{"id":"https://openalex.org/W7138444981","doi":"https://doi.org/10.1609/aaai.v40i28.39570","title":"SHADOW: Dynamic-Aware Credit Assignment Against Long-Horizon Tasks","display_name":"SHADOW: Dynamic-Aware Credit Assignment Against Long-Horizon Tasks","publication_year":2026,"publication_date":"2026-03-14","ids":{"openalex":"https://openalex.org/W7138444981","doi":"https://doi.org/10.1609/aaai.v40i28.39570"},"language":"en","primary_location":{"id":"doi:10.1609/aaai.v40i28.39570","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i28.39570","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://doi.org/10.1609/aaai.v40i28.39570","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5129660602","display_name":"Yuze Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210123185","display_name":"Zhejiang Lab","ror":"https://ror.org/02m2h7991","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210123185"]},{"id":"https://openalex.org/I4210164862","display_name":"Artificial Intelligence in Medicine (Canada)","ror":"https://ror.org/05p590m36","country_code":"CA","type":"company","lineage":["https://openalex.org/I4210164862"]}],"countries":["CA","CN"],"is_corresponding":false,"raw_author_name":"Yuze Liu","raw_affiliation_strings":["Zhejiang University\nShanghai Artificial Intelligence Laboratory"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University\nShanghai Artificial Intelligence Laboratory","institution_ids":["https://openalex.org/I4210123185","https://openalex.org/I4210164862"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129656287","display_name":"Chaochao Lu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]},{"id":"https://openalex.org/I4391012619","display_name":"Shanghai Artificial Intelligence Laboratory","ror":"https://ror.org/03wkvpx79","country_code":null,"type":"facility","lineage":["https://openalex.org/I4391012619"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chaochao Lu","raw_affiliation_strings":["Shanghai Artificial Intelligence Laboratory"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Artificial Intelligence Laboratory","institution_ids":["https://openalex.org/I4210100255","https://openalex.org/I4391012619"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5129672825","display_name":"Chao Yang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]},{"id":"https://openalex.org/I4391012619","display_name":"Shanghai Artificial Intelligence Laboratory","ror":"https://ror.org/03wkvpx79","country_code":null,"type":"facility","lineage":["https://openalex.org/I4391012619"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chao Yang","raw_affiliation_strings":["Shanghai Artificial Intelligence Laboratory"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Artificial Intelligence Laboratory","institution_ids":["https://openalex.org/I4210100255","https://openalex.org/I4391012619"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"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":"40","issue":"28","first_page":"23935","last_page":"23944"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.249099999666214,"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":0.249099999666214,"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/T10028","display_name":"Topic Modeling","score":0.1826999932527542,"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.10509999841451645,"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/benchmark","display_name":"Benchmark (surveying)","score":0.6848000288009644},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.590399980545044},{"id":"https://openalex.org/keywords/estimator","display_name":"Estimator","score":0.5246999859809875},{"id":"https://openalex.org/keywords/trajectory","display_name":"Trajectory","score":0.5199000239372253},{"id":"https://openalex.org/keywords/transition","display_name":"Transition (genetics)","score":0.4205000102519989},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.4009000062942505},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.3993000090122223},{"id":"https://openalex.org/keywords/neglect","display_name":"Neglect","score":0.3955000042915344}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7116000056266785},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6848000288009644},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.590399980545044},{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.5246999859809875},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.5199000239372253},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4440000057220459},{"id":"https://openalex.org/C194232998","wikidata":"https://www.wikidata.org/wiki/Q1606712","display_name":"Transition (genetics)","level":3,"score":0.4205000102519989},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4009000062942505},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.3993000090122223},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3977999985218048},{"id":"https://openalex.org/C2776289891","wikidata":"https://www.wikidata.org/wiki/Q1931511","display_name":"Neglect","level":2,"score":0.3955000042915344},{"id":"https://openalex.org/C178350159","wikidata":"https://www.wikidata.org/wiki/Q162714","display_name":"Credit risk","level":2,"score":0.3025999963283539},{"id":"https://openalex.org/C96250715","wikidata":"https://www.wikidata.org/wiki/Q965330","display_name":"Estimation","level":2,"score":0.3012999892234802},{"id":"https://openalex.org/C89611455","wikidata":"https://www.wikidata.org/wiki/Q6804646","display_name":"Mechanism (biology)","level":2,"score":0.2964000105857849},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.2953000068664551},{"id":"https://openalex.org/C145912823","wikidata":"https://www.wikidata.org/wiki/Q113558","display_name":"Dynamics (music)","level":2,"score":0.2946999967098236},{"id":"https://openalex.org/C77405623","wikidata":"https://www.wikidata.org/wiki/Q598451","display_name":"System dynamics","level":2,"score":0.27149999141693115},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.26930001378059387},{"id":"https://openalex.org/C2778753846","wikidata":"https://www.wikidata.org/wiki/Q6554239","display_name":"Link (geometry)","level":2,"score":0.2687999904155731},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.2669999897480011},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.2648000121116638},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.259799987077713}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1609/aaai.v40i28.39570","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i28.39570","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},{"id":"pmh:oai:ojs.aaai.org:article/39570","is_oa":false,"landing_page_url":"https://ojs.aaai.org/index.php/AAAI/article/view/39570","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"2159-5399","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"doi:10.1609/aaai.v40i28.39570","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i28.39570","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Reinforcement":[0],"learning":[1],"(RL)":[2],"has":[3],"emerged":[4],"as":[5,34],"the":[6,130,145],"predominant":[7],"paradigm":[8],"for":[9,40,75],"training":[10],"large":[11],"language":[12],"model":[13,133],"(LLM)":[14],"agents":[15],"to":[16,54,113],"solve":[17],"complex,":[18],"multi-step":[19],"tasks":[20],"through":[21,119],"environmental":[22],"interaction.":[23],"A":[24],"fundamental":[25],"challenge":[26],"in":[27],"such":[28],"long-horizon":[29],"scenarios":[30],"is":[31],"credit":[32,58,77],"assignment,":[33],"delayed":[35],"rewards":[36],"provide":[37],"inadequate":[38],"signals":[39],"evaluating":[41],"individual":[42,116],"action":[43,94,117],"contributions.":[44],"Existing":[45],"methods":[46],"typically":[47],"neglect":[48],"trajectory":[49],"transition":[50,73,124],"dynamics,":[51],"which":[52],"leads":[53],"coarse-grained":[55],"or":[56],"biased":[57],"assignment.":[59,78],"To":[60],"address":[61],"these":[62],"limitations,":[63],"we":[64],"introduce":[65],"SHADOW,":[66],"a":[67,86,102,120,149],"novel":[68],"framework":[69,80],"that":[70,91,107,135],"systematically":[71],"incorporates":[72],"dynamics":[74],"improved":[76],"Our":[79],"makes":[81],"two":[82],"primary":[83],"contributions:":[84],"(i)":[85],"dynamics-aware":[87],"state":[88],"grouping":[89],"mechanism":[90],"mitigates":[92],"misleading":[93],"comparisons":[95],"between":[96],"dynamically":[97],"inconsistent":[98],"states,":[99],"and":[100,148],"(ii)":[101],"local":[103],"dynamic":[104],"advantage":[105],"estimator":[106],"leverages":[108],"Generalized":[109],"Advantage":[110],"Estimation":[111],"(GAE)":[112],"precisely":[114],"quantify":[115],"contributions":[118],"fine-grained":[121],"analysis":[122],"of":[123,142,152],"patterns.":[125],"Comprehensive":[126],"experiments":[127],"conducted":[128],"with":[129],"Qwen2.5-1.5/7B-Instruct":[131],"agent":[132],"demonstrate":[134],"our":[136],"method":[137],"achieves":[138],"success":[139],"rate":[140],"improvements":[141],"9.4%/7.6%":[143],"on":[144,155],"ALFworld":[146],"benchmark":[147],"performance":[150],"gain":[151],"over":[153],"5%":[154],"WebShop.":[156]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2026-03-18T00:00:00"}