{"id":"https://openalex.org/W7220945110","doi":"https://doi.org/10.48550/arxiv.2610.08077","title":"Self-Retrospection Distillation: Turning Post-hoc Experiences into Prior Foresight","display_name":"Self-Retrospection Distillation: Turning Post-hoc Experiences into Prior Foresight","publication_year":2026,"publication_date":"2026-10-06","ids":{"openalex":"https://openalex.org/W7220945110","doi":"https://doi.org/10.48550/arxiv.2610.08077"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2610.08077","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.08077","pdf_url":"https://arxiv.org/pdf/2610.08077","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","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2610.08077","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5157923789","display_name":"Haoxiang Zhang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I36258959","display_name":"University of California San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]},{"id":"https://openalex.org/I4210155268","display_name":"Salesforce (United States)","ror":"https://ror.org/057315g56","country_code":"US","type":"company","lineage":["https://openalex.org/I4210155268"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhang, Haoxiang","raw_affiliation_strings":["Salesforce AI Research","UC San Diego"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Salesforce AI Research","institution_ids":["https://openalex.org/I4210155268"]},{"raw_affiliation_string":"UC San Diego","institution_ids":["https://openalex.org/I36258959"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134135095","display_name":"Qinglin Chen","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210155268","display_name":"Salesforce (United States)","ror":"https://ror.org/057315g56","country_code":"US","type":"company","lineage":["https://openalex.org/I4210155268"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chen, Qinglin","raw_affiliation_strings":["Salesforce AI Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Salesforce AI Research","institution_ids":["https://openalex.org/I4210155268"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101850869","display_name":"Hiroaki Hayashi","orcid":"https://orcid.org/0000-0002-6875-7443","observed_orcids":["https://orcid.org/0000-0002-6875-7443"]},"institutions":[{"id":"https://openalex.org/I4210155268","display_name":"Salesforce (United States)","ror":"https://ror.org/057315g56","country_code":"US","type":"company","lineage":["https://openalex.org/I4210155268"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hayashi, Hiroaki","raw_affiliation_strings":["Salesforce AI Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Salesforce AI Research","institution_ids":["https://openalex.org/I4210155268"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5146841920","display_name":"Zhuofeng Li","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I91045830","display_name":"Texas A&M University","ror":"https://ror.org/01f5ytq51","country_code":"US","type":"education","lineage":["https://openalex.org/I91045830"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Li, Zhuofeng","raw_affiliation_strings":["Texas A&M University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Texas A&M University","institution_ids":["https://openalex.org/I91045830"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133269372","display_name":"Siming Zhang","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Siming","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5157987999","display_name":"Jiaxin Zhang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210155268","display_name":"Salesforce (United States)","ror":"https://ror.org/057315g56","country_code":"US","type":"company","lineage":["https://openalex.org/I4210155268"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhang, Jiaxin","raw_affiliation_strings":["Salesforce AI Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Salesforce AI Research","institution_ids":["https://openalex.org/I4210155268"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5157919930","display_name":"Jixuan Chen","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I36258959","display_name":"University of California San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]},{"id":"https://openalex.org/I4210155268","display_name":"Salesforce (United States)","ror":"https://ror.org/057315g56","country_code":"US","type":"company","lineage":["https://openalex.org/I4210155268"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chen, Jixuan","raw_affiliation_strings":["Salesforce AI Research","UC San Diego"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Salesforce AI Research","institution_ids":["https://openalex.org/I4210155268"]},{"raw_affiliation_string":"UC San Diego","institution_ids":["https://openalex.org/I36258959"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125554383","display_name":"Fang Wu","orcid":"https://orcid.org/0000-0001-7240-3915","observed_orcids":["https://orcid.org/0000-0001-7240-3915"]},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wu, Fang","raw_affiliation_strings":["Stanford University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stanford University","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5157929801","display_name":"Pan Lu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lu, Pan","raw_affiliation_strings":["Stanford University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stanford University","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042646536","display_name":"Silvio Savarese","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210155268","display_name":"Salesforce (United