{"id":"https://openalex.org/W4416750078","doi":"https://doi.org/10.1109/iros60139.2025.11247645","title":"Advancing Learnable Multi-Agent Pathfinding Solvers with Active Fine-Tuning","display_name":"Advancing Learnable Multi-Agent Pathfinding Solvers with Active Fine-Tuning","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4416750078","doi":"https://doi.org/10.1109/iros60139.2025.11247645"},"language":null,"primary_location":{"id":"doi:10.1109/iros60139.2025.11247645","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros60139.2025.11247645","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5020304186","display_name":"Anton Andreychuk","orcid":"https://orcid.org/0000-0001-5320-4603"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Anton Andreychuk","raw_affiliation_strings":["AIRI,Moscow,Russia"],"affiliations":[{"raw_affiliation_string":"AIRI,Moscow,Russia","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056981356","display_name":"Konstantin Yakovlev","orcid":"https://orcid.org/0000-0002-4377-321X"},"institutions":[{"id":"https://openalex.org/I4210151089","display_name":"Geophysical Center","ror":"https://ror.org/04w1wsw24","country_code":"RU","type":"facility","lineage":["https://openalex.org/I1313323035","https://openalex.org/I4210151089","https://openalex.org/I4210163714"]}],"countries":["RU"],"is_corresponding":false,"raw_author_name":"Konstantin Yakovlev","raw_affiliation_strings":["FRC CSC RAS,Moscow,Russia"],"affiliations":[{"raw_affiliation_string":"FRC CSC RAS,Moscow,Russia","institution_ids":["https://openalex.org/I4210151089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080806360","display_name":"Aleksandr I. Panov","orcid":"https://orcid.org/0000-0002-9747-3837"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Aleksandr Panov","raw_affiliation_strings":["AIRI,Moscow,Russia"],"affiliations":[{"raw_affiliation_string":"AIRI,Moscow,Russia","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5089256022","display_name":"Alexey Skrynnik","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Alexey Skrynnik","raw_affiliation_strings":["AIRI,Moscow,Russia"],"affiliations":[{"raw_affiliation_string":"AIRI,Moscow,Russia","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5020304186"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.40250479,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"10564","last_page":"10571"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10586","display_name":"Robotic Path Planning Algorithms","score":0.954200029373169,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T10586","display_name":"Robotic Path Planning Algorithms","score":0.954200029373169,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.004399999976158142,"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/T10906","display_name":"AI-based Problem Solving and Planning","score":0.0027000000700354576,"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/pathfinding","display_name":"Pathfinding","score":0.6840000152587891},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.6223000288009644},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.521399974822998},{"id":"https://openalex.org/keywords/trajectory","display_name":"Trajectory","score":0.4668000042438507},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.4081000089645386},{"id":"https://openalex.org/keywords/abstraction","display_name":"Abstraction","score":0.37689998745918274},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.33980000019073486},{"id":"https://openalex.org/keywords/scope","display_name":"Scope (computer science)","score":0.3179999887943268}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.724399983882904},{"id":"https://openalex.org/C25321074","wikidata":"https://www.wikidata.org/wiki/Q1969601","display_name":"Pathfinding","level":4,"score":0.6840000152587891},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.6223000288009644},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.521399974822998},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4681999981403351},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.4668000042438507},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.4081000089645386},{"id":"https://openalex.org/C124304363","wikidata":"https://www.wikidata.org/wiki/Q673661","display_name":"Abstraction","level":2,"score":0.37689998745918274},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.33980000019073486},{"id":"https://openalex.org/C2778012447","wikidata":"https://www.wikidata.org/wiki/Q1034415","display_name":"Scope (computer science)","level":2,"score":0.3179999887943268},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3102000057697296},{"id":"https://openalex.org/C149810388","wikidata":"https://www.wikidata.org/wiki/Q5374873","display_name":"Emulation","level":2,"score":0.30959999561309814},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.3046000003814697},{"id":"https://openalex.org/C66882249","wikidata":"https://www.wikidata.org/wiki/Q169336","display_name":"Homogeneous","level":2,"score":0.2953000068664551},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.29339998960494995},{"id":"https://openalex.org/C2776505523","wikidata":"https://www.wikidata.org/wiki/Q4785468","display_name":"Plan (archaeology)","level":2,"score":0.2897000014781952},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.2833000123500824},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.2831000089645386},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.2775000035762787},{"id":"https://openalex.org/C73301696","wikidata":"https://www.wikidata.org/wiki/Q5469984","display_name":"Formalism (music)","level":3,"score":0.26170000433921814},{"id":"https://openalex.org/C168065819","wikidata":"https://www.wikidata.org/wiki/Q845566","display_name":"Debugging","level":2,"score":0.2614000141620636},{"id":"https://openalex.org/C114073186","wikidata":"https://www.wikidata.org/wiki/Q2631895","display_name":"Automated planning and scheduling","level":2,"score":0.26089999079704285},{"id":"https://openalex.org/C2779231336","wikidata":"https://www.wikidata.org/wiki/Q7534724","display_name":"Sketch","level":2,"score":0.257099986076355}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iros60139.2025.11247645","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros60139.2025.11247645","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W1588299616","https://openalex.org/W1973396716","https://openalex.org/W1989407213","https://openalex.org/W2124015815","https://openalex.org/W2575733488","https://openalex.org/W2579451340","https://openalex.org/W2892258706","https://openalex.org/W2903998385","https://openalex.org/W2914864020","https://openalex.org/W2964035402","https://openalex.org/W2964997335","https://openalex.org/W2981057983","https://openalex.org/W3037164939","https://openalex.org/W3166401044","https://openalex.org/W3201099806","https://openalex.org/W3204358081","https://openalex.org/W3206082228","https://openalex.org/W4283795314","https://openalex.org/W4312938942","https://openalex.org/W4362590704","https://openalex.org/W4382202651","https://openalex.org/W4382202860","https://openalex.org/W4386322136","https://openalex.org/W4388820116","https://openalex.org/W4389689571","https://openalex.org/W4392824688","https://openalex.org/W4393160223","https://openalex.org/W4394994419","https://openalex.org/W4402890475","https://openalex.org/W4403279656","https://openalex.org/W4405785123","https://openalex.org/W4409347993","https://openalex.org/W4413917925","https://openalex.org/W4413945055","https://openalex.org/W4415795780","https://openalex.org/W4415798273","https://openalex.org/W6922480057"],"related_works":[],"abstract_inverted_index":{"Multi-agent":[0],"pathfinding":[1],"(MAPF)":[2],"is":[3],"a":[4,69,91,142,146],"common":[5],"abstraction":[6],"of":[7,64],"multi-robot":[8],"trajectory":[9],"planning":[10],"problems,":[11],"where":[12],"multiple":[13],"homogeneous":[14],"robots":[15],"simultaneously":[16],"move":[17],"in":[18,141,151],"the":[19,62,65,82,118],"shared":[20],"environment.":[21],"While":[22],"solving":[23],"MAPF":[24,50,84,115,133,152],"optimally":[25],"has":[26],"been":[27],"proven":[28],"to":[29,137],"be":[30],"NP-hard,":[31],"scalable,":[32],"and":[33],"efficient,":[34],"solvers":[35,51],"are":[36],"vital":[37],"for":[38,149],"real-world":[39],"applications":[40],"like":[41],"logistics,":[42],"search-and-rescue,":[43],"etc.":[44],"To":[45],"this":[46],"end,":[47],"decentralized":[48],"suboptimal":[49],"that":[52,109],"leverage":[53],"machine":[54],"learning":[55,72],"have":[56],"come":[57],"on":[58,61],"stage.":[59],"Building":[60],"success":[63],"recently":[66],"introduced":[67],"MAPF-GPT,":[68,120],"pure":[70],"imitation":[71],"solver,":[73],"we":[74],"introduce":[75],"MAPF-GPT-DDG.":[76],"This":[77],"novel":[78,92],"approach":[79],"effectively":[80],"fine-tunes":[81],"pre-trained":[83],"model":[85],"using":[86],"centralized":[87],"expert":[88],"data.":[89],"Leveraging":[90],"delta-data":[93],"generation":[94],"mechanism,":[95],"MAPF-GPT-DDG":[96,110],"accelerates":[97],"training":[98],"while":[99],"significantly":[100],"improving":[101],"performance":[102],"at":[103],"test":[104],"time.":[105],"Our":[106],"experiments":[107],"demonstrate":[108],"surpasses":[111],"all":[112],"existing":[113],"learning-based":[114],"solvers,":[116],"including":[117],"original":[119],"regarding":[121],"solution":[122],"quality":[123],"across":[124],"many":[125],"testing":[126],"scenarios.":[127],"Remarkably,":[128],"it":[129],"can":[130],"work":[131],"with":[132],"instances":[134],"involving":[135],"up":[136],"1":[138],"million":[139],"agents":[140],"single":[143],"environment,":[144],"setting":[145],"new":[147],"milestone":[148],"scalability":[150],"domains.":[153]},"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-11-28T00:00:00"}