{"id":"https://openalex.org/W7207664422","doi":"https://doi.org/10.48550/arxiv.2609.02242","title":"Propose to Learn, Learn to Propose: Evaluability-Aware Assistance under Bounded Rationality","display_name":"Propose to Learn, Learn to Propose: Evaluability-Aware Assistance under Bounded Rationality","publication_year":2026,"publication_date":"2026-09-02","ids":{"openalex":"https://openalex.org/W7207664422","doi":"https://doi.org/10.48550/arxiv.2609.02242"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2609.02242","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.02242","pdf_url":"https://arxiv.org/pdf/2609.02242","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":"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/2609.02242","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5149720765","display_name":"Yifan Zhu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I9927081","display_name":"Aalto University","ror":"https://ror.org/020hwjq30","country_code":"FI","type":"education","lineage":["https://openalex.org/I9927081"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Zhu, Yifan","raw_affiliation_strings":["Department of Computer Science , Aalto University , Finland","ELLIS Institute Finland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science , Aalto University , Finland","institution_ids":["https://openalex.org/I9927081"]},{"raw_affiliation_string":"ELLIS Institute Finland","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077099438","display_name":"Sammie Katt","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I9927081","display_name":"Aalto University","ror":"https://ror.org/020hwjq30","country_code":"FI","type":"education","lineage":["https://openalex.org/I9927081"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Katt, Sammie","raw_affiliation_strings":["Department of Computer Science , Aalto University , Finland","ELLIS Institute Finland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science , Aalto University , Finland","institution_ids":["https://openalex.org/I9927081"]},{"raw_affiliation_string":"ELLIS Institute Finland","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5018305257","display_name":"Samuel Kaski A","orcid":"https://orcid.org/0000-0003-1925-9154","observed_orcids":["https://orcid.org/0000-0003-1925-9154"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kaski, Samuel","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"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/T10906","display_name":"AI-based Problem Solving and Planning","score":0.8213000297546387,"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/T10906","display_name":"AI-based Problem Solving and Planning","score":0.8213000297546387,"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/T10203","display_name":"Recommender Systems and Techniques","score":0.052799999713897705,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T10286","display_name":"Information Retrieval and Search Behavior","score":0.015200000256299973,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/bounded-rationality","display_name":"bounded rationality","score":0.9679999947547913},{"id":"https://openalex.org/keywords/ai-assistants","display_name":"AI assistants","score":0.7900000214576721},{"id":"https://openalex.org/keywords/user-evaluation","display_name":"user evaluation","score":0.40400001406669617},{"id":"https://openalex.org/keywords/prose","display_name":"prose","score":0.609000027179718},{"id":"https://openalex.org/keywords/evaluation-costs","display_name":"evaluation costs","score":0.38100001215934753}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5978999733924866},{"id":"https://openalex.org/C94822996","wikidata":"https://www.wikidata.org/wiki/Q1777902","display_name":"Satisficing","level":2,"score":0.5964999794960022},{"id":"https://openalex.org/C58694771","wikidata":"https://www.wikidata.org/wiki/Q814385","display_name":"Bounded rationality","level":2,"score":0.5943999886512756},{"id":"https://openalex.org/C2776999362","wikidata":"https://www.wikidata.org/wiki/Q2349274","display_name":"Planner","level":2,"score":0.5940999984741211},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5601999759674072},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.4569000005722046},{"id":"https://openalex.org/C2781249084","wikidata":"https://www.wikidata.org/wiki/Q908656","display_name":"Preference","level":2,"score":0.44999998807907104},{"id":"https://openalex.org/C34388435","wikidata":"https://www.wikidata.org/wiki/Q2267362","display_name":"Bounded function","level":2,"score":0.44350001215934753},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.4334999918937683},{"id":"https://openalex.org/C2777868144","wikidata":"https://www.wikidata.org/wiki/Q7239817","display_name":"Preference elicitation","level":3,"score":0.3903000056743622},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38749998807907104},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.37459999322891235},{"id":"https://openalex.org/C33676613","wikidata":"https://www.wikidata.org/wiki/Q13415176","display_name":"Dimension (graph