{"id":"https://openalex.org/W7204807602","doi":"https://doi.org/10.1016/j.array.2026.101323","title":"MAIL: Memory-driven, Adaptive, Incremental, and Literature-grounded framework for hypothesis generation in chemistry","display_name":"MAIL: Memory-driven, Adaptive, Incremental, and Literature-grounded framework for hypothesis generation in chemistry","publication_year":2026,"publication_date":"2026-10-08","ids":{"openalex":"https://openalex.org/W7204807602","doi":"https://doi.org/10.1016/j.array.2026.101323"},"language":"en","primary_location":{"id":"doi:10.1016/j.array.2026.101323","doi":"https://doi.org/10.1016/j.array.2026.101323","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.array.2026.101323","pdf_url":"https://www.sciencedirect.com/science/article/pii/S2590005626006466/pdf","source":{"id":"https://openalex.org/S4210194039","display_name":"Array","issn_l":"2590-0056","issn":["2590-0056"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["cwts-core","doaj","dongbi-d","jufo-1","norway-1","poland-40"],"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Array","raw_type":"journal-article"},"volume":null,"type":"article","indexed_in":["arxiv","crossref","datacite","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.sciencedirect.com/science/article/pii/S2590005626006466/pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5004686472","display_name":"Mahdi Babaei","orcid":"https://orcid.org/0000-0003-4255-3941","observed_orcids":["https://orcid.org/0000-0003-4255-3941"]},"institutions":[{"id":"https://openalex.org/I108468826","display_name":"Stevens Institute of Technology","ror":"https://ror.org/02z43xh36","country_code":"US","type":"education","lineage":["https://openalex.org/I108468826"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mahdi Babaei","raw_affiliation_strings":["Biomedical Engineering, Stevens Institute of Technology, 07030, Hoboken, NJ, USA"],"raw_orcid":"https://orcid.org/0000-0003-4255-3941","affiliations":[{"raw_affiliation_string":"Biomedical Engineering, Stevens Institute of Technology, 07030, Hoboken, NJ, USA","institution_ids":["https://openalex.org/I108468826"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101736269","display_name":"Xueshen Li","orcid":"https://orcid.org/0000-0002-6440-7462","observed_orcids":["https://orcid.org/0000-0002-6440-7462","https://orcid.org/0009-0005-5904-0722"]},"institutions":[{"id":"https://openalex.org/I108468826","display_name":"Stevens Institute of Technology","ror":"https://ror.org/02z43xh36","country_code":"US","type":"education","lineage":["https://openalex.org/I108468826"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xueshen Li","raw_affiliation_strings":["Biomedical Engineering, Stevens Institute of Technology, 07030, Hoboken, NJ, USA"],"raw_orcid":"https://orcid.org/0000-0002-6440-7462","affiliations":[{"raw_affiliation_string":"Biomedical Engineering, Stevens Institute of Technology, 07030, Hoboken, NJ, USA","institution_ids":["https://openalex.org/I108468826"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063065488","display_name":"Yutao Kuang","orcid":"https://orcid.org/0000-0003-0990-5079","observed_orcids":["https://orcid.org/0000-0003-0990-5079"]},"institutions":[{"id":"https://openalex.org/I141945490","display_name":"University of British Columbia","ror":"https://ror.org/03rmrcq20","country_code":"CA","type":"education","lineage":["https://openalex.org/I141945490"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Yutao Kuang","raw_affiliation_strings":["Department of Chemistry, University of British Columbia, V6T 1Z1, Vancouver, British Columbia, Canada"],"raw_orcid":"https://orcid.org/0000-0003-0990-5079","affiliations":[{"raw_affiliation_string":"Department of Chemistry, University of British Columbia, V6T 1Z1, Vancouver, British Columbia, Canada","institution_ids":["https://openalex.org/I141945490"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034853042","display_name":"Jolene P. Reid","orcid":"https://orcid.org/0000-0003-2397-0053","observed_orcids":["https://orcid.org/0000-0003-2397-0053"]},"institutions":[{"id":"https://openalex.org/I141945490","display_name":"University of British Columbia","ror":"https://ror.org/03rmrcq20","country_code":"CA","type":"education","lineage":["https://openalex.org/I141945490"]}],"countries":["CA"],"is_corresponding":true,"raw_author_name":"Jolene P. Reid","raw_affiliation_strings":["Department of Chemistry, University of British Columbia, V6T 1Z1, Vancouver, British Columbia, Canada"],"raw_orcid":"https://orcid.org/0000-0003-2397-0053","affiliations":[{"raw_affiliation_string":"Department of Chemistry, University of British Columbia, V6T 1Z1, Vancouver, British Columbia, Canada","institution_ids":["https://openalex.org/I141945490"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5148789105","display_name":"Yu Gan","orcid":"https://orcid.org/0000-0003-3409-3412","observed_orcids":["https://orcid.org/0000-0003-3409-3412"]},"institutions":[{"id":"https://openalex.org/I108468826","display_name":"Stevens Institute of