{"id":"https://openalex.org/W4415274157","doi":"https://doi.org/10.18653/v1/2026.findings-acl.370","title":"DeepPlanner: Scaling Planning Capability for Deep Research Agents via Advantage Shaping","display_name":"DeepPlanner: Scaling Planning Capability for Deep Research Agents via Advantage Shaping","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W4415274157","doi":"https://doi.org/10.18653/v1/2026.findings-acl.370"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2026.findings-acl.370","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.370","pdf_url":"https://aclanthology.org/2026.findings-acl.370.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":"Findings of the Association for Computational Linguistics: ACL 2026","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2026.findings-acl.370.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5066173871","display_name":"Wei Fan","orcid":"https://orcid.org/0000-0002-5980-4527"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wei Fan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114418786","display_name":"Wenlin Yao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wenlin Yao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100414978","display_name":"Zheng Li","orcid":"https://orcid.org/0000-0002-1518-5605"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zheng Li","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100313991","display_name":"Feng Yao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Feng Yao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100352262","display_name":"Xin Liu","orcid":"https://orcid.org/0000-0002-7339-2805"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xin Liu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021695553","display_name":"Liang Qiu","orcid":"https://orcid.org/0000-0002-6752-1340"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liang Qiu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100610166","display_name":"Qingyu Yin","orcid":"https://orcid.org/0009-0006-1129-4704"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qingyu Yin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Yangqiu Song","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yangqiu Song","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5088485347","display_name":"Bing Yin","orcid":"https://orcid.org/0000-0001-8889-2493"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bing Yin","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":0.01496919,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"7510","last_page":"7525"},"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":0.8041999936103821,"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":0.8041999936103821,"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/T10586","display_name":"Robotic Path Planning Algorithms","score":0.7942000031471252,"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":0.7325000166893005,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.6646000146865845},{"id":"https://openalex.org/keywords/automated-planning-and-scheduling","display_name":"Automated planning and scheduling","score":0.5411999821662903},{"id":"https://openalex.org/keywords/entropy","display_name":"Entropy (arrow of time)","score":0.5238999724388123},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.35100001096725464},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.3433000147342682},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.3343999981880188}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7386000156402588},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6646000146865845},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.595300018787384},{"id":"https://openalex.org/C114073186","wikidata":"https://www.wikidata.org/wiki/Q2631895","display_name":"Automated planning and scheduling","level":2,"score":0.5411999821662903},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.5238999724388123},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.43290001153945923},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.35100001096725464},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.3433000147342682},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.3343999981880188},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.29739999771118164},{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.2924000024795532},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.27950000762939453},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.2732999920845032},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.25949999690055847},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.25279998779296875}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.18653/v1/2026.findings-acl.370","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.370","pdf_url":"https://aclanthology.org/2026.findings-acl.370.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":"Findings of the Association for Computational Linguistics: ACL 2026","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2510.12979","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2510.12979","pdf_url":"https://arxiv.org/pdf/2510.12979","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,"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.2510.12979","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2510.12979","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,"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":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.findings-acl.370","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.370","pdf_url":"https://aclanthology.org/2026.findings-acl.370.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":"Findings of the Association for Computational Linguistics: ACL 2026","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G6239232959","display_name":"IPA: Intelligent Privacy Assistant for Large Language Model Applications","funder_award_id":"ITS/189/23FP","funder_id":"https://openalex.org/F4320321920","funder_display_name":"Innovation and Technology Commission"}],"funders":[{"id":"https://openalex.org/F4320321920","display_name":"Innovation and Technology Commission","ror":"https://ror.org/04vf9tr09"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4415274157.pdf","grobid_xml":"https://content.openalex.org/works/W4415274157.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Large":[0],"language":[1],"models":[2],"(LLMs)":[3],"augmented":[4],"with":[5,101],"multi-step":[6],"reasoning":[7,36],"and":[8,113,133],"action":[9,68],"generation":[10],"abilities":[11],"have":[12],"shown":[13],"promise":[14],"in":[15,34],"leveraging":[16],"external":[17],"tools":[18],"to":[19,46,105,109],"tackle":[20],"complex":[21],"tasks":[22],"that":[23,54,74,87,128],"require":[24],"long-horizon":[25],"planning.However,":[26],"existing":[27],"approaches":[28],"either":[29],"rely":[30],"on":[31],"implicit":[32],"planning":[33,49,60,91,131],"the":[35,48,90],"stage":[37],"or":[38],"introduce":[39],"explicit":[40],"planners":[41],"without":[42],"systematically":[43],"addressing":[44],"how":[45],"optimize":[47],"stage.As":[50],"evidence,":[51],"we":[52,79],"observe":[53],"under":[55,137],"vanilla":[56],"reinforcement":[57],"learning":[58],"(RL),":[59],"tokens":[61],"exhibit":[62],"significantly":[63],"higher":[64],"entropy":[65,111],"than":[66],"other":[67],"tokens,":[69,112],"revealing":[70],"uncertain":[71],"decision":[72],"points":[73],"remain":[75],"under-optimized.To":[76],"address":[77],"this,":[78],"propose":[80],"DEEPPLANNER1":[81],",":[82],"an":[83,102],"end-to-end":[84],"RL":[85],"framework":[86],"effectively":[88],"enhances":[89],"capabilities":[92],"of":[93],"deep":[94,124],"research":[95,125],"agents.Our":[96],"approach":[97],"shapes":[98],"token-level":[99],"advantage":[100],"entropy-based":[103],"term":[104],"allocate":[106],"larger":[107],"updates":[108],"high":[110],"selectively":[114],"upweights":[115],"sample-level":[116],"advantages":[117],"for":[118],"planning-intensive":[119],"rollouts.Extensive":[120],"experiments":[121],"across":[122],"seven":[123],"benchmarks":[126],"demonstrate":[127],"DEEPPLANNER":[129],"improves":[130],"quality":[132],"achieves":[134],"state-of-the-art":[135],"results":[136],"a":[138],"substantially":[139],"lower":[140],"training":[141],"budget.":[142]},"counts_by_year":[],"updated_date":"2026-08-05T07:39:15.569665","created_date":"2025-10-17T00:00:00"}