{"id":"https://openalex.org/W7170882484","doi":"https://doi.org/10.48550/arxiv.2607.20431","title":"Skill-Contracted Agents for Evidence-Aware Materials Literature Analysis","display_name":"Skill-Contracted Agents for Evidence-Aware Materials Literature Analysis","publication_year":2026,"publication_date":"2026-05-10","ids":{"openalex":"https://openalex.org/W7170882484","doi":"https://doi.org/10.48550/arxiv.2607.20431"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2607.20431","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2607.20431","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,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","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.2607.20431","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5036431343","display_name":"Bixuan Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Bixuan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5143566137","display_name":"Yu Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Yu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5141700328","display_name":"S Shi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shi, Shuo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136122210","display_name":"Xiaoya Huang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Huang, Xiaoya","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5143561949","display_name":"Peng Kang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kang, Peng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5143549121","display_name":"Lei Zheng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zheng, Lei","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":0.8920000195503235,"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":0.8920000195503235,"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/T10028","display_name":"Topic Modeling","score":0.01209999993443489,"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/T13274","display_name":"Expert finding and Q&A systems","score":0.010099999606609344,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/credibility","display_name":"Credibility","score":0.7148000001907349},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6488999724388123},{"id":"https://openalex.org/keywords/property","display_name":"Property (philosophy)","score":0.5339000225067139},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.49300000071525574},{"id":"https://openalex.org/keywords/ranking","display_name":"Ranking (information retrieval)","score":0.4368000030517578},{"id":"https://openalex.org/keywords/citation-analysis","display_name":"Citation analysis","score":0.3677000105381012},{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.36399999260902405}],"concepts":[{"id":"https://openalex.org/C2780224610","wikidata":"https://www.wikidata.org/wiki/Q1530061","display_name":"Credibility","level":2,"score":0.7148000001907349},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.666700005531311},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6488999724388123},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5515999794006348},{"id":"https://openalex.org/C189950617","wikidata":"https://www.wikidata.org/wiki/Q937228","display_name":"Property (philosophy)","level":2,"score":0.5339000225067139},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.49300000071525574},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.4368000030517578},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3727000057697296},{"id":"https://openalex.org/C105345328","wikidata":"https://www.wikidata.org/wiki/Q206276","display_name":"Citation analysis","level":3,"score":0.3677000105381012},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.36399999260902405},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.35850000381469727},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3246000111103058},{"id":"https://openalex.org/C161156560","wikidata":"https://www.wikidata.org/wiki/Q1638872","display_name":"Document retrieval","level":2,"score":0.3140000104904175},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.301800012588501},{"id":"https://openalex.org/C2777382242","wikidata":"https://www.wikidata.org/wiki/Q6017816","display_name":"Index (typography)","level":2,"score":0.27880001068115234},{"id":"https://openalex.org/C2778805511","wikidata":"https://www.wikidata.org/wiki/Q1713","display_name":"Citation","level":2,"score":0.2583000063896179},{"id":"https://openalex.org/C2777855551","wikidata":"https://www.wikidata.org/wiki/Q12310021","display_name":"Subject (documents)","level":2,"score":0.2508000135421753}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2607.20431","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2607.20431","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,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2607.20431","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2607.20431","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,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.8464813232421875}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Materials":[0],"science":[1],"literature":[2,161],"analysis":[3,162],"requires":[4],"simultaneous":[5],"attention":[6],"to":[7,20,95],"composition,":[8],"processing,":[9],"characterization,":[10],"and":[11,76,80,101,131,141,156],"property":[12],"relationships,":[13],"yet":[14],"conventional":[15],"retrieval-augmented":[16],"generation":[17,45,158],"pipelines":[18],"struggle":[19],"reconcile":[21],"heterogeneous":[22],"tasks":[23],"within":[24],"a":[25,33,62,105,122],"single":[26],"retrieve-then-generate":[27],"architecture.":[28],"Here":[29],"we":[30],"present":[31],"AlphaAgent,":[32],"skill-driven":[34],"agent":[35],"framework":[36],"that":[37,149],"decouples":[38],"retrieval-based":[39],"question":[40],"answering":[41],"from":[42,70],"paper-level":[43],"report":[44],"through":[46],"explicit":[47,150],"skill":[48,53,91],"contracts.":[49],"A":[50,88],"dedicated":[51],"retrieval":[52,132,154],"rewrites":[54],"user":[55],"requests":[56],"into":[57],"material-specific":[58],"search":[59],"intents,":[60],"queries":[61,82],"curated":[63],"index":[64],"of":[65,113,143],"more":[66],"than":[67],"300,000":[68],"papers":[69],"the":[71,135],"Journal":[72],"Citation":[73],"Reports":[74],"Metallurgy":[75],"Metallurgical":[77],"Engineering":[78],"category,":[79],"reformulates":[81],"when":[83],"initial":[84],"evidence":[85],"is":[86],"insufficient.":[87],"separate":[89],"report-generation":[90],"parses":[92],"full-text":[93],"PDFs":[94],"produce":[96],"structured":[97],"per-paper":[98],"analytical":[99,117],"reports":[100],"cross-paper":[102],"summaries.":[103],"In":[104],"blind":[106],"evaluation":[107],"on":[108],"40":[109],"materials-science":[110],"questions,":[111],"half":[112],"which":[114],"required":[115],"deep":[116],"reasoning,":[118],"AlphaAgent":[119],"substantially":[120],"outperformed":[121],"baseline":[123],"system":[124],"matched":[125],"for":[126,163],"underlying":[127],"model,":[128],"document":[129],"index,":[130],"scale,":[133],"with":[134],"largest":[136],"gains":[137],"in":[138],"mechanistic":[139],"explanation":[140],"awareness":[142],"credibility":[144],"boundaries.":[145],"These":[146],"results":[147],"indicate":[148],"task":[151],"separation,":[152],"refined":[153],"intent,":[155],"evidence-aware":[157],"improve":[159],"large-language-model-based":[160],"materials":[164],"research.":[165]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2026-07-25T00:00:00"}