{"id":"https://openalex.org/W7225645152","doi":"https://doi.org/10.18653/2026.aacl-long.202","title":"HorizonBench: Evaluating Ideation Agents on Future Scientific Discoveries","display_name":"HorizonBench: Evaluating Ideation Agents on Future Scientific Discoveries","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7225645152","doi":"https://doi.org/10.18653/2026.aacl-long.202"},"language":"en","primary_location":{"id":"doi:10.18653/2026.aacl-long.202","doi":"https://doi.org/10.18653/2026.aacl-long.202","is_oa":true,"landing_page_url":"https://doi.org/10.18653/2026.aacl-long.202","pdf_url":"https://aclanthology.org/2026.aacl-long.202.pdf","source":{"id":"https://openalex.org/S7407087740","display_name":"International Joint Conference on Natural Language Processing and Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics (IJCNLP-AACL)","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 15th International Joint Conference on Natural Language Processing and the 5th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://aclanthology.org/2026.aacl-long.202.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5104435539","display_name":"Markus Flicke","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4401726832","display_name":"T\u00fcbingen AI Center","ror":"https://ror.org/0107nyd78","country_code":"DE","type":"education","lineage":["https://openalex.org/I149899117","https://openalex.org/I4210135521","https://openalex.org/I4401726832","https://openalex.org/I8087733"]},{"id":"https://openalex.org/I8087733","display_name":"University of T\u00fcbingen","ror":"https://ror.org/03a1kwz48","country_code":"DE","type":"education","lineage":["https://openalex.org/I8087733"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Markus Flicke","raw_affiliation_strings":["T\u00fcbingen AI Center ,","University of T\u00fcbingen ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"T\u00fcbingen AI Center ,","institution_ids":["https://openalex.org/I4401726832"]},{"raw_affiliation_string":"University of T\u00fcbingen ,","institution_ids":["https://openalex.org/I8087733"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5161305496","display_name":"Haoyu He","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4401726832","display_name":"T\u00fcbingen AI Center","ror":"https://ror.org/0107nyd78","country_code":"DE","type":"education","lineage":["https://openalex.org/I149899117","https://openalex.org/I4210135521","https://openalex.org/I4401726832","https://openalex.org/I8087733"]},{"id":"https://openalex.org/I8087733","display_name":"University of T\u00fcbingen","ror":"https://ror.org/03a1kwz48","country_code":"DE","type":"education","lineage":["https://openalex.org/I8087733"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Haoyu He","raw_affiliation_strings":["T\u00fcbingen AI Center ,","University of T\u00fcbingen ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"T\u00fcbingen AI Center ,","institution_ids":["https://openalex.org/I4401726832"]},{"raw_affiliation_string":"University of T\u00fcbingen ,","institution_ids":["https://openalex.org/I8087733"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041189908","display_name":"Kashyap Chitta","orcid":"https://orcid.org/0000-0002-3891-3230","observed_orcids":["https://orcid.org/0000-0002-3891-3230"]},"institutions":[{"id":"https://openalex.org/I4405263145","display_name":"ELLIS Institute T\u00fcbingen","ror":"https://ror.org/036z3g533","country_code":"DE","type":"other","lineage":["https://openalex.org/I4405263145"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Kashyap Chitta","raw_affiliation_strings":["ELLIS Institute T\u00fcbingen ,","KE : SAI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ELLIS Institute T\u00fcbingen ,","institution_ids":["https://openalex.org/I4405263145"]},{"raw_affiliation_string":"KE : SAI","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5161310381","display_name":"Yong Cao","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4401726832","display_name":"T\u00fcbingen AI Center","ror":"https://ror.org/0107nyd78","country_code":"DE","type":"education","lineage":["https://openalex.org/I149899117","https://openalex.org/I4210135521","https://openalex.org/I4401726832","https://openalex.org/I8087733"]},{"id":"https://openalex.org/I8087733","display_name":"University of T\u00fcbingen","ror":"https://ror.org/03a1kwz48","country_code":"DE","type":"education","lineage":["https://openalex.org/I8087733"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Yong Cao","raw_affiliation_strings":["T\u00fcbingen AI Center ,","University of T\u00fcbingen ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"T\u00fcbingen AI Center ,","institution_ids":["https://openalex.org/I4401726832"]},{"raw_affiliation_string":"University of T\u00fcbingen ,","institution_ids":["https://openalex.org/I8087733"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5161326778","display_name":"Andreas