States)","ror":"https://ror.org/057315g56","country_code":"US","type":"company","lineage":["https://openalex.org/I4210155268"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Savarese, Silvio","raw_affiliation_strings":["Salesforce AI Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Salesforce AI Research","institution_ids":["https://openalex.org/I4210155268"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021827617","display_name":"Julian McAuley","orcid":"https://orcid.org/0000-0003-0955-7588","observed_orcids":["https://orcid.org/0000-0003-0955-7588"]},"institutions":[{"id":"https://openalex.org/I36258959","display_name":"University of California San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"McAuley, Julian","raw_affiliation_strings":["UC San Diego"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"UC San Diego","institution_ids":["https://openalex.org/I36258959"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5066791810","display_name":"Chien-Sheng Wu","orcid":"https://orcid.org/0000-0002-5598-5324","observed_orcids":["https://orcid.org/0000-0002-5598-5324"]},"institutions":[{"id":"https://openalex.org/I4210155268","display_name":"Salesforce (United States)","ror":"https://ror.org/057315g56","country_code":"US","type":"company","lineage":["https://openalex.org/I4210155268"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wu, Chien-Sheng","raw_affiliation_strings":["Salesforce AI Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Salesforce AI Research","institution_ids":["https://openalex.org/I4210155268"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":2,"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":0.9926999807357788,"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":0.9926999807357788,"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/T10906","display_name":"AI-based Problem Solving and Planning","score":0.003700000001117587,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.00039999998989515007,"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-with-verifiable-rewards","display_name":"reinforcement learning with verifiable rewards","score":0.8339999914169312},{"id":"https://openalex.org/keywords/self-distillation","display_name":"self-distillation","score":0.6119999885559082},{"id":"https://openalex.org/keywords/tool-integrated-reasoning","display_name":"tool-integrated reasoning","score":0.9599999785423279}],"concepts":[{"id":"https://openalex.org/C10347200","wikidata":"https://www.wikidata.org/wiki/Q1960297","display_name":"Hindsight bias","level":2,"score":0.953000009059906},{"id":"https://openalex.org/C64848388","wikidata":"https://www.wikidata.org/wiki/Q188867","display_name":"Futures studies","level":2,"score":0.807200014591217},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5386999845504761},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5242999792098999},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.5166000127792358},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.45980000495910645},{"id":"https://openalex.org/C148220186","wikidata":"https://www.wikidata.org/wiki/Q7111912","display_name":"Outcome (game theory)","level":2,"score":0.45159998536109924},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4397999942302704},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.43479999899864197},{"id":"https://openalex.org/C90329073","wikidata":"https://www.wikidata.org/wiki/Q914232","display_name":"Ask price","level":2,"score":0.42399999499320984},{"id":"https://openalex.org/C2779795794","wikidata":"https://www.wikidata.org/wiki/Q7315343","display_name":"Reset (finance)","level":2,"score":0.42160001397132874},{"id":"https://openalex.org/C2776650193","wikidata":"https://www.wikidata.org/wiki/Q264661","display_name":"Obstacle","level":2,"score":0.399399995803833},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3978999853134155},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.37929999828338623},{"id":"https://openalex.org/C2776946740","wikidata":"https://www.wikidata.org/wiki/Q358652","display_name":"Deliberation","level":3,"score":0.3605000078678131},{"id":"https://openalex.org/C187029079","wikidata":"https://www.wikidata.org/wiki/Q958679","display_name":"Cognitive reframing","level":2,"score":0.358599990606308},{"id":"https://openalex.org/C155108698","wikidata":"https://www.wikidata.org/wiki/Q1231081","display_name":"Randomized experiment","level":2,"score":0.3467999994754791},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.33739998936653137},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.33739998936653137},{"id":"https://openalex.org/C2776502983","wikidata":"https://www.wikidata.org/wiki/Q690182","display_name":"Contrast (vision)","level":2,"score":0.3370000123977661},{"id":"https://openalex.org/C2779458634","wikidata":"https://www.wikidata.org/wiki/Q24963715","display_name":"Debiasing","level":2,"score":0.31949999928474426},{"id":"https://openalex.org/C176777502","wikidata":"https://www.wikidata.org/wiki/Q4774623","display_name":"Anticipation (artificial intelligence)","level":2,"score":0.3052999973297119},{"id":"https://openalex.org/C102483320","wikidata":"https://www.wikidata.org/wiki/Q1143725","display_name":"Observational learning","level":3,"score":0.2849999964237213},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.2759999930858612},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.2734000086784363},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.27160000801086426},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.27000001072883606},{"id":"https://openalex.org/C56739046","wikidata":"https://www.wikidata.org/wiki/Q192060","display_name":"Knowledge