{"id":"https://openalex.org/W4417449994","doi":"https://doi.org/10.1145/3773966.3777986","title":"CoDA: A Context-Decoupled Hierarchical Agent with Reinforcement Learning","display_name":"CoDA: A Context-Decoupled Hierarchical Agent with Reinforcement Learning","publication_year":2026,"publication_date":"2026-02-16","ids":{"openalex":"https://openalex.org/W4417449994","doi":"https://doi.org/10.1145/3773966.3777986"},"language":null,"primary_location":{"id":"doi:10.1145/3773966.3777986","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3773966.3777986","pdf_url":null,"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 Nineteenth ACM International Conference on Web Search and Data Mining","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3773966.3777986","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5044608966","display_name":"X. L. Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xuanzhang Liu","raw_affiliation_strings":["Georgia Institute of Technology, Atlanta, GA, USA"],"raw_orcid":"https://orcid.org/0009-0003-6818-8820","affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology, Atlanta, GA, USA","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Jianglun Feng","orcid":"https://orcid.org/0009-0001-9513-5260"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianglun Feng","raw_affiliation_strings":["Alibaba Group, Hangzhou, Zhejiang, China"],"raw_orcid":"https://orcid.org/0009-0001-9513-5260","affiliations":[{"raw_affiliation_string":"Alibaba Group, Hangzhou, Zhejiang, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003576554","display_name":"Zhuoran Zhuang","orcid":"https://orcid.org/0009-0003-7028-6067"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhuoran Zhuang","raw_affiliation_strings":["Alibaba Group, Hangzhou, China"],"raw_orcid":"https://orcid.org/0009-0003-7028-6067","affiliations":[{"raw_affiliation_string":"Alibaba Group, Hangzhou, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Junzhe Zhao","orcid":"https://orcid.org/0009-0007-7248-5018"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junzhe Zhao","raw_affiliation_strings":["Alibaba Group, Hangzhou, China"],"raw_orcid":"https://orcid.org/0009-0007-7248-5018","affiliations":[{"raw_affiliation_string":"Alibaba Group, Hangzhou, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027171343","display_name":"Maofei Que","orcid":"https://orcid.org/0009-0004-1410-3825"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Maofei Que","raw_affiliation_strings":["Alibaba Group, Hangzhou, China"],"raw_orcid":"https://orcid.org/0009-0004-1410-3825","affiliations":[{"raw_affiliation_string":"Alibaba Group, Hangzhou, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Jieting Li","orcid":"https://orcid.org/0009-0006-3354-2975"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jieting Li","raw_affiliation_strings":["Alibaba Group, Hangzhou, China"],"raw_orcid":"https://orcid.org/0009-0006-3354-2975","affiliations":[{"raw_affiliation_string":"Alibaba Group, Hangzhou, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Dianlei Wang","orcid":"https://orcid.org/0009-0006-7862-4114"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dianlei Wang","raw_affiliation_strings":["Alibaba Group, Hangzhou, China"],"raw_orcid":"https://orcid.org/0009-0006-7862-4114","affiliations":[{"raw_affiliation_string":"Alibaba Group, Hangzhou, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Hao Tong","orcid":"https://orcid.org/0009-0008-9023-2732"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hao Tong","raw_affiliation_strings":["Alibaba Group, Hangzhou, China"],"raw_orcid":"https://orcid.org/0009-0008-9023-2732","affiliations":[{"raw_affiliation_string":"Alibaba Group, Hangzhou, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Ye Chen","orcid":"https://orcid.org/0009-0007-6024-6562"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ye Chen","raw_affiliation_strings":["Alibaba Group, Hangzhou, China"],"raw_orcid":"https://orcid.org/0009-0007-6024-6562","affiliations":[{"raw_affiliation_string":"Alibaba Group, Hangzhou, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"last","author":{"id":null,"display_name":"Pan Li","orcid":"https://orcid.org/0000-0003-4957-3064"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Pan Li","raw_affiliation_strings":["Georgia Institute of Technology, Atlanta, GA, USA"],"raw_orcid":"https://orcid.org/0000-0003-4957-3064","affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology, Atlanta, GA, USA","institution_ids":["https://openalex.org/I130701444"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"436","last_page":"446"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.45980000495910645,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.45980000495910645,"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":0.1673000007867813,"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/T10028","display_name":"Topic Modeling","score":0.05739999935030937,"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":0.902899980545044},{"id":"https://openalex.org/keywords/planner","display_name":"Planner","score":0.6518999934196472},{"id":"https://openalex.org/keywords/executor","display_name":"Executor","score":0.6294000148773193},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.6104999780654907},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.4611000120639801},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.3774000108242035},{"id":"https://openalex.org/keywords/simple","display_name":"Simple (philosophy)","score":0.35280001163482666}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.902899980545044},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8037999868392944},{"id":"https://openalex.org/C2776999362","wikidata":"https://www.wikidata.org/wiki/Q2349274","display_name":"Planner","level":2,"score":0.6518999934196472},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.646399974822998},{"id":"https://openalex.org/C180591056","wikidata":"https://www.wikidata.org/wiki/Q654437","display_name":"Executor","level":2,"score":0.6294000148773193},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6104999780654907},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.47870001196861267},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.4611000120639801},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.3774000108242035},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.35280001163482666},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.33180001378059387},{"id":"https://openalex.org/C74072328","wikidata":"https://www.wikidata.org/wiki/Q1142726","display_name":"Intelligent agent","level":2,"score":0.2980000078678131},{"id":"https://openalex.org/C199190896","wikidata":"https://www.wikidata.org/wiki/Q3509276","display_name":"Learning classifier system","level":3,"score":0.2973000109195709},{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.295199990272522},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.29179999232292175},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.2549000084400177},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.25130000710487366}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3773966.3777986","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3773966.3777986","pdf_url":null,"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 Nineteenth ACM International Conference on Web Search and Data Mining","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2512.12716","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2512.12716","pdf_url":"https://arxiv.org/pdf/2512.12716","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"}],"best_oa_location":{"id":"doi:10.1145/3773966.3777986","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3773966.3777986","pdf_url":null,"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 Nineteenth ACM International Conference on Web Search and Data Mining","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Large":[0],"Language":[1],"Model":[2],"(LLM)":[3],"agents":[4],"trained":[5],"with":[6],"reinforcement":[7,58,120],"learning":[8,59,121],"(RL)":[9],"show":[10],"great":[11],"promise":[12],"for":[13],"solving":[14],"complex,":[15],"multi-step":[16],"tasks.":[17],"However,":[18],"their":[19],"performance":[20,147,167],"is":[21,190],"often":[22],"crippled":[23],"by":[24],"''Context":[25],"Explosion'',":[26],"where":[27],"the":[28,35,178],"accumulation":[29],"of":[30,180],"long":[31],"text":[32],"outputs":[33],"overwhelms":[34],"model's":[36],"context":[37,186],"window":[38],"and":[39,96,157],"leads":[40],"to":[41,77,128],"reasoning":[42],"failures.":[43],"To":[44],"address":[45],"this,":[46],"we":[47],"introduce":[48],"CoDA,":[49],"a":[50,54,70,85,92,97,119,125],"Context-Decoupled":[51],"hierarchical":[52,182],"Agent,":[53],"simple":[55],"but":[56],"effective":[57],"framework":[60],"that":[61,75,88,100,123,143],"decouples":[62],"high-level":[63,86],"planning":[64],"from":[65],"low-level":[66,98],"execution.":[67],"It":[68],"employs":[69],"single,":[71],"shared":[72],"LLM":[73],"backbone":[74],"learns":[76],"operate":[78],"in":[79,104,162,184],"two":[80],"distinct,":[81],"contextually":[82],"isolated":[83,107],"roles:":[84],"Planner":[87],"decomposes":[89],"tasks":[90],"within":[91],"concise":[93],"strategic":[94],"context,":[95],"Executor":[99],"handles":[101],"tool":[102],"interactions":[103],"an":[105],"ephemeral,":[106],"workspace.":[108],"We":[109],"train":[110],"this":[111],"unified":[112],"agent":[113],"end-to-end":[114],"using":[115],"PECO":[116],"(Planner-Executor":[117],"Co-Optimization),":[118],"methodology":[122],"applies":[124],"trajectory-level":[126],"reward":[127],"jointly":[129],"optimize":[130],"both":[131],"roles,":[132],"fostering":[133],"seamless":[134],"collaboration":[135],"through":[136],"context-dependent":[137],"policy":[138],"updates.":[139],"Extensive":[140],"experiments":[141],"demonstrate":[142],"CoDA":[144],"achieves":[145],"significant":[146],"improvements":[148],"over":[149],"state-of-the-art":[150],"baselines":[151,171],"on":[152],"complex":[153],"multi-hop":[154],"question-answering":[155],"benchmarks,":[156],"it":[158],"exhibits":[159],"strong":[160],"robustness":[161],"long-context":[163],"scenarios,":[164],"maintaining":[165],"stable":[166],"while":[168],"all":[169],"other":[170],"suffer":[172],"severe":[173],"degradation,":[174],"thus":[175],"further":[176],"validating":[177],"effectiveness":[179],"our":[181],"design":[183],"mitigating":[185],"overload.":[187],"Our":[188],"code":[189],"available":[191],"at":[192],"https://github.com/liuxuanzhang718/CoDA.":[193]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2025-12-17T00:00:00"}