{"id":"https://openalex.org/W4417224607","doi":"https://doi.org/10.48550/arxiv.2504.00255","title":"SciReplicate-Bench: Benchmarking LLMs in Agent-driven Algorithmic Reproduction from Research Papers","display_name":"SciReplicate-Bench: Benchmarking LLMs in Agent-driven Algorithmic Reproduction from Research Papers","publication_year":2025,"publication_date":"2025-03-31","ids":{"openalex":"https://openalex.org/W4417224607","doi":"https://doi.org/10.48550/arxiv.2504.00255"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2504.00255","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2504.00255","pdf_url":"https://arxiv.org/pdf/2504.00255","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","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2504.00255","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5032134059","display_name":"Yanzheng Xiang","orcid":"https://orcid.org/0009-0000-0405-3327","observed_orcids":["https://orcid.org/0009-0000-0405-3327","https://orcid.org/0000-0002-3395-9766"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiang, Yanzheng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070326893","display_name":"Hanqi Yan","orcid":"https://orcid.org/0000-0001-5034-4520","observed_orcids":["https://orcid.org/0000-0001-5034-4520"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yan, Hanqi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102543278","display_name":"Shuyin Ouyang","orcid":"https://orcid.org/0009-0007-0056-3101","observed_orcids":["https://orcid.org/0009-0007-0056-3101"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ouyang, Shuyin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125549970","display_name":"Lin Gui","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gui, Lin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":null,"display_name":"He, Yulan","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"He, Yulan","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":true,"cited_by_count":1,"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/T10260","display_name":"Software Engineering Research","score":0.9804999828338623,"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"}},"topics":[{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":0.9804999828338623,"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"}},{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.014399999752640724,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.0007999999797903001,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/large-language-models","display_name":"large language models","score":0.8209999799728394},{"id":"https://openalex.org/keywords/reasoning-graphs","display_name":"reasoning graphs","score":0.6830000281333923},{"id":"https://openalex.org/keywords/execution-accuracy","display_name":"execution accuracy","score":0.6790000200271606},{"id":"https://openalex.org/keywords/benchmark","display_name":"benchmark","score":0.5569999814033508}],"concepts":[{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.7631000280380249},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7608000040054321},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6496000289916992},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.592199981212616},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.5473999977111816},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.4341000020503998},{"id":"https://openalex.org/C81669768","wikidata":"https://www.wikidata.org/wiki/Q2359161","display_name":"Precision and recall","level":2,"score":0.4147999882698059},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4074000120162964},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.39800000190734863},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.37779998779296875},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.3750999867916107},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.36570000648498535},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.34450000524520874},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3409999907016754},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.32280001044273376},{"id":"https://openalex.org/C195344581","wikidata":"https://www.wikidata.org/wiki/Q2555318","display_name":"Automated reasoning","level":2,"score":0.2915000021457672},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.28769999742507935},{"id":"https://openalex.org/C2780762811","wikidata":"https://www.wikidata.org/wiki/Q1784941","display_name":"Cosine similarity","level":3,"score":0.2538999915122986}],"mesh":[],"locations_count":3,"locations":[{"id":"pmh:oai:arXiv.org:2504.00255","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2504.00255","pdf_url":"https://arxiv.org/pdf/2504.00255","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:kclpure.kcl.ac.uk:openaire/964a22fd-b90e-44e4-b6a6-3a01cf408dc0","doi":null,"is_oa":true,"landing_page_url":"https://kclpure.kcl.ac.uk/portal/files/352933625/1031_SciReplicate_Bench_Benchm.pdf","pdf_url":"https://kclpure.kcl.ac.uk/ws/files/352933625/1031_SciReplicate_Bench_Benchm.pdf","source":{"id":"https://openalex.org/S4306400216","display_name":"Research