{"id":"https://openalex.org/W7222653404","doi":"https://doi.org/10.48550/arxiv.2610.22322","title":"Learning Self-Orchestration in Decentralized Agent Swarms","display_name":"Learning Self-Orchestration in Decentralized Agent Swarms","publication_year":2026,"publication_date":"2026-10-15","ids":{"openalex":"https://openalex.org/W7222653404","doi":"https://doi.org/10.48550/arxiv.2610.22322"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2610.22322","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.22322","pdf_url":"https://arxiv.org/pdf/2610.22322","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/2610.22322","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5158868729","display_name":"Guowei Xu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I136199984","display_name":"Harvard University","ror":"https://ror.org/03vek6s52","country_code":"US","type":"education","lineage":["https://openalex.org/I136199984"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xu, Guowei","raw_affiliation_strings":["Harvard University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harvard University","institution_ids":["https://openalex.org/I136199984"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055702764","display_name":"Zhenting Qi","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I136199984","display_name":"Harvard University","ror":"https://ror.org/03vek6s52","country_code":"US","type":"education","lineage":["https://openalex.org/I136199984"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Qi, Zhenting","raw_affiliation_strings":["Harvard University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harvard University","institution_ids":["https://openalex.org/I136199984"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022060155","display_name":"Amani Kiruga","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I136199984","display_name":"Harvard University","ror":"https://ror.org/03vek6s52","country_code":"US","type":"education","lineage":["https://openalex.org/I136199984"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kiruga, Amani","raw_affiliation_strings":["Harvard University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harvard University","institution_ids":["https://openalex.org/I136199984"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015520086","display_name":"Himabindu Lakkaraju","orcid":"https://orcid.org/0000-0001-7922-6544","observed_orcids":["https://orcid.org/0000-0001-7922-6544"]},"institutions":[{"id":"https://openalex.org/I136199984","display_name":"Harvard University","ror":"https://ror.org/03vek6s52","country_code":"US","type":"education","lineage":["https://openalex.org/I136199984"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lakkaraju, Himabindu","raw_affiliation_strings":["Harvard University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harvard University","institution_ids":["https://openalex.org/I136199984"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5158902934","display_name":"Yilun Du","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I136199984","display_name":"Harvard University","ror":"https://ror.org/03vek6s52","country_code":"US","type":"education","lineage":["https://openalex.org/I136199984"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Du, Yilun","raw_affiliation_strings":["Harvard University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harvard University","institution_ids":["https://openalex.org/I136199984"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I136199984"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"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/T10456","display_name":"Multi-Agent Systems and Negotiation","score":0.288100004196167,"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":0.288100004196167,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.27559998631477356,"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/T10249","display_name":"Distributed Control Multi-Agent Systems","score":0.2515000104904175,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/bidding-behavior","display_name":"bidding behavior","score":0.6970000267028809},{"id":"https://openalex.org/keywords/multiagent-coordination","display_name":"multi-agent coordination","score":0.7099999785423279},{"id":"https://openalex.org/keywords/robot-navigation","display_name":"robot navigation","score":0.9919999837875366},{"id":"https://openalex.org/keywords/collective-behavior","display_name":"collective behavior","score":0.39500001072883606}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.691100001335144},{"id":"https://openalex.org/C9233905","wikidata":"https://www.wikidata.org/wiki/Q3276328","display_name":"Bidding","level":2,"score":0.6463000178337097},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6173999905586243},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5266000032424927},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5145999789237976},{"id":"https://openalex.org/C199168358","wikidata":"https://www.wikidata.org/wiki/Q3367000","display_name":"Orchestration","level":3,"score":0.48919999599456787},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.48750001192092896},{"id":"https://openalex.org/C41550386","wikidata":"https://www.wikidata.org/wiki/Q529909","display_name":"Multi-agent system","level":2,"score":0.4812999963760376},{"id":"https://openalex.org/C169337768","wikidata":"https://www.wikidata.org/wiki/Q2446723","display_name":"Swarm