{"id":"https://openalex.org/W7225204544","doi":"https://doi.org/10.48550/arxiv.2611.02706","title":"Hindsight Credit Assignment over Trees for Agentic RL","display_name":"Hindsight Credit Assignment over Trees for Agentic RL","publication_year":2026,"publication_date":"2026-11-02","ids":{"openalex":"https://openalex.org/W7225204544","doi":"https://doi.org/10.48550/arxiv.2611.02706"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2611.02706","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2611.02706","pdf_url":"https://arxiv.org/pdf/2611.02706","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,"listed_in":[],"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"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2611.02706","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5160490042","display_name":"Penghong Zhao","orcid":null,"observed_orcids":[]},"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":"Zhao, Penghong","raw_affiliation_strings":["Alibaba Cloud Computing"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Cloud Computing","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5160415499","display_name":"Yihao Chen","orcid":null,"observed_orcids":[]},"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":"Chen, Yihao","raw_affiliation_strings":["Alibaba Cloud Computing"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Cloud Computing","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5160522353","display_name":"Maoheng Yuan","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuan, Maoheng","raw_affiliation_strings":["Fudan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fudan University","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5160450017","display_name":"Yunjian Zhang","orcid":null,"observed_orcids":[]},"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":"Zhang, Yunjian","raw_affiliation_strings":["Alibaba Cloud Computing"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Cloud Computing","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023291127","display_name":"Abudukelimu Wuerkaixi","orcid":"https://orcid.org/0000-0002-5609-606X","observed_orcids":["https://orcid.org/0000-0002-5609-606X"]},"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":"Wuerkaixi, Abudukelimu","raw_affiliation_strings":["Alibaba Cloud Computing"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Cloud Computing","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5160526772","display_name":"Haoran Xu","orcid":null,"observed_orcids":[]},"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":"Xu, Haoran","raw_affiliation_strings":["Alibaba Cloud Computing"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Cloud Computing","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109424642","display_name":"Man Lv","orcid":null,"observed_orcids":[]},"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":"Lv, Man","raw_affiliation_strings":["Alibaba Cloud Computing"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Cloud Computing","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5160492511","display_name":"Yaolong Wang","orcid":null,"observed_orcids":[]},"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":"Wang, Yaolong","raw_affiliation_strings":["Alibaba Cloud Computing"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Cloud Computing","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5160532383","display_name":"Zhijie Sun","orcid":null,"observed_orcids":[]},"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":"Sun, Zhijie","raw_affiliation_strings":["Alibaba Cloud Computing"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Cloud Computing","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5160451461","display_name":"Guohua Liu","orcid":null,"observed_orcids":[]},"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":"Liu, Guohua","raw_affiliation_strings":["Alibaba Cloud Computing"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Cloud Computing","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5160440244","display_name":"Yuewei Zhang","orcid":null,"observed_orcids":[]},"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":"Zhang, Yuewei","raw_affiliation_strings":["Alibaba Cloud Computing"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Cloud Computing","institution_ids":["https://openalex.org/I45928872"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9976000189781189,"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":0.9976000189781189,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.00019999999494757503,"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":0.00019999999494757503,"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/llm-based-agents","display_name":"LLM agents","score":0.7990000247955322},{"id":"https://openalex.org/keywords/long-horizon-reinforcement-learning","display_name":"long-horizon reinforcement learning","score":0.8830000162124634},{"id":"https://openalex.org/keywords/sparse-rewards","display_name":"sparse rewards","score":0.8600000143051147}],"concepts":[{"id":"https://openalex.org/C10347200","wikidata":"https://www.wikidata.org/wiki/Q1960297","display_name":"Hindsight bias","level":2,"score":0.9901000261306763},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7728999853134155},{"id":"https://openalex.org/C148220186","wikidata":"https://www.wikidata.org/wiki/Q7111912","display_name":"Outcome (game theory)","level":2,"score":0.6140999794006348},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5083000063896179},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.5008000135421753},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.49639999866485596},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.492000013589859},{"id":"https://openalex.org/C2779436431","wikidata":"https://www.wikidata.org/wiki/Q30672407","display_name":"Policy