management","level":1,"score":0.2615000009536743},{"id":"https://openalex.org/C98184364","wikidata":"https://www.wikidata.org/wiki/Q1780131","display_name":"Argument (complex analysis)","level":2,"score":0.2572999894618988},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.2515999972820282}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2610.08077","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.08077","pdf_url":"https://arxiv.org/pdf/2610.08077","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.2610.08077","doi":"https://doi.org/10.48550/arxiv.2610.08077","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2610.08077","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2610.08077","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.08077","pdf_url":"https://arxiv.org/pdf/2610.08077","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":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7220945110.pdf","grobid_xml":"https://content.openalex.org/works/W7220945110.grobid-xml"},"referenced_works_count":32,"referenced_works":["https://openalex.org/W1491843047","https://openalex.org/W2100677568","https://openalex.org/W2119717200","https://openalex.org/W2736601468","https://openalex.org/W2795843265","https://openalex.org/W2989847975","https://openalex.org/W3126325318","https://openalex.org/W4389422760","https://openalex.org/W4391631327","https://openalex.org/W4416176141","https://openalex.org/W4417422257","https://openalex.org/W4417538327","https://openalex.org/W7103139038","https://openalex.org/W7125406082","https://openalex.org/W7125861034","https://openalex.org/W7126034091","https://openalex.org/W7128545450","https://openalex.org/W7133300551","https://openalex.org/W7140517510","https://openalex.org/W7150828934","https://openalex.org/W7154299763","https://openalex.org/W7154507714","https://openalex.org/W7155089822","https://openalex.org/W7161258139","https://openalex.org/W7163174940","https://openalex.org/W7166590586","https://openalex.org/W7166714766","https://openalex.org/W7167266087","https://openalex.org/W7167642481","https://openalex.org/W7169575253","https://openalex.org/W7172290630","https://openalex.org/W7202181542"],"related_works":["https://openalex.org/W7220446565","https://openalex.org/W7155380143","https://openalex.org/W7222340647","https://openalex.org/W7214951477","https://openalex.org/W7202134906","https://openalex.org/W7161705850","https://openalex.org/W7164382286","https://openalex.org/W7170063487","https://openalex.org/W7164801679","https://openalex.org/W7171952724"],"abstract_inverted_index":{"Reinforcement":[0],"learning":[1,10,182],"with":[2,87,150],"verifiable":[3],"rewards":[4,16],"(RLVR)":[5],"turns":[6],"agent":[7,49,60,220],"experience":[8,75,221],"into":[9,113],"signals":[11],"primarily":[12],"through":[13],"scalar":[14],"outcome":[15],"after":[17],"interaction.":[18,239],"For":[19],"group-relative":[20],"objectives,":[21],"however,":[22],"this":[23,110],"signal":[24,183],"vanishes":[25],"when":[26,162,167],"all":[27],"rollouts":[28],"receive":[29],"the":[30,43,48,81,117,188,197,211],"same":[31,118,212],"reward,":[32],"even":[33],"though":[34],"their":[35],"trajectories":[36],"may":[37],"reveal":[38],"useful":[39,101,223],"information":[40],"about":[41],"what":[42,61],"task":[44],"requires":[45],"and":[46,84,102,127,140,147],"how":[47],"fails.":[50],"We":[51,68],"ask":[52],"a":[53,92,124],"complementary":[54],"question:":[55],"can":[56,179,242],"hindsight":[57,112],"teach":[58],"an":[59],"it":[62,86],"could":[63],"have":[64,99],"anticipated":[65],"before":[66,237],"acting?":[67],"introduce":[69],"prospective":[70],"learning,":[71],"which":[72],"uses":[73],"post-hoc":[74,219],"to":[76,154],"supervise":[77],"foresight":[78,115],"predictions":[79],"from":[80,184],"pre-interaction":[82],"view,":[83],"instantiate":[85],"Self-Retrospection":[88],"Distillation":[89],"(SRD).":[90],"Intuitively,":[91],"completed":[93],"trajectory":[94],"reveals":[95],"knowledge":[96],"that":[97,104,218],"would":[98],"been":[100],"pitfalls":[103],"should":[105],"be":[106,130,243],"avoided;":[107],"SRD":[108,144,178,207],"distills":[109],"privileged":[111],"trajectory-blind":[114],"of":[116,152,169,193],"policy.":[119],"Foresight":[120],"serves":[121],"only":[122,225],"as":[123],"training":[125,199],"target":[126],"need":[128],"not":[129,224],"explicitly":[131],"generated":[132],"at":[133,202,245],"inference":[134],"time.":[135],"Across":[136],"10":[137],"tool-integrated":[138],"reasoning":[139],"long-horizon":[141],"agentic":[142],"tasks,":[143],"complements":[145],"RLVR":[146,198],"self-distillation":[148],"baselines":[149],"gains":[151],"up":[153,201],"24.2":[155],"pp.":[156],"Its":[157],"advantage":[158],"is":[159,165,222],"especially":[160],"pronounced":[161],"reward":[163],"contrast":[164],"scarce:":[166],"37--98%":[168],"rollout":[170,213],"groups":[171,194],"are":[172,195],"reward-uniform":[173],"across":[174],"model":[175],"scales,":[176],"yet":[177],"still":[180],"exploit":[181],"sampled":[185],"trajectories.":[186],"In":[187],"2B":[189],"setting,":[190],"where":[191],"98%":[192],"all-failure,":[196],"ends":[200],"0.0%":[203],"success,":[204],"while":[205],"adding":[206],"reaches":[208],"60.6%":[209],"under":[210],"budget.":[214],"Our":[215],"results":[216],"suggest":[217],"for":[226,233],"evaluating":[227],"or":[228],"improving":[229],"behavior,":[230],"but":[231],"also":[232],"shaping":[234],"predictive":[235],"representations":[236],"available":[238],"Training":[240],"code":[241],"found":[244],"https://github.com/SalesforceAIResearch/SRD.":[246]},"counts_by_year":[{"year":2026,"cited_by_count":2}],"updated_date":"2026-11-08T12:12:28.789561","created_date":"2026-10-09T00:00:00"}