robotics","level":3,"score":0.4706000089645386},{"id":"https://openalex.org/C181335050","wikidata":"https://www.wikidata.org/wiki/Q14915018","display_name":"Swarm behaviour","level":2,"score":0.44359999895095825},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.41780000925064087},{"id":"https://openalex.org/C103683099","wikidata":"https://www.wikidata.org/wiki/Q5370102","display_name":"Embodied agent","level":3,"score":0.39250001311302185},{"id":"https://openalex.org/C100609095","wikidata":"https://www.wikidata.org/wiki/Q1335050","display_name":"Embodied cognition","level":2,"score":0.39100000262260437},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.37790000438690186},{"id":"https://openalex.org/C74072328","wikidata":"https://www.wikidata.org/wiki/Q1142726","display_name":"Intelligent agent","level":2,"score":0.3522000014781952},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.34850001335144043},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.28290000557899475},{"id":"https://openalex.org/C13687954","wikidata":"https://www.wikidata.org/wiki/Q4826847","display_name":"Autonomous agent","level":2,"score":0.2818000018596649},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.2777000069618225},{"id":"https://openalex.org/C166109690","wikidata":"https://www.wikidata.org/wiki/Q4677422","display_name":"Action selection","level":3,"score":0.2734000086784363},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.2615000009536743}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2610.22322","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.22322","pdf_url":"https://arxiv.org/pdf/2610.22322","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.2610.22322","doi":"https://doi.org/10.48550/arxiv.2610.22322","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2610.22322","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:2610.22322","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.22322","pdf_url":"https://arxiv.org/pdf/2610.22322","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":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7222653404.pdf","grobid_xml":"https://content.openalex.org/works/W7222653404.grobid-xml"},"referenced_works_count":8,"referenced_works":["https://openalex.org/W1760997490","https://openalex.org/W2119717200","https://openalex.org/W2964339842","https://openalex.org/W3014266552","https://openalex.org/W4387835442","https://openalex.org/W4402684050","https://openalex.org/W4405783893","https://openalex.org/W4416780398"],"related_works":["https://openalex.org/W4404896819","https://openalex.org/W4392305667","https://openalex.org/W7215000109","https://openalex.org/W3175267607","https://openalex.org/W1537982122","https://openalex.org/W7167816663","https://openalex.org/W7164001001","https://openalex.org/W6996915380","https://openalex.org/W1593417677","https://openalex.org/W7127150490"],"abstract_inverted_index":{"The":[0],"capabilities":[1,32,85],"of":[2,30,36,88],"an":[3],"agent":[4,55,118,185,198],"swarm":[5],"depend":[6],"on":[7,101,204],"both":[8,78,139],"its":[9],"individual":[10,31,84],"members":[11],"and":[12,51,69,80,86,106,115,141,146,167,194],"how":[13,70],"they":[14],"coordinate.":[15],"Yet":[16],"existing":[17],"multi-agent":[18],"systems":[19],"often":[20],"train":[21],"agents":[22],"within":[23],"fixed":[24],"orchestration":[25],"structures,":[26],"separating":[27],"the":[28,34,125,156],"learning":[29,48],"from":[33,144],"organization":[35],"collective":[37,71],"behavior.":[38],"We":[39,98],"introduce":[40],"market-based":[41],"post-training":[42,114],"(MPT),":[43],"a":[44,94],"framework":[45],"for":[46],"jointly":[47],"action":[49,79,128,140],"policies":[50],"self-orchestration":[52,131,190],"in":[53,196],"decentralized":[54,197],"swarms.":[56,199],"Agents":[57],"express":[58],"their":[59],"willingness":[60],"to":[61,90,164],"participate":[62],"through":[63],"bids,":[64],"which":[65],"determine":[66],"who":[67],"acts":[68],"outcomes":[72],"provide":[73,150],"local":[74],"training":[75,158],"credit.":[76],"Learning":[77],"bidding":[81,142],"behavior":[82],"allows":[83],"patterns":[87],"participation":[89,119],"adapt":[91,162],"together":[92],"without":[93],"central":[95],"coordinating":[96],"agent.":[97],"evaluate":[99],"MPT":[100],"embodied":[102],"crafting,":[103],"robot":[104],"navigation,":[105],"deep":[107],"research.":[108],"Results":[109],"show":[110,137],"gains":[111],"over":[112],"monolithic":[113],"confirm":[116],"that":[117,138,147,188],"indeed":[120],"evolves":[121],"with":[122,171],"learning.":[123],"With":[124],"same":[126],"post-trained":[127],"policies,":[129],"learned":[130,148,189],"outperforms":[132],"alternative":[133],"coordination":[134],"strategies.":[135],"Ablations":[136],"benefit":[143],"learning,":[145],"bids":[149],"more":[151],"effective":[152],"action-training":[153],"signals.":[154],"Beyond":[155],"original":[157],"objectives,":[159],"trained":[160],"swarms":[161],"faster":[163],"related":[165],"tasks":[166],"achieve":[168],"better":[169],"performance":[170,182],"larger":[172],"populations":[173,178],"at":[174,208],"inference":[175],"time.":[176],"Larger":[177],"also":[179],"suffer":[180],"smaller":[181],"losses":[183],"under":[184],"dropout,":[186],"demonstrating":[187],"supports":[191],"reuse,":[192],"scaling,":[193],"robustness":[195],"More":[200],"details":[201],"are":[202],"available":[203],"our":[205],"project":[206],"page":[207],"https://guoweixu.com/mpt/.":[209]},"counts_by_year":[],"updated_date":"2026-11-08T12:12:28.789561","created_date":"2026-10-17T00:00:00"}