{"id":"https://openalex.org/W4416775342","doi":"https://doi.org/10.52202/085713-0847","title":"AutoDiscovery: Open-ended Scientific Discovery via Bayesian Surprise","display_name":"AutoDiscovery: Open-ended Scientific Discovery via Bayesian Surprise","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4416775342","doi":"https://doi.org/10.52202/085713-0847"},"language":"en","primary_location":{"id":"doi:10.52202/085713-0847","doi":"https://doi.org/10.52202/085713-0847","is_oa":false,"landing_page_url":"https://doi.org/10.52202/085713-0847","pdf_url":null,"source":{"id":"https://openalex.org/S4363606243","display_name":"neural information processing systems","issn_l":"1049-5258","issn":["1049-5258"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","norway-2"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Advances in Neural Information Processing Systems 38","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2507.00310","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Dhruv Agarwal","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I24603500","display_name":"University of Massachusetts Amherst","ror":"https://ror.org/0072zz521","country_code":"US","type":"education","lineage":["https://openalex.org/I24603500"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dhruv Agarwal","raw_affiliation_strings":["UMass Amherst / Ai2"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"UMass Amherst / Ai2","institution_ids":["https://openalex.org/I24603500"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069912951","display_name":"Bodhisattwa Prasad Majumder","orcid":"https://orcid.org/0009-0000-2691-305X","observed_orcids":["https://orcid.org/0009-0000-2691-305X","https://orcid.org/0000-0002-7026-3100"]},"institutions":[{"id":"https://openalex.org/I4210156221","display_name":"Allen Institute for Artificial Intelligence","ror":"https://ror.org/05w520734","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I4210156221"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bodhisattwa Prasad Majumder","raw_affiliation_strings":["Allen Institute for AI (AI2)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Allen Institute for AI (AI2)","institution_ids":["https://openalex.org/I4210156221"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Reece Adamson","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210156221","display_name":"Allen Institute for Artificial Intelligence","ror":"https://ror.org/05w520734","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I4210156221"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Reece Adamson","raw_affiliation_strings":["Allen Institute for Artificial Intelligence"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Allen Institute for Artificial Intelligence","institution_ids":["https://openalex.org/I4210156221"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Megha Chakravorty","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I24603500","display_name":"University of Massachusetts Amherst","ror":"https://ror.org/0072zz521","country_code":"US","type":"education","lineage":["https://openalex.org/I24603500"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Megha Chakravorty","raw_affiliation_strings":["University of Massachusetts at Amherst"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Massachusetts at Amherst","institution_ids":["https://openalex.org/I24603500"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120435725","display_name":"Satvika Reddy Gavireddy","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I24603500","display_name":"University of Massachusetts Amherst","ror":"https://ror.org/0072zz521","country_code":"US","type":"education","lineage":["https://openalex.org/I24603500"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Satvika Reddy Gavireddy","raw_affiliation_strings":["University of Massachusetts at Amherst"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Massachusetts at Amherst","institution_ids":["https://openalex.org/I24603500"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017240523","display_name":"Aditya Parashar","orcid":"https://orcid.org/0009-0007-2592-2561","observed_orcids":["https://orcid.org/0009-0007-2592-2561"]},"institutions":[{"id":"https://openalex.org/I1305444813","display_name":"Capital One (United States)","ror":"https://ror.org/00svp7168","country_code":"US","type":"company","lineage":["https://openalex.org/I1305444813"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Aditya Parashar","raw_affiliation_strings":["Capital One"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Capital One","institution_ids":["https://openalex.org/I1305444813"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084474211","display_name":"Harshit Surana","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210156221","display_name":"Allen Institute for Artificial Intelligence","ror":"https://ror.org/05w520734","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I4210156221"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Harshit Surana","raw_affiliation_strings":["Allen Institute for Artificial Intelligence"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Allen Institute for Artificial Intelligence","institution_ids":["https://openalex.org/I4210156221"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087135401","display_name":"Bhavana Dalvi