theory)","level":2,"score":0.37310001254081726},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3578999936580658},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.3409999907016754},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.30250000953674316},{"id":"https://openalex.org/C201717286","wikidata":"https://www.wikidata.org/wiki/Q938185","display_name":"Rationality","level":2,"score":0.29109999537467957},{"id":"https://openalex.org/C539667460","wikidata":"https://www.wikidata.org/wiki/Q2414942","display_name":"Management science","level":1,"score":0.28130000829696655},{"id":"https://openalex.org/C17098449","wikidata":"https://www.wikidata.org/wiki/Q176814","display_name":"Partially observable Markov decision process","level":4,"score":0.26080000400543213}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2609.02242","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.02242","pdf_url":"https://arxiv.org/pdf/2609.02242","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2609.02242","doi":"https://doi.org/10.48550/arxiv.2609.02242","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2609.02242","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:2609.02242","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.02242","pdf_url":"https://arxiv.org/pdf/2609.02242","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G448529986","display_name":null,"funder_award_id":"EP/W002973/1","funder_id":"https://openalex.org/F4320314731","funder_display_name":"UK Research and Innovation"}],"funders":[{"id":"https://openalex.org/F4320314731","display_name":"UK Research and Innovation","ror":"https://ror.org/001aqnf71"},{"id":"https://openalex.org/F4320322725","display_name":"China Scholarship Council","ror":"https://ror.org/04atp4p48"},{"id":"https://openalex.org/F4320332050","display_name":"Finnish Center for Artificial Intelligence","ror":"https://ror.org/0321d1h15"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7207664422.pdf","grobid_xml":"https://content.openalex.org/works/W7207664422.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7162249665","https://openalex.org/W4281934051","https://openalex.org/W2790907256","https://openalex.org/W4407012960","https://openalex.org/W7124295378","https://openalex.org/W7214987721","https://openalex.org/W2798789011","https://openalex.org/W4283775315","https://openalex.org/W1995231402","https://openalex.org/W7140293356"],"abstract_inverted_index":{"AI":[0,199],"assistants":[1],"often":[2,26],"collaborate":[3],"by":[4,149],"proposing":[5],"candidate":[6],"edits,":[7],"plans,":[8],"or":[9,23],"designs":[10],"that":[11,28,117,131,146,178,184],"users":[12],"evaluate":[13,33],"before":[14],"adoption.":[15],"Existing":[16],"assistance":[17,85],"methods":[18,186],"focus":[19],"on":[20],"proposal":[21,48],"quality":[22,204],"user-goal":[24],"inference,":[25],"assuming":[27],"the":[29,68,110,171],"user":[30,192],"can":[31,37],"reliably":[32],"any":[34],"proposal,":[35],"which":[36,98,127],"fail":[38],"in":[39,97],"practice":[40],"because":[41],"of":[42,113,198],"bounded":[43],"rationality.":[44],"We":[45,76,137],"study":[46],"evaluability-aware":[47],"planning,":[49],"where":[50,67],"proposals":[51,120,148,183],"serve":[52],"both":[53],"as":[54,58,80,194],"task":[55],"interventions":[56],"and":[57,64,87,121,152,164,173,205],"probes":[59,123],"for":[60],"learning":[61],"latent":[62],"preferences":[63],"evaluation":[65,168],"constraints,":[66],"resulting":[69],"belief":[70],"updates":[71],"then":[72],"guide":[73],"later":[74],"proposals.":[75],"formalise":[77],"this":[78,114],"setting":[79],"ProSE,":[81],"a":[82,91,105,142,174,195],"hidden-parameter":[83],"sequential":[84],"problem,":[86],"instantiate":[88],"it":[89],"with":[90,140],"KL-regularised":[92],"bounded-rational":[93],"binary":[94],"response":[95],"model":[96],"acceptance":[99,134],"trades":[100],"off":[101],"value":[102],"gain":[103],"against":[104],"distance-dependent":[106],"evaluability":[107,193],"penalty.":[108],"Analysing":[109],"planning":[111],"consequence":[112],"likelihood":[115],"reveals":[116],"likely":[118],"accepted":[119],"informative":[122,182],"need":[124],"not":[125],"coincide,":[126],"explains":[128],"why":[129],"planners":[130],"only":[132],"pursue":[133],"systematically":[135],"underperform.":[136],"operationalise":[138],"ProSE":[139],"\\textsc{ProSE-Plan},":[141],"depth-2":[143],"Bayes-adaptive":[144],"planner":[145],"scores":[147],"possible":[150],"responses":[151],"response-induced":[153],"posterior":[154],"beliefs.":[155],"In":[156],"controlled":[157],"graph":[158],"simulations,":[159],"\\textsc{ProSE-Plan}":[160],"improves":[161],"over":[162],"evaluability-unaware":[163],"myopic":[165],"baselines":[166],"when":[167],"cost":[169],"is":[170],"bottleneck,":[172],"probe-commit":[175],"ablation":[176],"confirms":[177],"our":[179],"approach":[180],"selects":[181],"simpler":[185],"miss.":[187],"Our":[188],"results":[189],"thus":[190],"identify":[191],"planning-relevant":[196],"dimension":[197],"assistance,":[200],"complementary":[201],"to":[202],"generation":[203],"preference":[206],"inference.":[207]},"counts_by_year":[],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2026-09-04T00:00:00"}