{"id":"https://openalex.org/W7220470408","doi":"https://doi.org/10.48550/arxiv.2610.03631","title":"NeutronGym: Physics-Graded Neutron Instrument Design for LLM Agents","display_name":"NeutronGym: Physics-Graded Neutron Instrument Design for LLM Agents","publication_year":2026,"publication_date":"2026-10-02","ids":{"openalex":"https://openalex.org/W7220470408","doi":"https://doi.org/10.48550/arxiv.2610.03631"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2610.03631","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.03631","pdf_url":"https://arxiv.org/pdf/2610.03631","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/2610.03631","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5157580629","display_name":"Lijie Ding","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I1289243028","display_name":"Oak Ridge National Laboratory","ror":"https://ror.org/01qz5mb56","country_code":"US","type":"facility","lineage":["https://openalex.org/I1289243028","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I4210159294"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ding, Lijie","raw_affiliation_strings":["Neutron Scattering Division , Oak Ridge National Laboratory , Oak Ridge , TN 37831 , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Neutron Scattering Division , Oak Ridge National Laboratory , Oak Ridge , TN 37831 , USA","institution_ids":["https://openalex.org/I1289243028"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5058863771","display_name":"Changwoo Do","orcid":"https://orcid.org/0000-0001-8358-8417","observed_orcids":["https://orcid.org/0000-0001-8358-8417"]},"institutions":[{"id":"https://openalex.org/I1289243028","display_name":"Oak Ridge National Laboratory","ror":"https://ror.org/01qz5mb56","country_code":"US","type":"facility","lineage":["https://openalex.org/I1289243028","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I4210159294"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Do, Changwoo","raw_affiliation_strings":["Neutron Scattering Division , Oak Ridge National Laboratory , Oak Ridge , TN 37831 , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Neutron Scattering Division , Oak Ridge National Laboratory , Oak Ridge , TN 37831 , USA","institution_ids":["https://openalex.org/I1289243028"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I1289243028"],"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/T13904","display_name":"Artificial Intelligence Applications","score":0.2896000146865845,"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/T13904","display_name":"Artificial Intelligence Applications","score":0.2896000146865845,"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/T11949","display_name":"Nuclear Physics and Applications","score":0.1370999962091446,"subfield":{"id":"https://openalex.org/subfields/3108","display_name":"Radiation"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11948","display_name":"Machine Learning in Materials Science","score":0.05810000002384186,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/llm-based-agents","display_name":"LLM agents","score":0.7590000033378601},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"reinforcement learning","score":0.6589999794960022},{"id":"https://openalex.org/keywords/qwen3","display_name":"Qwen3","score":0.5019999742507935}],"concepts":[{"id":"https://openalex.org/C30038468","wikidata":"https://www.wikidata.org/wiki/Q4354775","display_name":"Memorization","level":2,"score":0.6195999979972839},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5218999981880188},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4943000078201294},{"id":"https://openalex.org/C153701036","wikidata":"https://www.wikidata.org/wiki/Q659974","display_name":"Trustworthiness","level":2,"score":0.4636000096797943},{"id":"https://openalex.org/C160145156","wikidata":"https://www.wikidata.org/wiki/Q778586","display_name":"Executable","level":2,"score":0.4156000018119812},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.39469999074935913},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.39010000228881836},{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.37290000915527344},{"id":"https://openalex.org/C100660578","wikidata":"https://www.wikidata.org/wiki/Q18733","display_name":"Recall","level":2,"score":0.357699990272522},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.3382999897003174},{"id":"https://openalex.org/C2777286243","wikidata":"https://www.wikidata.org/wiki/Q5591926","display_name":"Grading (engineering)","level":2,"score":0.33230000734329224},{"id":"https://openalex.org/C207520454","wikidata":"https://www.wikidata.org/wiki/Q3099911","display_name":"Scientific instrument","level":2,"score":0.32690000534057617},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.3124000132083893},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.2896000146865845},{"id":"https://openalex.org/C168065819","wikidata":"https://www.wikidata.org/wiki/Q845566","display_name":"Debugging","level":2,"score":0.28780001401901245},{"id":"https://openalex.org/C118530786","wikidata":"https://www.wikidata.org/wiki/Q1134732","display_name":"Instrumentation (computer programming)","level":2,"score":0.2816999852657318},{"id":"https://openalex.org/C18619997","wikidata":"https://www.wikidata.org/wiki/Q47627","display_name":"Experimental