Technology","ror":"https://ror.org/02z43xh36","country_code":"US","type":"education","lineage":["https://openalex.org/I108468826"]},{"id":"https://openalex.org/I66946132","display_name":"University of Maryland, College Park","ror":"https://ror.org/047s2c258","country_code":"US","type":"education","lineage":["https://openalex.org/I66946132"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Yu Gan","raw_affiliation_strings":["Artificial Intelligence Interdisciplinary Institute at Maryland, University of Maryland, 20742, College Park, MD, United States","Biomedical Engineering, Stevens Institute of Technology, 07030, Hoboken, NJ, USA","Department of Bioengineering, University of Maryland, 20742, College Park, MD, United States"],"raw_orcid":"https://orcid.org/0000-0003-3409-3412","affiliations":[{"raw_affiliation_string":"Artificial Intelligence Interdisciplinary Institute at Maryland, University of Maryland, 20742, College Park, MD, United States","institution_ids":["https://openalex.org/I66946132"]},{"raw_affiliation_string":"Biomedical Engineering, Stevens Institute of Technology, 07030, Hoboken, NJ, USA","institution_ids":["https://openalex.org/I108468826"]},{"raw_affiliation_string":"Department of Bioengineering, University of Maryland, 20742, College Park, MD, United States","institution_ids":["https://openalex.org/I66946132"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5034853042","https://openalex.org/A5148789105"],"corresponding_institution_ids":["https://openalex.org/I108468826","https://openalex.org/I141945490","https://openalex.org/I66946132"],"apc_list":{"value":1680,"currency":"USD","value_usd":1680},"apc_paid":{"value":1680,"currency":"USD","value_usd":1680},"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.54135615,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"32","issue":null,"first_page":"101323","last_page":"101323"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11948","display_name":"Machine Learning in Materials Science","score":0.5268999934196472,"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":0.5268999934196472,"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/T10211","display_name":"Computational Drug Discovery Methods","score":0.23510000109672546,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.03840000182390213,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/hypothesis-generation","display_name":"hypothesis generation","score":0.8460000157356262},{"id":"https://openalex.org/keywords/chemistry","display_name":"chemistry","score":0.6169999837875366},{"id":"https://openalex.org/keywords/large-language-models","display_name":"large language models","score":0.8769999742507935},{"id":"https://openalex.org/keywords/chemical-literature","display_name":"chemical literature","score":0.5569999814033508},{"id":"https://openalex.org/keywords/temporal-grounding","display_name":"temporal grounding","score":0.5559999942779541}],"concepts":[{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.7620999813079834},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6281999945640564},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5364000201225281},{"id":"https://openalex.org/C2777735758","wikidata":"https://www.wikidata.org/wiki/Q817765","display_name":"Path (computing)","level":2,"score":0.5130000114440918},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.44519999623298645},{"id":"https://openalex.org/C151201525","wikidata":"https://www.wikidata.org/wiki/Q177239","display_name":"Limit (mathematics)","level":2,"score":0.3815000057220459},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.359499990940094},{"id":"https://openalex.org/C14224292","wikidata":"https://www.wikidata.org/wiki/Q13600188","display_name":"Conceptual framework","level":2,"score":0.3555999994277954},{"id":"https://openalex.org/C4554734","wikidata":"https://www.wikidata.org/wiki/Q593744","display_name":"Knowledge base","level":2,"score":0.33889999985694885},{"id":"https://openalex.org/C13606891","wikidata":"https://www.wikidata.org/wiki/Q2623243","display_name":"Conceptual model","level":2,"score":0.29429998993873596},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.28760001063346863}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1016/j.array.2026.101323","doi":"https://doi.org/10.1016/j.array.2026.101323","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.array.2026.101323","pdf_url":"https://www.sciencedirect.com/science/article/pii/S2590005626006466/pdf","source":{"id":"https://openalex.org/S4210194039","display_name":"Array","issn_l":"2590-0056","issn":["2590-0056"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["cwts-core","doaj","dongbi-d","jufo-1","norway-1","poland-40"],"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Array","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:2608.28315","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.28315","pdf_url":"https://arxiv.org/pdf/2608.28315","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":"pmh:oai:doaj.org/article:b7c45abdc300421a8c628c84f0291321","doi":null,"is_oa":false,"landing_page_url":"https://doaj.org/article/b7c45abdc300421a8c628c84f0291321","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Array, Vol 