Mishra","orcid":"https://orcid.org/0000-0002-3813-8641","observed_orcids":["https://orcid.org/0000-0002-3813-8641"]},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bhavana Dalvi Mishra","raw_affiliation_strings":["Google Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Research","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5107835063","display_name":"Andrew McCallum","orcid":"https://orcid.org/0000-0003-2843-6992","observed_orcids":["https://orcid.org/0000-0003-2843-6992"]},"institutions":[{"id":"https://openalex.org/I24603500","display_name":"University of Massachusetts Amherst","ror":"https://ror.org/0072zz521","country_code":"US","type":"education","lineage":["https://openalex.org/I24603500"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Andrew McCallum","raw_affiliation_strings":["UMass Amherst"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"UMass Amherst","institution_ids":["https://openalex.org/I24603500"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077726785","display_name":"Ashish Sabharwal","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210156221","display_name":"Allen Institute for Artificial Intelligence","ror":"https://ror.org/05w520734","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I4210156221"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ashish Sabharwal","raw_affiliation_strings":["Ai2 (Allen Institute for AI)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ai2 (Allen Institute for AI)","institution_ids":["https://openalex.org/I4210156221"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5049837138","display_name":"Peter A. Clark","orcid":"https://orcid.org/0000-0003-1001-9226","observed_orcids":["https://orcid.org/0000-0003-1001-9226"]},"institutions":[{"id":"https://openalex.org/I4210156221","display_name":"Allen Institute for Artificial Intelligence","ror":"https://ror.org/05w520734","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I4210156221"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Peter Clark","raw_affiliation_strings":["Allen Institute for AI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Allen Institute for AI","institution_ids":["https://openalex.org/I4210156221"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.33051477,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"28504","last_page":"28542"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10538","display_name":"Data Mining Algorithms and Applications","score":0.18410000205039978,"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"}},"topics":[{"id":"https://openalex.org/T10538","display_name":"Data Mining Algorithms and Applications","score":0.18410000205039978,"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/T11948","display_name":"Machine Learning in Materials Science","score":0.1598999947309494,"subfield":{"id":"https://openalex.org/subfields/2505","display_name":"Materials Chemistry"},"field":{"id":"https://openalex.org/fields/25","display_name":"Materials Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T13904","display_name":"Artificial Intelligence Applications","score":0.07400000095367432,"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/autonomous-scientific-discovery","display_name":"autonomous scientific discovery","score":0.9649999737739563},{"id":"https://openalex.org/keywords/bayesian-surprise","display_name":"Bayesian surprise","score":0.9959999918937683},{"id":"https://openalex.org/keywords/large-language-models","display_name":"large language models","score":0.7609999775886536},{"id":"https://openalex.org/keywords/monte-carlo-tree-search","display_name":"Monte Carlo tree search","score":0.8830000162124634},{"id":"https://openalex.org/keywords/epistemic-change","display_name":"epistemic change","score":0.6769999861717224},{"id":"https://openalex.org/keywords/data-driven-discovery","display_name":"data-driven discovery","score":0.8190000057220459}],"concepts":[{"id":"https://openalex.org/C2984917352","wikidata":"https://www.wikidata.org/wiki/Q12772819","display_name":"Scientific discovery","level":2,"score":0.7538999915122986},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6547999978065491},{"id":"https://openalex.org/C127705205","wikidata":"https://www.wikidata.org/wiki/Q5748245","display_name":"Heuristics","level":2,"score":0.6432999968528748},{"id":"https://openalex.org/C2780343955","wikidata":"https://www.wikidata.org/wiki/Q333173","display_name":"Surprise","level":2,"score":0.5884000062942505},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5295000076293945},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4616999924182892},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.45750001072883606},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.4413999915122986},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.37929999828338623},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.37459999322891235},{"id":"https://openalex.org/C160234255","wikidata":"https://www.wikidata.org/wiki/Q812535","display_name":"Bayesian inference","level":3,"score":0.35359999537467957},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.3327000141143799},{"id":"https://openalex.org/C33724603","wikidata":"https://www.wikidata.org/wiki/Q812540","display_name":"Bayesian network","level":2,"score":0.3181000053882599},{"id":"https://openalex.org/C207685749","wikidata":"https://www.wikidata.org/wiki/Q2088941","display_name":"Domain