learning","level":2,"score":0.45669999718666077},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.4228000044822693},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.39410001039505005},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3882000148296356},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.35580000281333923},{"id":"https://openalex.org/C84525736","wikidata":"https://www.wikidata.org/wiki/Q831366","display_name":"Decision tree","level":2,"score":0.350600004196167},{"id":"https://openalex.org/C42475967","wikidata":"https://www.wikidata.org/wiki/Q194292","display_name":"Operations research","level":1,"score":0.2939000129699707},{"id":"https://openalex.org/C2777503682","wikidata":"https://www.wikidata.org/wiki/Q5418327","display_name":"Evidence-based policy","level":3,"score":0.28690001368522644},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.27709999680519104},{"id":"https://openalex.org/C175444787","wikidata":"https://www.wikidata.org/wiki/Q39072","display_name":"Microeconomics","level":1,"score":0.27469998598098755},{"id":"https://openalex.org/C2778445095","wikidata":"https://www.wikidata.org/wiki/Q18354077","display_name":"Sample complexity","level":2,"score":0.27239999175071716},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.26969999074935913},{"id":"https://openalex.org/C79416737","wikidata":"https://www.wikidata.org/wiki/Q2305519","display_name":"Social learning","level":2,"score":0.267300009727478},{"id":"https://openalex.org/C62611344","wikidata":"https://www.wikidata.org/wiki/Q1062658","display_name":"Node (physics)","level":2,"score":0.26600000262260437},{"id":"https://openalex.org/C77967617","wikidata":"https://www.wikidata.org/wiki/Q4677561","display_name":"Active learning (machine learning)","level":2,"score":0.2632000148296356},{"id":"https://openalex.org/C155108698","wikidata":"https://www.wikidata.org/wiki/Q1231081","display_name":"Randomized experiment","level":2,"score":0.2540999948978424}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2611.02706","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2611.02706","pdf_url":"https://arxiv.org/pdf/2611.02706","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,"listed_in":[],"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.2611.02706","doi":"https://doi.org/10.48550/arxiv.2611.02706","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2611.02706","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,"listed_in":[],"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":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2611.02706","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2611.02706","pdf_url":"https://arxiv.org/pdf/2611.02706","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,"listed_in":[],"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"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7225204544.pdf","grobid_xml":"https://content.openalex.org/works/W7225204544.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7083493645","https://openalex.org/W7221537839","https://openalex.org/W7134953399","https://openalex.org/W7169806788","https://openalex.org/W7214775583","https://openalex.org/W7222982781","https://openalex.org/W7221812116","https://openalex.org/W7168511125","https://openalex.org/W7212730484","https://openalex.org/W7202134906"],"abstract_inverted_index":{"Reinforcement":[0],"learning":[1,51,60],"for":[2,14,40],"long-horizon":[3,165],"LLM":[4],"agents":[5],"faces":[6],"a":[7,48,83,87,94],"fundamental":[8],"dilemma:":[9],"successful":[10,88],"experiences":[11,23],"are":[12],"essential":[13],"policy":[15,19,110],"improvement,":[16],"yet":[17],"limited":[18],"capabilities":[20],"make":[21],"such":[22],"difficult":[24],"to":[25,164],"discover.":[26],"Sparse":[27],"outcome":[28,127],"rewards":[29],"compound":[30],"this":[31,43],"challenge,":[32],"leaving":[33],"sampled":[34],"trajectories":[35],"with":[36,135],"little":[37],"relative":[38,119],"feedback":[39,134],"learning.":[41,167],"In":[42],"paper,":[44],"we":[45],"propose":[46],"TriGRPO,":[47],"tree-based":[49],"reinforcement":[50],"framework":[52],"that":[53,97],"turns":[54],"scarce":[55],"successes":[56],"into":[57],"exploration":[58,102],"and":[59,67,103,129,149],"signals":[61],"through":[62,75],"hindsight":[63,157],"credit":[64,124,158],"assignment":[65,159],"within":[66],"across":[68,152],"rollout":[69,73,92,150],"trees.":[70],"TriGRPO":[71],"constructs":[72],"trees":[74],"hindsight-guided":[76],"branching:":[77],"when":[78],"an":[79,161],"ongoing":[80],"trajectory":[81],"reaches":[82],"matched":[84],"decision":[85],"state,":[86],"action":[89],"discovered":[90],"during":[91],"initiates":[93],"sibling":[95],"branch":[96],"continues":[98],"autonomously,":[99],"enabling":[100],"further":[101],"parent-sibling":[104,126],"comparisons.":[105],"Three":[106],"complementary":[107],"groups":[108,116,122,131],"organize":[109],"optimization":[111],"over":[112],"these":[113],"trees:":[114],"root":[115],"capture":[117],"within-prompt":[118],"returns,":[120],"node":[121],"assign":[123],"from":[125],"differences,":[128],"cross":[130],"supplement":[132],"sparse":[133],"historical":[136],"performance":[137,148],"on":[138],"related":[139],"tasks.":[140],"Experimental":[141],"results":[142],"demonstrate":[143],"consistent":[144],"gains":[145],"in":[146],"task":[147],"efficiency":[151],"model":[153],"scales,":[154],"highlighting":[155],"structured":[156],"as":[160],"effective":[162],"approach":[163],"agent":[166]},"counts_by_year":[],"updated_date":"2026-11-06T12:05:46.655746","created_date":"2026-11-04T00:00:00"}
