{"id":"https://openalex.org/W7155176741","doi":"https://doi.org/10.48550/arxiv.2604.19341","title":"Evaluation-driven Scaling for Scientific Discovery","display_name":"Evaluation-driven Scaling for Scientific Discovery","publication_year":2026,"publication_date":"2026-04-21","ids":{"openalex":"https://openalex.org/W7155176741","doi":"https://doi.org/10.48550/arxiv.2604.19341"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2604.19341","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.19341","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2604.19341","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5134301441","display_name":"Haotian Ye","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ye, Haotian","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134271844","display_name":"Haowei Lin","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lin, Haowei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134328448","display_name":"Jingyi Tang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tang, Jingyi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134350438","display_name":"Yizhen Luo","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Luo, Yizhen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059221640","display_name":"Caiyin Yang","orcid":"https://orcid.org/0000-0002-9057-4256"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yang, Caiyin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134277772","display_name":"Chang Su","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Su, Chang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026274141","display_name":"Rahul Thapa","orcid":"https://orcid.org/0000-0002-1137-955X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Thapa, Rahul","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041254229","display_name":"Rui Q. Yang","orcid":"https://orcid.org/0000-0002-4504-4897"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yang, Rui","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5121596937","display_name":"Ruihua Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Ruihua","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134331840","display_name":"Zeyu Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Zeyu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134328702","display_name":"Chong Gao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gao, Chong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134361626","display_name":"Dachao Ding","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ding, Dachao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134224139","display_name":"Guangrong He","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"He, Guangrong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071335825","display_name":"Miaolei Zhang","orcid":"https://orcid.org/0000-0001-5932-063X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Miaolei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006685570","display_name":"Lina Sun","orcid":"https://orcid.org/0000-0002-6190-6039"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sun, Lina","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100417763","display_name":"Wenyang Wang","orcid":"https://orcid.org/0000-0002-4863-2045"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Wenyang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134331117","display_name":"Yuchen Zhong","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhong, Yuchen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031602793","display_name":"Zhuohao Shen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shen, Zhuohao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134259842","display_name":"Di He","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"He, Di","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134262992","display_name":"Jianzhu Ma","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ma, Jianzhu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134335235","display_name":"Stefano Ermon","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ermon, Stefano","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134345647","display_name":"Tongyang Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Tongyang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100730785","display_name":"Xiaowen Chu","orcid":"https://orcid.org/0000-0001-9745-4372"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chu, Xiaowen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134253597","display_name":"James Zou","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zou, James","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5103223472","display_name":"Yuzhi Xu","orcid":"https://orcid.org/0000-0002-3325-5427"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xu, Yuzhi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"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":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11948","display_name":"Machine Learning in Materials Science","score":0.4722999930381775,"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"}},"topics":[{"id":"https://openalex.org/T11948","display_name":"Machine Learning in Materials Science","score":0.4722999930381775,"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/T10682","display_name":"Quantum Computing Algorithms and Architecture","score":0.1111999973654747,"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/T11986","display_name":"Scientific Computing and Data Management","score":0.07829999923706055,"subfield":{"id":"https://openalex.org/subfields/1802","display_name":"Information Systems and Management"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.6137999892234802},{"id":"https://openalex.org/keywords/simple","display_name":"Simple (philosophy)","score":0.5968000292778015},{"id":"https://openalex.org/keywords/scaling","display_name":"Scaling","score":0.5640000104904175},{"id":"https://openalex.org/keywords/scientific-discovery","display_name":"Scientific discovery","score":0.5116000175476074},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5013999938964844},{"id":"https://openalex.org/keywords/base","display_name":"Base (topology)","score":0.3855000138282776},{"id":"https://openalex.org/keywords/knowledge-base","display_name":"Knowledge base","score":0.3003999888896942}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6834999918937683},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.6137999892234802},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.5968000292778015},{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.5640000104904175},{"id":"https://openalex.org/C2984917352","wikidata":"https://www.wikidata.org/wiki/Q12772819","display_name":"Scientific discovery","level":2,"score":0.5116000175476074},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5013999938964844},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.451200008392334},{"id":"https://openalex.org/C42058472","wikidata":"https://www.wikidata.org/wiki/Q810214","display_name":"Base (topology)","level":2,"score":0.3855000138282776},{"id":"https://openalex.org/C4554734","wikidata":"https://www.wikidata.org/wiki/Q593744","display_name":"Knowledge base","level":2,"score":0.3003999888896942},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.299699991941452},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.2937000095844269},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2883000075817108},{"id":"https://openalex.org/C74172769","wikidata":"https://www.wikidata.org/wiki/Q1446839","display_name":"Routing (electronic design automation)","level":2,"score":0.28369998931884766},{"id":"https://openalex.org/C184670325","wikidata":"https://www.wikidata.org/wiki/Q512604","display_name":"Loop (graph theory)","level":2,"score":0.2782999873161316},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.267300009727478},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2606000006198883},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.2597000002861023}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2604.19341","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.19341","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2604.19341","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.19341","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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"},"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":{"Language":[0],"models":[1,197,215],"are":[2],"increasingly":[3],"used":[4,151],"in":[5,69],"scientific":[6,80,124,234],"discovery":[7,63,116],"to":[8,75,87,208,217],"generate":[9],"hypotheses,":[10],"propose":[11],"candidate":[12,35],"solutions,":[13],"implement":[14],"systems,":[15],"and":[16,72,106,141,168,236],"iteratively":[17],"refine":[18],"them.":[19],"At":[20],"the":[21,29,49,58,77,119,149,177],"core":[22],"of":[23,31,51,60,79],"these":[24,245],"trial-and-error":[25],"loops":[26,64,117],"lies":[27],"evaluation:":[28],"process":[30],"obtaining":[32],"feedback":[33],"on":[34,194,202],"solutions":[36,132,212],"via":[37],"verifiers,":[38],"simulators,":[39],"or":[40],"task-specific":[41],"scoring":[42],"functions.":[43],"While":[44],"prior":[45],"work":[46],"has":[47,54],"highlighted":[48],"importance":[50],"evaluation,":[52],"it":[53],"not":[55,198],"explicitly":[56],"formulated":[57],"problem":[59,83],"how":[61],"evaluation-driven":[62,115,224],"can":[65],"be":[66],"scaled":[67],"up":[68,148],"a":[70,82,96,228,238],"principled":[71],"effective":[73,223],"manner":[74],"push":[76],"boundaries":[78],"discovery,":[81,235],"this":[84],"paper":[85],"seeks":[86],"address.":[88],"We":[89],"introduce":[90],"Simple":[91],"Test-time":[92],"Evaluation-driven":[93],"Scaling":[94],"(SimpleTES),":[95],"general":[97],"framework":[98,242],"that":[99,162,175,187,213],"strategically":[100],"combines":[101],"parallel":[102],"exploration,":[103],"feedback-driven":[104,190],"refinement,":[105],"local":[107],"selection,":[108],"revealing":[109],"substantial":[110],"gains":[111],"unlocked":[112],"by":[113,154,166],"scaling":[114,226],"along":[118],"right":[120],"dimensions.":[121],"Across":[122],"21":[123],"problems":[125,204],"spanning":[126],"six":[127],"domains,":[128],"SimpleTES":[129,183],"discovers":[130],"state-of-the-art":[131],"using":[133],"gpt-oss":[134],"models,":[135],"consistently":[136],"outperforming":[137],"both":[138],"frontier-model":[139],"baselines":[140],"sophisticated":[142],"optimization":[143],"pipelines.":[144],"Particularly,":[145],"we":[146],"sped":[147],"widely":[150],"LASSO":[152],"algorithm":[153],"over":[155],"2x,":[156],"designed":[157],"quantum":[158],"circuit":[159],"routing":[160],"policies":[161],"reduce":[163],"gate":[164],"overhead":[165],"24.5%,":[167],"discovered":[169],"new":[170],"Erdos":[171],"minimum":[172],"overlap":[173],"constructions":[174],"surpass":[176],"best-known":[178],"results.":[179],"Beyond":[180],"novel":[181],"discoveries,":[182],"produces":[184],"trajectory-level":[185],"histories":[186],"naturally":[188],"supervise":[189],"learning.":[191],"When":[192],"post-trained":[193],"successful":[195],"trajectories,":[196],"only":[199],"improve":[200],"efficiency":[201],"seen":[203],"but":[205],"also":[206],"generalize":[207],"unseen":[209],"problems,":[210],"discovering":[211],"base":[214],"fail":[216],"uncover.":[218],"Together,":[219],"our":[220],"results":[221],"establish":[222],"loop":[225],"as":[227],"central":[229],"axis":[230],"for":[231,243],"advancing":[232],"LLM-driven":[233],"provide":[237],"simple":[239],"yet":[240],"practical":[241],"realizing":[244],"gains.":[246]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-04-23T00:00:00"}