Portal (King's College London)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I183935753","host_organization_name":"King's College London","host_organization_lineage":["https://openalex.org/I183935753"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Xiang, Y, Yan, H, Ouyang, S, Gui, L & He, Y 2025, SciReplicate-Bench : Benchmarking LLMs in Agent-driven Algorithmic Reproduction from Research Papers. in Proceedings of the Conference on Language Modeling (COLM).","raw_type":"info:eu-repo/semantics/publishedVersion"},{"id":"doi:10.48550/arxiv.2504.00255","doi":"https://doi.org/10.48550/arxiv.2504.00255","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2504.00255","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":"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"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2504.00255","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2504.00255","pdf_url":"https://arxiv.org/pdf/2504.00255","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":[{"id":"https://openalex.org/G2577708131","display_name":"Turing AI Fellowship: Event-Centric Framework for Natural Language Understanding","funder_award_id":"EP/V020579/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G6382798043","display_name":"Turing AI Fellowship: Event-Centric Framework for Natural Language Understanding","funder_award_id":"EP/V020579/2","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"}],"funders":[{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W6979262165","https://openalex.org/W7120955969","https://openalex.org/W7220455017","https://openalex.org/W7128638839","https://openalex.org/W7202187487","https://openalex.org/W7214034969","https://openalex.org/W4414981968","https://openalex.org/W7137824411","https://openalex.org/W7165000826","https://openalex.org/W7204269323"],"abstract_inverted_index":{"This":[0],"study":[1],"evaluates":[2],"large":[3],"language":[4],"models":[5],"(LLMs)":[6],"in":[7,13,65],"generating":[8],"code":[9,126,191],"from":[10,28,60,92,101,125],"algorithm":[11,24,108,177],"descriptions":[12,178],"recent":[14],"NLP":[15,62],"papers.":[16],"The":[17,158],"task":[18],"requires":[19],"two":[20],"key":[21,180],"competencies:":[22],"(1)":[23],"comprehension:":[25],"synthesizing":[26],"information":[27],"papers":[29,63],"and":[30,37,43,70,94,103,120,128,139,152,190,194],"academic":[31],"literature":[32,93],"to":[33,182],"understand":[34],"implementation":[35,132],"logic,":[36],"(2)":[38],"coding":[39],"expertise:":[40],"identifying":[41],"dependencies":[42,100],"correctly":[44],"implementing":[45],"necessary":[46],"APIs.":[47],"To":[48,106],"facilitate":[49],"rigorous":[50],"evaluation,":[51],"we":[52,77,110,134,147],"introduce":[53,111],"SciReplicate-Bench,":[54,76],"a":[55,80,85,95],"benchmark":[56,189],"of":[57,84],"100":[58],"tasks":[59],"36":[61],"published":[64],"2024,":[66],"featuring":[67],"detailed":[68],"annotations":[69],"comprehensive":[71],"test":[72],"cases.":[73],"Building":[74],"on":[75],"propose":[78],"Sci-Reproducer,":[79],"dual-agent":[81],"framework":[82],"consisting":[83],"Paper":[86],"Agent":[87,97],"that":[88,98],"interprets":[89],"algorithmic":[90],"concepts":[91],"Code":[96],"retrieves":[99],"repositories":[102],"implements":[104],"solutions.":[105],"assess":[107],"understanding,":[109],"reasoning":[112,122,153],"graph":[113],"accuracy,":[114,137,166],"which":[115],"quantifies":[116],"similarity":[117],"between":[118],"generated":[119],"reference":[121],"graphs":[123],"derived":[124],"comments":[127],"structure.":[129],"For":[130],"evaluating":[131],"quality,":[133],"employ":[135],"execution":[136,165],"CodeBLEU,":[138],"repository":[140],"dependency/API":[141],"recall":[142],"metrics.":[143],"In":[144],"our":[145,188],"experiments,":[146],"evaluate":[148],"various":[149],"powerful":[150],"non-reasoning":[151],"LLMs":[154],"as":[155,179],"foundational":[156],"models.":[157],"best-performing":[159],"LLM":[160],"using":[161],"\\ModelName~achieves":[162],"only":[163],"39%":[164],"highlighting":[167],"the":[168],"benchmark's":[169],"difficulty.":[170],"Our":[171],"analysis":[172],"identifies":[173],"missing":[174],"or":[175],"inconsistent":[176],"barriers":[181],"successful":[183],"reproduction.":[184],"We":[185],"make":[186],"available":[187],"at":[192,197],"https://github.com/xyzCS/SciReplicate-Bench":[193],"project":[195],"homepage":[196],"https://xyzcs.github.io/scireplicate.github.io/.":[198]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-09-30T09:27:27.532063","created_date":"2025-10-10T00:00:00"}