{"id":"https://openalex.org/W7166873365","doi":"https://doi.org/10.18653/v1/2026.acl-long.1100","title":"SPARK: Strategic Policy-Aware Exploration via Dynamic Branching for Long-Horizon Agentic Learning","display_name":"SPARK: Strategic Policy-Aware Exploration via Dynamic Branching for Long-Horizon Agentic Learning","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7166873365","doi":"https://doi.org/10.18653/v1/2026.acl-long.1100"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2026.acl-long.1100","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.1100","pdf_url":"https://aclanthology.org/2026.acl-long.1100.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.1100.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5139798608","display_name":"Jinyang Wu","orcid":null},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jinyang Wu","raw_affiliation_strings":["Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139757557","display_name":"Shuo Yang","orcid":null},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuo Yang","raw_affiliation_strings":["Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139841709","display_name":"Yuhao Shen","orcid":null},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuhao Shen","raw_affiliation_strings":["Zhejiang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139728445","display_name":"Shuai Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuai Zhang","raw_affiliation_strings":["Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139852042","display_name":"Zhengqi Wen","orcid":null},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhengqi Wen","raw_affiliation_strings":["Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5139733429","display_name":"Jianhua Tao","orcid":null},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianhua Tao","raw_affiliation_strings":["Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"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":0.83545459,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"23981","last_page":"24004"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.7631999850273132,"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":0.7631999850273132,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.01679999940097332,"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/T11273","display_name":"Advanced Graph Neural Networks","score":0.011500000022351742,"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/branching","display_name":"Branching (polymer chemistry)","score":0.4293000102043152},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.29330000281333923},{"id":"https://openalex.org/keywords/perspective","display_name":"Perspective (graphical)","score":0.28529998660087585},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.2669999897480011},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.24740000069141388}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.539900004863739},{"id":"https://openalex.org/C206175624","wikidata":"https://www.wikidata.org/wiki/Q595731","display_name":"Branching (polymer chemistry)","level":2,"score":0.4293000102043152},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3725999891757965},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.29330000281333923},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.28529998660087585},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.2669999897480011},{"id":"https://openalex.org/C56739046","wikidata":"https://www.wikidata.org/wiki/Q192060","display_name":"Knowledge management","level":1,"score":0.2563000023365021},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.24740000069141388},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.2418999969959259},{"id":"https://openalex.org/C37228920","wikidata":"https://www.wikidata.org/wiki/Q1307600","display_name":"Experiential learning","level":2,"score":0.23240000009536743}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2026.acl-long.1100","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.1100","pdf_url":"https://aclanthology.org/2026.acl-long.1100.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.1100","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.1100","pdf_url":"https://aclanthology.org/2026.acl-long.1100.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":[{"score":0.415907084941864,"id":"https://metadata.un.org/sdg/13","display_name":"Climate action"}],"awards":[{"id":"https://openalex.org/G1202467192","display_name":null,"funder_award_id":"U21B2010","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":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7166873365.pdf","grobid_xml":"https://content.openalex.org/works/W7166873365.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Reinforcement":[0],"learning":[1],"has":[2],"empowered":[3],"large":[4],"language":[5],"models":[6],"to":[7,21,56,88,97,120,129],"act":[8],"as":[9],"intelligent":[10],"agents,":[11],"yet":[12],"training":[13,153],"them":[14],"for":[15,82],"long-horizon":[16],"tasks":[17,139],"remains":[18],"challenging":[19],"due":[20],"the":[22,115,127],"scarcity":[23],"of":[24],"highquality":[25],"trajectories,":[26,100],"especially":[27],"under":[28],"limited":[29],"resources.Existing":[30],"methods":[31],"typically":[32],"scale":[33],"up":[34],"rollout":[35],"sizes":[36],"and":[37,133,163],"indiscriminately":[38],"allocate":[39],"computational":[40],"resources":[41],"among":[42],"intermediate":[43],"steps.Such":[44],"attempts":[45],"inherently":[46],"waste":[47],"substantial":[48],"computation":[49],"budget":[50],"on":[51,123],"trivial":[52],"steps":[53],"while":[54],"failing":[55],"guarantee":[57],"sample":[58],"quality.To":[59],"address":[60],"this,":[61],"we":[62],"propose":[63],"SPARK":[64,145],"(Strategic":[65],"Policy-Aware":[66],"ex-ploRation":[67],"via":[68],"Key-state":[69],"dynamic":[70],"branching),":[71],"a":[72],"novel":[73],"framework":[74],"that":[75,106,144],"selectively":[76],"branches":[77],"at":[78,93,167],"critical":[79,94],"decision":[80,95],"states":[81],"resource-efficient":[83],"exploration.Our":[84],"key":[85],"insight":[86],"is":[87],"activate":[89],"adaptive":[90],"branching":[91],"exploration":[92,132],"points":[96],"probe":[98],"promising":[99],"thereby":[101],"achieving":[102],"precise":[103],"resource":[104],"allocation":[105],"prioritizes":[107],"sampling":[108],"quality":[109],"over":[110],"blind":[111],"coverage.This":[112],"design":[113],"leverages":[114],"agent's":[116],"intrinsic":[117],"decisionmaking":[118],"signals":[119],"reduce":[121],"dependence":[122],"human":[124],"priors,":[125],"enabling":[126],"agent":[128],"autonomously":[130],"expand":[131],"achieve":[134],"stronger":[135],"generalization.Experiments":[136],"across":[137],"diverse":[138],"(e.g.,":[140],"embodied":[141],"planning),":[142],"demonstrate":[143],"achieves":[146],"superior":[147],"success":[148],"rates":[149],"with":[150],"significantly":[151],"fewer":[152],"samples,":[154],"exhibiting":[155],"robust":[156],"generalization":[157],"even":[158],"in":[159],"unseen":[160],"scenarios.Our":[161],"code":[162],"checkpoints":[164],"are":[165],"available":[166],"https://github.com/jinyangwu/SPARK.":[168]},"counts_by_year":[],"updated_date":"2026-08-21T09:56:20.448147","created_date":"2026-07-02T00:00:00"}