economics","level":2,"score":0.272599995136261},{"id":"https://openalex.org/C152568617","wikidata":"https://www.wikidata.org/wiki/Q2348","display_name":"Neutron","level":2,"score":0.2712000012397766},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.2572999894618988},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2538999915122986},{"id":"https://openalex.org/C44154836","wikidata":"https://www.wikidata.org/wiki/Q45045","display_name":"Simulation","level":1,"score":0.25130000710487366}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2610.03631","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.03631","pdf_url":"https://arxiv.org/pdf/2610.03631","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.2610.03631","doi":"https://doi.org/10.48550/arxiv.2610.03631","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2610.03631","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:2610.03631","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.03631","pdf_url":"https://arxiv.org/pdf/2610.03631","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/W7220470408.pdf","grobid_xml":"https://content.openalex.org/works/W7220470408.grobid-xml"},"referenced_works_count":40,"referenced_works":["https://openalex.org/W1857945056","https://openalex.org/W2408761201","https://openalex.org/W2626849060","https://openalex.org/W3003257820","https://openalex.org/W4386435778","https://openalex.org/W4389925942","https://openalex.org/W4391631327","https://openalex.org/W4406033138","https://openalex.org/W4406092746","https://openalex.org/W4407588785","https://openalex.org/W4412979501","https://openalex.org/W4413766540","https://openalex.org/W4414810229","https://openalex.org/W4414939355","https://openalex.org/W4416238240","https://openalex.org/W6941502030","https://openalex.org/W7117126565","https://openalex.org/W7118374140","https://openalex.org/W7129076256","https://openalex.org/W7130324431","https://openalex.org/W7133217982","https://openalex.org/W7154463892","https://openalex.org/W7154743487","https://openalex.org/W7154979744","https://openalex.org/W7155496691","https://openalex.org/W7159585813","https://openalex.org/W7160821619","https://openalex.org/W7160909247","https://openalex.org/W7160947383","https://openalex.org/W7161231670","https://openalex.org/W7161237792","https://openalex.org/W7161571342","https://openalex.org/W7161969463","https://openalex.org/W7163164257","https://openalex.org/W7163279756","https://openalex.org/W7163991313","https://openalex.org/W7164585052","https://openalex.org/W7165659912","https://openalex.org/W7165754228","https://openalex.org/W7168281855"],"related_works":["https://openalex.org/W7164585052","https://openalex.org/W7222042171","https://openalex.org/W7221319027","https://openalex.org/W7161237792","https://openalex.org/W7162409218","https://openalex.org/W4417492955","https://openalex.org/W7213365188","https://openalex.org/W7128293528","https://openalex.org/W7169829189","https://openalex.org/W7138972045"],"abstract_inverted_index":{"Designing":[0],"a":[1,48,67,81,95,108,135,141,146,191,209,225],"scientific":[2],"instrument":[3,34],"tests":[4],"whether":[5],"language-model":[6],"agents":[7,36],"can":[8],"do":[9],"physics":[10,205],"rather":[11],"than":[12],"recall":[13],"it,":[14],"provided":[15],"the":[16,28,73,104,154,174,186,196,203,241],"grading":[17],"cannot":[18],"be":[19],"argued":[20],"with.":[21],"We":[22],"introduce":[23],"NeutronGym,":[24],"to":[25,129],"our":[26],"knowledge":[27],"first":[29],"executable":[30],"environment":[31,117],"for":[32],"neutron":[33],"design:":[35],"build":[37],"instruments":[38,90],"through":[39],"validating":[40],"tools,":[41],"McStas":[42],"ray-traces":[43],"what":[44,169,190],"they":[45],"build,":[46],"and":[47,55,94,110,153,238],"level-resolved":[49],"ladder":[50],"grades":[51],"syntax,":[52],"runtime,":[53],"structure":[54],"science":[56],"with":[57,77],"no":[58],"LLM":[59],"judge.":[60],"Procedural":[61],"families":[62],"supply":[63],"unlimited":[64],"instances":[65,133],"of":[66,103,131,134],"fixed":[68],"layout":[69],"whose":[70,137],"design":[71,143],"parameters":[72],"agent":[74],"must":[75],"set,":[76],"held-out":[78,132],"parameter":[79],"regimes;":[80],"curated":[82],"slice,":[83],"McStasBench,":[84],"adds":[85],"16":[86],"tasks":[87],"from":[88,127,140],"published":[89],"behind":[91],"memorization":[92],"probes":[93,242],"sandbox.":[96],"Seven":[97],"models":[98,220],"reproduce":[99],"at":[100,145,157,195,215],"most":[101],"7":[102],"16,":[105],"none":[106,111],"retrieves":[107],"reference,":[109],"meets":[112],"an":[113,150],"improvement":[114],"target.":[115],"The":[116,166],"also":[118],"trains.":[119],"Reinforcement":[120],"learning":[121],"on":[122,161],"its":[123],"reward":[124,184],"takes":[125],"Qwen3-8B":[126],"11%":[128],"77%":[130],"family":[136],"targets":[138],"come":[139],"hidden":[142],"(69%":[144],"second":[147],"seed),":[148],"past":[149],"untrained":[151],"Qwen3-32B,":[152],"recipe":[155],"holds,":[156],"one":[158],"seed":[159],"each,":[160],"three":[162],"further":[163],"gated":[164],"families.":[165],"analysis":[167],"says":[168],"that":[170,211,233,243],"gain":[171],"is.":[172],"Without":[173],"ladder's":[175],"partial":[176],"credit":[177],"it":[178],"collapses":[179],"by":[180],"60":[181],"points.":[182],"From":[183],"alone":[185],"trained":[187],"model":[188],"reaches":[189],"classical":[192],"optimizer":[193],"reaches,":[194],"agent's":[197],"simulation":[198],"budget,":[199],"only":[200],"when":[201],"handed":[202],"closed-form":[204],"(77%":[206],"against":[207],"81%,":[208],"gap":[210],"does":[212],"not":[213],"separate":[214],"this":[216],"size),":[217],"while":[218],"frontier":[219],"still":[221],"solve":[222],"98-99%.":[223],"Getting":[224],"trustworthy":[226],"result":[227],"meant":[228],"failing":[229],"four":[230],"task":[231],"designs":[232],"no-model":[234],"baselines":[235],"could":[236],"solve,":[237],"we":[239],"release":[240],"found":[244],"them.":[245]},"counts_by_year":[],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-10-06T00:00:00"}