{"id":"https://openalex.org/W7166877659","doi":"https://doi.org/10.18653/v1/2026.acl-long.216","title":"D2Plan: Dual-Agent Dynamic Global Planning for Complex Retrieval-Augmented Reasoning","display_name":"D2Plan: Dual-Agent Dynamic Global Planning for Complex Retrieval-Augmented Reasoning","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7166877659","doi":"https://doi.org/10.18653/v1/2026.acl-long.216"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2026.acl-long.216","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.216","pdf_url":"https://aclanthology.org/2026.acl-long.216.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.216.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102690975","display_name":"Kangcheng Luo","orcid":null},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kangcheng Luo","raw_affiliation_strings":["Peking University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Peking University","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5121822884","display_name":"Tinglang Wu","orcid":null},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tinglang Wu","raw_affiliation_strings":["Peking University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Peking University","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5139814112","display_name":"Yansong Feng","orcid":null},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yansong Feng","raw_affiliation_strings":["Peking University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Peking University","institution_ids":["https://openalex.org/I20231570"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I20231570"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.8656772,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4722","last_page":"4754"},"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":0.854200005531311,"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":0.854200005531311,"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/T11010","display_name":"Logic, Reasoning, and Knowledge","score":0.03629999980330467,"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":0.03550000116229057,"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/process","display_name":"Process (computing)","score":0.34119999408721924},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.3278999924659729},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.2976999878883362},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.29499998688697815},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.2651999890804291}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.566100001335144},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.39809998869895935},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.34119999408721924},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.3278999924659729},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2976999878883362},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.29499998688697815},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.2651999890804291},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.24269999563694},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.23029999434947968},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.2232999950647354}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2026.acl-long.216","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.216","pdf_url":"https://aclanthology.org/2026.acl-long.216.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.216","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.216","pdf_url":"https://aclanthology.org/2026.acl-long.216.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":[{"display_name":"Climate action","id":"https://metadata.un.org/sdg/13","score":0.4408339560031891},{"display_name":"Sustainable cities and communities","id":"https://metadata.un.org/sdg/11","score":0.408709853887558}],"awards":[{"id":"https://openalex.org/G7590666161","display_name":null,"funder_award_id":"92570207","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7166877659.pdf","grobid_xml":"https://content.openalex.org/works/W7166877659.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Recent":[0],"search-augmented":[1],"LLMs":[2,147],"trained":[3],"with":[4,29,142],"reinforcement":[5],"learning":[6],"(RL)":[7],"can":[8],"interleave":[9],"searching":[10],"and":[11,33,51,94,105,118,140,166],"reasoning":[12,15,53,104,165],"for":[13,81,122],"multi-hop":[14],"tasks.However,":[16],"they":[17],"face":[18],"two":[19],"critical":[20,49],"failure":[21],"modes":[22],"as":[23,64],"the":[24,89,97,113,123,150],"accumulating":[25],"context":[26],"becomes":[27],"flooded":[28],"both":[30],"crucial":[31],"evidence":[32,57],"irrelevant":[34,170],"information:":[35],"(1)":[36],"ineffective":[37],"search":[38],"chain":[39],"construction":[40],"that":[41,58,157],"produces":[42],"incorrect":[43],"queries":[44],"or":[45],"omits":[46],"retrieval":[47,111,116],"of":[48,91,132],"information,":[50,171],"(2)":[52],"hijacking":[54],"by":[55],"peripheral":[56],"causes":[59],"models":[60],"to":[61,145,148,169],"misidentify":[62],"distractors":[63],"valid":[65],"evidence.To":[66],"address":[67],"these":[68],"challenges,":[69],"we":[70],"propose":[71],"D":[72,151,158],"2":[73,85,152,159],"PLAN,":[74],"a":[75,92,95,127],"Dual-agent":[76],"Dynamic":[77],"global":[78,101],"Planning":[79],"paradigm":[80],"complex":[82],"retrieval-augmented":[83],"reasoning.D":[84],"PLAN":[86,153,160],"operates":[87],"through":[88],"collaboration":[90],"Reasoner":[93,98],"Purifier:":[96],"constructs":[99],"explicit":[100],"plans":[102],"during":[103],"dynamically":[106],"adapts":[107],"them":[108],"based":[109],"on":[110,137,176],"feedback;":[112],"Purifier":[114],"assesses":[115],"relevance":[117],"condenses":[119],"key":[120],"information":[121],"Reasoner.We":[124],"further":[125],"introduce":[126],"two-stage":[128],"training":[129],"framework":[130],"consisting":[131],"supervised":[133],"finetuning":[134],"(SFT)":[135],"cold-start":[136],"synthesized":[138],"trajectories":[139],"RL":[141],"plan-oriented":[143],"rewards":[144],"teach":[146],"master":[149],"paradigm.Extensive":[154],"experiments":[155],"demonstrate":[156],"enables":[161],"more":[162],"coherent":[163],"multi-step":[164],"stronger":[167],"resilience":[168],"thereby":[172],"achieving":[173],"superior":[174],"performance":[175],"challenging":[177],"QA":[178],"benchmarks.":[179]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-07-02T00:00:00"}