{"id":"https://openalex.org/W7134833769","doi":"https://doi.org/10.48550/arxiv.2603.07642","title":"Helix: Evolutionary Reinforcement Learning for Open-Ended Scientific Problem Solving","display_name":"Helix: Evolutionary Reinforcement Learning for Open-Ended Scientific Problem Solving","publication_year":2026,"publication_date":"2026-03-08","ids":{"openalex":"https://openalex.org/W7134833769","doi":"https://doi.org/10.48550/arxiv.2603.07642"},"language":null,"primary_location":{"id":"pmh:doi:10.48550/arxiv.2603.07642","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"publisher-specific-oa","license_id":"https://openalex.org/licenses/publisher-specific-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":null,"any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5128654837","display_name":"Chang Su","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Su, Chang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128662862","display_name":"Zhongkai Hao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hao, Zhongkai","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128683978","display_name":"Zhizhou Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Zhizhou","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128645138","display_name":"Zeyu Xia","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xia, Zeyu","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128684890","display_name":"Youjia Wu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wu, Youjia","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128631920","display_name":"Hang Su","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Su, Hang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5128687047","display_name":"Jun Zhu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhu, Jun","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5128654837"],"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":0.48159998655319214,"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":0.48159998655319214,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.060100000351667404,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T11636","display_name":"Artificial Intelligence in Healthcare and Education","score":0.05609999969601631,"subfield":{"id":"https://openalex.org/subfields/2718","display_name":"Health Informatics"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8166000247001648},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.4966000020503998},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.32330000400543213},{"id":"https://openalex.org/keywords/evolutionary-algorithm","display_name":"Evolutionary algorithm","score":0.3116999864578247},{"id":"https://openalex.org/keywords/helix","display_name":"Helix (gastropod)","score":0.28519999980926514},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.2745000123977661}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8166000247001648},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6116999983787537},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5273000001907349},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4966000020503998},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3564000129699707},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.32330000400543213},{"id":"https://openalex.org/C159149176","wikidata":"https://www.wikidata.org/wiki/Q14489129","display_name":"Evolutionary algorithm","level":2,"score":0.3116999864578247},{"id":"https://openalex.org/C2778530040","wikidata":"https://www.wikidata.org/wiki/Q1937315","display_name":"Helix (gastropod)","level":3,"score":0.28519999980926514},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.2745000123977661},{"id":"https://openalex.org/C105902424","wikidata":"https://www.wikidata.org/wiki/Q1197129","display_name":"Evolutionary computation","level":2,"score":0.2718999981880188},{"id":"https://openalex.org/C47932503","wikidata":"https://www.wikidata.org/wiki/Q5395689","display_name":"Error-driven learning","level":3,"score":0.2628999948501587},{"id":"https://openalex.org/C77967617","wikidata":"https://www.wikidata.org/wiki/Q4677561","display_name":"Active learning (machine learning)","level":2,"score":0.2612000107765198}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:doi:10.48550/arxiv.2603.07642","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"publisher-specific-oa","license_id":"https://openalex.org/licenses/publisher-specific-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"},{"id":"doi:10.48550/arxiv.2603.07642","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.07642","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":"article"}],"best_oa_location":{"id":"pmh:doi:10.48550/arxiv.2603.07642","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"publisher-specific-oa","license_id":"https://openalex.org/licenses/publisher-specific-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"},"sustainable_development_goals":[{"score":0.48482102155685425,"id":"https://metadata.un.org/sdg/1","display_name":"No poverty"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Large":[0],"language":[1],"models":[2],"(LLMs)":[3],"with":[4,67,121,142],"reasoning":[5],"abilities":[6],"have":[7],"demonstrated":[8],"growing":[9],"promise":[10],"for":[11,94],"tackling":[12],"complex":[13],"scientific":[14],"problems.":[15],"Yet":[16],"such":[17],"tasks":[18],"are":[19],"inherently":[20],"domain-specific,":[21],"unbounded":[22],"and":[23,29,50,90,158],"open-ended,":[24],"demanding":[25],"exploration":[26,48,86],"across":[27],"vast":[28],"flexible":[30],"solution":[31,101],"spaces.":[32],"Existing":[33],"approaches,":[34],"whether":[35],"purely":[36],"learning-based":[37],"or":[38],"reliant":[39],"on":[40,155],"carefully":[41,144],"designed":[42],"workflows,":[43],"often":[44],"suffer":[45],"from":[46],"limited":[47],"efficiency":[49],"poor":[51],"generalization.":[52],"To":[53],"overcome":[54],"these":[55],"challenges,":[56],"we":[57],"present":[58],"HELIX":[59,70,117,138],"--":[60],"a":[61,76,122,130,143],"Hierarchical":[62],"Evolutionary":[63],"reinforcement":[64,92],"Learning":[65],"framework":[66],"In-context":[68],"eXperiences.":[69],"introduces":[71],"two":[72],"key":[73],"novelties:":[74],"(i)":[75],"diverse":[77],"yet":[78],"high-quality":[79],"pool":[80],"of":[81,108,124,126,152],"candidate":[82],"solutions":[83],"that":[84,98],"broadens":[85],"through":[87],"in-context":[88],"learning,":[89],"(ii)":[91],"learning":[93,136],"iterative":[95],"policy":[96],"refinement":[97],"progressively":[99],"elevates":[100],"quality.":[102],"This":[103],"synergy":[104],"enables":[105],"the":[106,113,156],"discovery":[107],"more":[109],"advanced":[110],"solutions.":[111],"On":[112],"circle":[114],"packing":[115],"task,":[116],"achieves":[118],"state-of-the-art":[119],"result":[120],"sum":[123],"radii":[125],"2.63598308":[127],"using":[128],"only":[129],"14B":[131],"model.":[132],"Across":[133],"standard":[134],"machine":[135],"benchmarks,":[137],"further":[139],"surpasses":[140],"GPT-4o":[141],"engineered":[145],"pipeline,":[146],"delivering":[147],"an":[148],"average":[149],"F1":[150],"improvement":[151],"5.95":[153],"points":[154],"Adult":[157],"Bank":[159],"Marketing":[160],"datasets.":[161]},"counts_by_year":[],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2026-03-11T00:00:00"}