knowledge","level":2,"score":0.31520000100135803},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.3009999990463257},{"id":"https://openalex.org/C108010975","wikidata":"https://www.wikidata.org/wiki/Q500094","display_name":"Pruning","level":2,"score":0.2879999876022339},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.28760001063346863},{"id":"https://openalex.org/C2781316041","wikidata":"https://www.wikidata.org/wiki/Q1230584","display_name":"Diversity (politics)","level":2,"score":0.2870999872684479},{"id":"https://openalex.org/C2781249084","wikidata":"https://www.wikidata.org/wiki/Q908656","display_name":"Preference","level":2,"score":0.26750001311302185},{"id":"https://openalex.org/C93959086","wikidata":"https://www.wikidata.org/wiki/Q6888345","display_name":"Model selection","level":2,"score":0.25859999656677246},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.2563000023365021}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.52202/085713-0847","doi":"https://doi.org/10.52202/085713-0847","is_oa":false,"landing_page_url":"https://doi.org/10.52202/085713-0847","pdf_url":null,"source":{"id":"https://openalex.org/S4363606243","display_name":"neural information processing systems","issn_l":"1049-5258","issn":["1049-5258"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","norway-2"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Advances in Neural Information Processing Systems 38","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2507.00310","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2507.00310","pdf_url":"https://arxiv.org/pdf/2507.00310","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.2507.00310","doi":"https://doi.org/10.48550/arxiv.2507.00310","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2507.00310","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:2507.00310","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2507.00310","pdf_url":"https://arxiv.org/pdf/2507.00310","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":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7221153834","https://openalex.org/W7166705739","https://openalex.org/W7167065561","https://openalex.org/W7166637639","https://openalex.org/W4417011637","https://openalex.org/W7165295667","https://openalex.org/W7220950862","https://openalex.org/W7162454801","https://openalex.org/W7161760552","https://openalex.org/W4402952666"],"abstract_inverted_index":{"The":[0,65],"promise":[1],"of":[2,29,148,176,222],"autonomous":[3],"scientific":[4,47,116],"discovery":[5,48,178],"(ASD)":[6],"hinges":[7],"not":[8],"only":[9],"on":[10,15,38,75],"answering":[11],"questions,":[12],"but":[13,84],"also":[14],"knowing":[16],"which":[17],"questions":[18,41],"to":[19,42,58,88,135,230],"ask.":[20],"Most":[21],"recent":[22],"works":[23],"in":[24,34,69,173],"ASD":[25,71,112,244],"explore":[26,145],"the":[27,55,85,91,97,124,128,146,167,174,213],"use":[28],"large":[30],"language":[31],"models":[32],"(LLMs)":[33],"goal-driven":[35],"settings,":[36],"relying":[37],"human-specified":[39],"research":[40],"guide":[43],"hypothesis":[44,94,134],"generation.":[45],"However,":[46],"may":[49],"be":[50],"accelerated":[51],"further":[52,218],"by":[53,61,205,212,225],"allowing":[54],"AI":[56],"system":[57,227],"drive":[59],"exploration":[60,117],"its":[62,136],"own":[63],"criteria.":[64],"few":[66],"existing":[67],"approaches":[68],"open-ended":[70,111,243],"select":[72],"hypotheses":[73],"based":[74],"diversity":[76],"heuristics":[77],"or":[78],"subjective":[79],"proxies":[80],"for":[81,110],"human":[82,216],"interestingness,":[83],"former":[86],"struggles":[87],"meaningfully":[89],"navigate":[90],"typically":[92],"vast":[93],"space,":[95],"and":[96,190],"latter":[98],"suffers":[99],"from":[100,127],"imprecise":[101],"definitions.":[102],"This":[103],"paper":[104],"presents":[105],"AutoDiscovery":[106,172,201],"--":[107],"a":[108,133,154,198],"method":[109,152],"that":[113,196,220],"instead":[114],"drives":[115],"using":[118,164],"Bayesian":[119],"surprise.":[120],"Here,":[121],"we":[122],"quantify":[123],"epistemic":[125],"shift":[126],"LLM's":[129],"prior":[130],"beliefs":[131,138],"about":[132],"posterior":[137],"after":[139],"gathering":[140],"experimental":[141],"results.":[142],"To":[143],"efficiently":[144],"space":[147],"nested":[149],"hypotheses,":[150],"our":[151,226],"employs":[153],"Monte":[155],"Carlo":[156],"tree":[157],"search":[158],"(MCTS)":[159],"strategy":[160],"with":[161],"progressive":[162],"widening":[163],"surprisal":[165],"as":[166,186,233],"reward":[168],"function.":[169],"We":[170],"evaluate":[171],"setting":[175],"data-driven":[177],"across":[179],"21":[180],"real-world":[181],"datasets":[182],"spanning":[183],"domains":[184],"such":[185],"biology,":[187],"economics,":[188],"finance,":[189],"behavioral":[191],"science.":[192],"Our":[193,215],"results":[194],"demonstrate":[195],"under":[197],"fixed":[199],"budget,":[200],"substantially":[202],"outperforms":[203],"competitors":[204],"producing":[206],"5-29%":[207],"more":[208],"discoveries":[209,223],"deemed":[210],"surprising":[211,229],"LLM.":[214],"evaluation":[217],"reveals":[219],"two-thirds":[221],"made":[224],"are":[228],"domain":[231],"experts":[232],"well,":[234],"suggesting":[235],"this":[236],"is":[237],"an":[238],"important":[239],"step":[240],"towards":[241],"building":[242],"systems.":[245]},"counts_by_year":[],"updated_date":"2026-10-06T10:28:23.643775","created_date":"2025-10-10T00:00:00"}