{"id":"https://openalex.org/W7204893974","doi":"https://doi.org/10.18653/2026.findings-emnlp.1885","title":"S3C-LLM: Skill-Code Guided Agentic Language Models for Spectrum-to-Structure Elucidation","display_name":"S3C-LLM: Skill-Code Guided Agentic Language Models for Spectrum-to-Structure Elucidation","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7204893974","doi":"https://doi.org/10.18653/2026.findings-emnlp.1885"},"language":"en","primary_location":{"id":"doi:10.18653/2026.findings-emnlp.1885","doi":"https://doi.org/10.18653/2026.findings-emnlp.1885","is_oa":true,"landing_page_url":"https://doi.org/10.18653/2026.findings-emnlp.1885","pdf_url":"https://aclanthology.org/2026.findings-emnlp.1885.pdf","source":{"id":"https://openalex.org/S7407096085","display_name":"Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: EMNLP 2026","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://aclanthology.org/2026.findings-emnlp.1885.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5104174550","display_name":"Xuanle Zhao","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xuanle Zhao","raw_affiliation_strings":["School of Artificial Intelligence , University of Chinese Academy of Sciences","The Key Laboratory of Cognition and Decision Intelligence for Complex Systems , Institute of Automation , Chinese Academy of Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence , University of Chinese Academy of Sciences","institution_ids":["https://openalex.org/I4210165038"]},{"raw_affiliation_string":"The Key Laboratory of Cognition and Decision Intelligence for Complex Systems , Institute of Automation , Chinese Academy of Sciences","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5148873826","display_name":"Xinyuan Cai","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinyuan Cai","raw_affiliation_strings":["The Key Laboratory of Cognition and Decision Intelligence for Complex Systems , Institute of Automation , Chinese Academy of Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Key Laboratory of Cognition and Decision Intelligence for Complex Systems , Institute of Automation , Chinese Academy of Sciences","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5148848058","display_name":"Xiang Cheng","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiang Cheng","raw_affiliation_strings":["The Key Laboratory of Cognition and Decision Intelligence for Complex Systems , Institute of Automation , Chinese Academy of Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Key Laboratory of Cognition and Decision Intelligence for Complex Systems , Institute of Automation , Chinese Academy of Sciences","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5148904535","display_name":"Bo Xu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bo XU","raw_affiliation_strings":["School of Artificial Intelligence , University of Chinese Academy of Sciences","The Key Laboratory of Cognition and Decision Intelligence for Complex Systems , Institute of Automation , Chinese Academy of Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence , University of Chinese Academy of Sciences","institution_ids":["https://openalex.org/I4210165038"]},{"raw_affiliation_string":"The Key Laboratory of Cognition and Decision Intelligence for Complex Systems , Institute of Automation , Chinese Academy of Sciences","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.73358386,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"40184","last_page":"40212"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10211","display_name":"Computational Drug Discovery Methods","score":0.774399995803833,"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"}},"topics":[{"id":"https://openalex.org/T10211","display_name":"Computational Drug Discovery Methods","score":0.774399995803833,"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/T10640","display_name":"Spectroscopy and Chemometric Analyses","score":0.04039999842643738,"subfield":{"id":"https://openalex.org/subfields/1602","display_name":"Analytical Chemistry"},"field":{"id":"https://openalex.org/fields/16","display_name":"Chemistry"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11948","display_name":"Machine Learning in Materials Science","score":0.03310000151395798,"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/agentic-large-language-models","display_name":"agentic large language models","score":0.8320000171661377},{"id":"https://openalex.org/keywords/two-stage-training","display_name":"two-stage training","score":0.5350000262260437},{"id":"https://openalex.org/keywords/reinforcement-learning-from-human-feedback","display_name":"reinforcement learning from human feedback","score":0.7559999823570251},{"id":"https://openalex.org/keywords/molecular-structure-prediction","display_name":"molecular structure