{"id":"https://openalex.org/W7166796391","doi":"https://doi.org/10.18653/v1/2026.acl-long.1543","title":"NeuralFSM: Adaptive Multi-Agent Coordination via Learning Finite-State Execution Policy","display_name":"NeuralFSM: Adaptive Multi-Agent Coordination via Learning Finite-State Execution Policy","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7166796391","doi":"https://doi.org/10.18653/v1/2026.acl-long.1543"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2026.acl-long.1543","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.1543","pdf_url":"https://aclanthology.org/2026.acl-long.1543.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.1543.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5125270206","display_name":"Jiye Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiye Wang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139793138","display_name":"Yu Guang Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yu Wang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139831569","display_name":"Jianbin Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jianbin Li","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113397476","display_name":"Shiduo Yang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shiduo Yang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139804621","display_name":"Kenan Guo","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kenan Guo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5125265534","display_name":"Yuanhe Zhao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yuanhe Zhao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.78598787,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"33414","last_page":"33436"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.8033999800682068,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.8033999800682068,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.06549999862909317,"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/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.02160000056028366,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/task","display_name":"Task (project management)","score":0.34380000829696655},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.3142000138759613},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.3001999855041504},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.2994000017642975},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.289000004529953},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.2856999933719635}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6190000176429749},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.34380000829696655},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.32910001277923584},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.3142000138759613},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.3001999855041504},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2994000017642975},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.289000004529953},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.2856999933719635},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.2786000072956085},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.272599995136261},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.26190000772476196},{"id":"https://openalex.org/C182306322","wikidata":"https://www.wikidata.org/wiki/Q1779371","display_name":"Order (exchange)","level":2,"score":0.2531999945640564}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2026.acl-long.1543","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.1543","pdf_url":"https://aclanthology.org/2026.acl-long.1543.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.1543","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.1543","pdf_url":"https://aclanthology.org/2026.acl-long.1543.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/W7166796391.pdf","grobid_xml":"https://content.openalex.org/works/W7166796391.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"LLM-powered":[0],"multi-agent":[1,37],"systems":[2],"(MAS)":[3],"have":[4],"demonstrated":[5],"strong":[6,132],"performance":[7,148],"on":[8,16,107],"complex":[9],"tasks.However,":[10],"most":[11],"existing":[12],"approaches":[13],"still":[14],"rely":[15],"hand-crafted":[17],"communication":[18,23,53],"protocols":[19],"or":[20,91],"automatically":[21],"designed":[22],"topologies,":[24],"which":[25,135],"generalize":[26],"poorly":[27],"across":[28],"tasks.We":[29],"introduce":[30],"NeuralFSM,":[31],"a":[32,41,59,146],"state-driven":[33],"framework":[34,70],"that":[35,111],"formulates":[36],"problem":[38],"solving":[39],"as":[40],"finite-state":[42],"execution":[43],"process.NeuralFSM":[44],"learns":[45],"both":[46],"the":[47,68,140],"state":[48],"transition":[49,76],"distribution":[50],"and":[51,77,100],"inter-agent":[52],"weights":[54],"from":[55],"interaction":[56],"traces":[57],"using":[58],"Temporal":[60],"Coordination":[61],"Controller.Rather":[62],"than":[63],"prioritizing":[64],"explicit":[65],"structure":[66],"generation,":[67],"proposed":[69],"uses":[71],"task":[72],"context":[73],"to":[74],"modulate":[75],"routing":[78],"decisions,":[79],"enabling":[80],"flexible":[81],"coordination":[82],"without":[83],"manual":[84],"protocol":[85],"design.To":[86],"improve":[87],"robustness":[88],"against":[89],"noisy":[90],"adversarial":[92],"agents,":[93],"we":[94],"incorporate":[95],"graph":[96],"regularization":[97],"during":[98],"training":[99],"apply":[101],"trust-aware":[102],"message":[103],"attenuation":[104],"at":[105,155],"runtime.Experiments":[106],"diverse":[108],"benchmarks":[109],"show":[110],"NeuralFSM":[112,130],"consistently":[113],"outperforms":[114],"previous":[115],"baselines":[116],"by":[117,139],"an":[118],"average":[119],"margin":[120],"of":[121],"6.74%":[122],"\u223c":[123],"19.39%,":[124],"while":[125],"substantially":[126],"reducing":[127],"token":[128],"consumption.Moreover,":[129],"exhibits":[131],"inherent":[133],"robustness,":[134],"is":[136,153],"further":[137],"enhanced":[138],"protection":[141],"layer,":[142],"resulting":[143],"only":[144],"in":[145],"1.82%":[147],"drop":[149],"under":[150],"attack.The":[151],"code":[152],"available":[154],"https:":[156],"//github.com/DisseverYOLO/NeuralFSM.":[157]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-07-02T00:00:00"}