07359","doi":"https://doi.org/10.48550/arxiv.2602.07359","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2602.07359","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2602.07359","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2602.07359","pdf_url":"https://arxiv.org/pdf/2602.07359","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7128492425.pdf","grobid_xml":"https://content.openalex.org/works/W7128492425.grobid-xml"},"referenced_works_count":6,"referenced_works":["https://openalex.org/W4406840771","https://openalex.org/W4416439805","https://openalex.org/W4417006854","https://openalex.org/W4417089504","https://openalex.org/W7102388436","https://openalex.org/W7125714233"],"related_works":["https://openalex.org/W7127706655","https://openalex.org/W4415250073","https://openalex.org/W4414973506","https://openalex.org/W7126098298","https://openalex.org/W7154367515","https://openalex.org/W7125819036","https://openalex.org/W7128057589","https://openalex.org/W7161583407","https://openalex.org/W7167890363","https://openalex.org/W7127320818"],"abstract_inverted_index":{"Deep":[0,61],"research":[1,62,125,179],"agents":[2,27,74],"have":[3,23],"emerged":[4],"as":[5],"powerful":[6],"tools":[7],"for":[8],"automating":[9],"complex":[10,93],"intellectual":[11],"tasks":[12],"through":[13,31,146],"multi-step":[14],"reasoning":[15,113],"and":[16,38,60,71,149,170],"web-based":[17],"information":[18],"seeking.":[19],"While":[20],"recent":[21],"efforts":[22],"successfully":[24],"enhanced":[25],"these":[26,144],"by":[28,201],"scaling":[29,44,76,118],"depth":[30,79,171],"increasing":[32],"the":[33,41,58,69,129,141,166,197],"number":[34,130],"of":[35,43,73,131],"sequential":[36],"thinking":[37],"tool":[39,48,85,104,152,158],"calls,":[40],"potential":[42],"width":[45,82,119,169],"via":[46,83],"parallel":[47,84,103,157],"calling":[49,105,159],"remains":[50],"largely":[51],"unexplored.":[52],"In":[53],"this":[54],"work,":[55],"we":[56,139,188],"propose":[57],"Wide":[59],"agent,":[63],"a":[64,111,173],"framework":[65],"designed":[66],"to":[67,96,106,134,155],"investigate":[68],"behavior":[70],"performance":[72,122],"when":[75],"not":[77],"only":[78],"but":[80],"also":[81],"calling.":[86],"Unlike":[87],"existing":[88],"approaches":[89],"that":[90,117,164],"rely":[91],"on":[92,123,194],"multi-agent":[94],"orchestration":[95],"parallelize":[97],"workloads,":[98],"our":[99],"method":[100],"leverages":[101],"intrinsic":[102],"facilitate":[107],"effective":[108],"coordination":[109],"within":[110],"single":[112],"step.":[114],"We":[115],"demonstrate":[116],"significantly":[120],"improves":[121],"deep":[124,178],"benchmarks":[126],"while":[127],"reducing":[128],"turns":[132],"required":[133],"obtain":[135,189],"correct":[136],"answers.":[137],"Furthermore,":[138],"analyze":[140],"factors":[142],"driving":[143],"improvements":[145],"case":[147],"studies":[148],"explore":[150],"various":[151],"call":[153],"schedulers":[154],"optimize":[156],"strategy.":[160],"Our":[161],"findings":[162],"suggest":[163],"optimizing":[165],"trade-off":[167],"between":[168],"is":[172],"critical":[174],"pathway":[175],"toward":[176],"high-efficiency":[177],"agents.":[180],"Notably,":[181],"without":[182],"context":[183],"management":[184],"or":[185],"other":[186],"tricks,":[187],"62.2%":[190],"accuracy":[191],"with":[192],"GPT-5-Medium":[193],"BrowseComp,":[195],"surpassing":[196],"original":[198],"54.9%":[199],"reported":[200],"GPT-5-High.":[202]},"counts_by_year":[{"year":2026,"cited_by_count":6}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-02-11T00:00:00"}