prediction","score":0.49300000071525574}],"concepts":[{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.7617999911308289},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6086999773979187},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.5799000263214111},{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.5649999976158142},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5400999784469604},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4684999883174896},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.39890000224113464},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.39489999413490295},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3847000002861023},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.37929999828338623},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.3529999852180481},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.3334999978542328},{"id":"https://openalex.org/C22367795","wikidata":"https://www.wikidata.org/wiki/Q7625208","display_name":"Structured prediction","level":2,"score":0.31619998812675476},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.299699991941452},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.2799000144004822},{"id":"https://openalex.org/C188147891","wikidata":"https://www.wikidata.org/wiki/Q147638","display_name":"Cognitive science","level":1,"score":0.2727999985218048},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.25619998574256897}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.18653/2026.findings-emnlp.1885","doi":"https://doi.org/10.18653/2026.findings-emnlp.1885","is_oa":true,"landing_page_url":"https://doi.org/10.18653/2026.findings-emnlp.1885","pdf_url":"https://aclanthology.org/2026.findings-emnlp.1885.pdf","source":{"id":"https://openalex.org/S7407096085","display_name":"Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: EMNLP 2026","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2608.30910","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.30910","pdf_url":"https://arxiv.org/pdf/2608.30910","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.2608.30910","doi":"https://doi.org/10.48550/arxiv.2608.30910","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2608.30910","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":"doi:10.18653/2026.findings-emnlp.1885","doi":"https://doi.org/10.18653/2026.findings-emnlp.1885","is_oa":true,"landing_page_url":"https://doi.org/10.18653/2026.findings-emnlp.1885","pdf_url":"https://aclanthology.org/2026.findings-emnlp.1885.pdf","source":{"id":"https://openalex.org/S7407096085","display_name":"Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: EMNLP 2026","raw_type":"proceedings-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7204893974.pdf","grobid_xml":"https://content.openalex.org/works/W7204893974.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4416858251","https://openalex.org/W4410131581","https://openalex.org/W7171925512","https://openalex.org/W7083685966","https://openalex.org/W7138925913","https://openalex.org/W4416510415","https://openalex.org/W4416237352","https://openalex.org/W4402696886","https://openalex.org/W4401960047","https://openalex.org/W4402484720"],"abstract_inverted_index":{"Spectroscopic":[0],"structure":[1],"elucidation":[2],"is":[3],"central":[4],"to":[5,80],"molecular":[6],"analysis,":[7],"but":[8],"recent":[9],"Large":[10],"Language":[11],"Model":[12],"(LLM)-based":[13],"methods":[14],"mostly":[15],"formulate":[16],"it":[17,29],"as":[18,41],"direct":[19],"spectrum-to-SMILES":[20],"generation.Although":[21],"this":[22,53],"paradigm":[23],"can":[24],"leverage":[25],"paired":[26],"spectral":[27],"data,":[28],"does":[30],"not":[31],"explicitly":[32],"model":[33],"the":[34,85,90],"analytical":[35],"workflow":[36],"used":[37],"by":[38,126],"spectroscopists,":[39],"such":[40],"diagnostic":[42],"peak":[43],"interpretation,":[44],"fragment":[45],"reasoning,":[46],"formula":[47,95],"constraints,":[48],"and":[49,60,88,94,113,144],"chemical":[50],"consistency":[51],"checking.In":[52],"paper,":[54],"we":[55,100],"introduce":[56],"S3C-LLM,":[57],"a":[58,70,102,107,114],"skill-guided":[59],"code-grounded":[61],"agentic":[62],"LLM":[63],"for":[64],"spectrum-to-structure":[65],"elucidation.Rather":[66],"than":[67,152],"directly":[68],"predicting":[69],"molecule,":[71],"S3C-LLM":[72,138],"retrieves":[73],"modality-specific":[74],"spectroscopy":[75,104],"skills,":[76],"executes":[77],"analysis":[78],"code":[79],"instantiate":[81],"these":[82],"skills":[83],"on":[84,133],"input":[86],"spectra,":[87,148],"integrates":[89],"resulting":[91],"peak-level":[92],"evidence":[93],"constraints":[96],"before":[97],"generating":[98],"SMILES.Specifically,":[99],"contribute":[101],"selfevolving":[103],"skill":[105],"library,":[106],"thinkingaugmented":[108],"skill-code":[109],"trajectory":[110],"construction":[111],"pipeline,":[112],"two-stage":[115],"training":[116,156],"strategy":[117],"that":[118,137],"teaches":[119],"Qwen3-4B":[120],"through":[121],"supervised":[122],"finetuning":[123],"(SFT)":[124],"followed":[125],"our":[127],"proposed":[128],"steplevel":[129],"reinforcement":[130],"learning":[131],"(RL).Experiments":[132],"diverse":[134],"benchmarks":[135],"show":[136],"consistently":[139],"outperforms":[140],"current":[141],"general":[142],"LLMs":[143],"spectrum-specific":[145],"models":[146],"across":[147],"while":[149],"using":[150],"less":[151],"1/10th":[153],"of":[154],"SpectraLLM's":[155],"corpus.":[157]},"counts_by_year":[],"updated_date":"2026-10-31T12:09:11.096373","created_date":"2026-09-02T00:00:00"}