32, Iss , Pp 101323- (2026)","raw_type":"article"},{"id":"doi:10.48550/arxiv.2608.28315","doi":"https://doi.org/10.48550/arxiv.2608.28315","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2608.28315","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":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.1016/j.array.2026.101323","doi":"https://doi.org/10.1016/j.array.2026.101323","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.array.2026.101323","pdf_url":"https://www.sciencedirect.com/science/article/pii/S2590005626006466/pdf","source":{"id":"https://openalex.org/S4210194039","display_name":"Array","issn_l":"2590-0056","issn":["2590-0056"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["cwts-core","doaj","dongbi-d","jufo-1","norway-1","poland-40"],"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Array","raw_type":"journal-article"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[{"display_name":"Peace, justice, and strong institutions","score":0.5470028519630432,"id":"https://metadata.un.org/sdg/16"}],"study_designs":[],"awards":[{"id":"https://openalex.org/G2252583846","display_name":null,"funder_award_id":"SA-AUT-2024-022a","funder_id":"https://openalex.org/F4320306487","funder_display_name":"Research Corporation for Science Advancement"},{"id":"https://openalex.org/G9001198581","display_name":null,"funder_award_id":"SA-AUT-2024-022b","funder_id":"https://openalex.org/F4320311304","funder_display_name":"Research Corporation for Scientific Advancement"},{"id":"https://openalex.org/G9001235844","display_name":null,"funder_award_id":"SA-AUT-2024-022a","funder_id":"https://openalex.org/F4320311304","funder_display_name":"Research Corporation for Scientific Advancement"}],"funders":[{"id":"https://openalex.org/F4320306487","display_name":"Research Corporation for Science Advancement","ror":"https://ror.org/00jp8d455"},{"id":"https://openalex.org/F4320311304","display_name":"Research Corporation for Scientific Advancement","ror":"https://ror.org/00jp8d455"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7204807602.pdf","grobid_xml":"https://content.openalex.org/works/W7204807602.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"The":[0],"ever-expanding":[1],"volume":[2],"of":[3,162,182],"the":[4,17,116,147,156,163,169,180],"chemical":[5,187],"literature":[6],"offers":[7],"unprecedented":[8],"opportunities":[9],"to":[10,27,184],"generate":[11,190],"novel":[12],"and":[13,57,63,77,110,124,128,142,150,159,167,189,196],"impactful":[14],"hypotheses.":[15],"However,":[16],"bottleneck":[18],"lies":[19],"in":[20,84],"efficiently":[21],"navigating":[22],"this":[23,41,66],"vast":[24],"knowledge":[25],"base":[26],"formulate":[28],"high-quality,":[29],"experimentally":[30],"meaningful":[31],"insights.":[32],"While":[33],"Large":[34],"Language":[35],"Models":[36],"(LLMs)":[37],"show":[38],"promise":[39],"for":[40,81,174],"task,":[42],"existing":[43],"methods":[44],"often":[45],"rely":[46],"on":[47,119],"static":[48],"inspiration":[49],"corpora,":[50],"predefined":[51],"heuristics,":[52],"or":[53],"laborious":[54],"human-in-the-loop":[55],"pipelines":[56],"decision-support":[58],"frameworks":[59],"that":[60,107,192],"limit":[61],"scalability":[62],"novelty.":[64],"In":[65],"work,":[67],"we":[68],"propose":[69],"an":[70,103],"automated":[71],"approach,":[72],"a":[73,93,120,125],"Memory-driven,":[74],"Adaptive,":[75],"Incremental,":[76],"Literature-grounded":[78],"(MAIL)":[79],"framework":[80,118],"hypothesis":[82,90],"generation":[83,91],"chemistry.":[85],"Our":[86],"MAIL":[87,117,138],"method":[88],"formulates":[89],"as":[92],"temporally":[94],"grounded,":[95],"memory-driven":[96],"reasoning":[97],"process,":[98],"where":[99],"hypotheses":[100,191],"emerge":[101],"from":[102],"evolving":[104],"conceptual":[105],"path":[106],"continuously":[108],"accumulates":[109],"reinterprets":[111],"prior":[112],"knowledge.":[113],"We":[114],"evaluated":[115],"public":[121],"TOMATO-Chem":[122],"dataset":[123],"newly":[126],"curated":[127],"disseminated":[129],"high-novelty":[130],"nature/science":[131],"challenge":[132],"(HN-NS)":[133],"dataset.":[134],"Across":[135],"both":[136,194],"datasets,":[137],"generates":[139],"structurally":[140],"coherent":[141],"mechanistically":[143],"plausible":[144],"hypotheses,":[145,166],"achieves":[146],"highest":[148,170],"MIOS":[149],"MPOS":[151],"by":[152],"more":[153],"effectively":[154],"recovering":[155],"central":[157],"ideas":[158],"methodological":[160],"elements":[161],"historical":[164],"target":[165],"obtains":[168],"overall":[171],"expert-evaluation":[172],"scores":[173],"scientific":[175],"quality.":[176],"These":[177],"results":[178],"demonstrate":[179],"potential":[181],"LLMs":[183],"autonomously":[185],"explore":[186],"domains":[188],"are":[193],"innovative":[195],"chemically":[197],"plausible.":[198]},"counts_by_year":[],"updated_date":"2026-10-19T09:35:57.686232","created_date":"2026-09-01T00:00:00"}