Geiger","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Andreas Geiger","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"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":0.0,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4466","last_page":"4479"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.6333000063896179,"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"}},"topics":[{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.6333000063896179,"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/T10286","display_name":"Information Retrieval and Search Behavior","score":0.07819999754428864,"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/T10203","display_name":"Recommender Systems and Techniques","score":0.03799999877810478,"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/large-language-models","display_name":"large language models","score":0.6299999952316284},{"id":"https://openalex.org/keywords/scientific-hypothesis-generation","display_name":"scientific hypothesis generation","score":0.34200000762939453}],"concepts":[{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.47099998593330383},{"id":"https://openalex.org/C55587333","wikidata":"https://www.wikidata.org/wiki/Q1133029","display_name":"Engineering ethics","level":1,"score":0.34540000557899475},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.3000999987125397},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.29510000348091125},{"id":"https://openalex.org/C170477896","wikidata":"https://www.wikidata.org/wiki/Q17039022","display_name":"Ideation","level":2,"score":0.2946999967098236},{"id":"https://openalex.org/C539667460","wikidata":"https://www.wikidata.org/wiki/Q2414942","display_name":"Management science","level":1,"score":0.26499998569488525},{"id":"https://openalex.org/C195732255","wikidata":"https://www.wikidata.org/wiki/Q981008","display_name":"Sociology of scientific knowledge","level":2,"score":0.25130000710487366},{"id":"https://openalex.org/C75630572","wikidata":"https://www.wikidata.org/wiki/Q538904","display_name":"Applied psychology","level":1,"score":0.2508000135421753},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.23909999430179596},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2282000035047531}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/2026.aacl-long.202","doi":"https://doi.org/10.18653/2026.aacl-long.202","is_oa":true,"landing_page_url":"https://doi.org/10.18653/2026.aacl-long.202","pdf_url":"https://aclanthology.org/2026.aacl-long.202.pdf","source":{"id":"https://openalex.org/S7407087740","display_name":"International Joint Conference on Natural Language Processing and Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics (IJCNLP-AACL)","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 15th International Joint Conference on Natural Language Processing and the 5th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/2026.aacl-long.202","doi":"https://doi.org/10.18653/2026.aacl-long.202","is_oa":true,"landing_page_url":"https://doi.org/10.18653/2026.aacl-long.202","pdf_url":"https://aclanthology.org/2026.aacl-long.202.pdf","source":{"id":"https://openalex.org/S7407087740","display_name":"International Joint Conference on Natural Language Processing and Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics (IJCNLP-AACL)","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 15th International Joint Conference on Natural Language Processing and the 5th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7225645152.pdf","grobid_xml":"https://content.openalex.org/works/W7225645152.grobid-xml"},"referenced_works_count":18,"referenced_works":["https://openalex.org/W4385681674","https://openalex.org/W4402952666","https://openalex.org/W4403707291","https://openalex.org/W4412875478","https://openalex.org/W4412889754","https://openalex.org/W4414581606","https://openalex.org/W4414827381","https://openalex.org/W4415062263","https://openalex.org/W4415950435","https://openalex.org/W4417167277","https://openalex.org/W4417224607","https://openalex.org/W6891935834","https://openalex.org/W6948133953","https://openalex.org/W6948437691","https://openalex.org/W6966977675","https://openalex.org/W7127187793","https://openalex.org/W7138446791","https://openalex.org/W7138448176"],"related_works":["https://openalex.org/W7140113567","https://openalex.org/W7223955021","https://openalex.org/W7224311831","https://openalex.org/W4411119411","https://openalex.org/W4416034681","https://openalex.org/W4412886834","https://openalex.org/W7224376710","https://openalex.org/W7223709866","https://openalex.org/W4412889809","https://openalex.org/W4401042401"],"abstract_inverted_index":{"As":[0],"ideation":[1,45,47,83,98,158],"agents":[2,48,84,135,181],"become":[3],"more":[4],"capable,":[5],"evaluating":[6],"them":[7],"poses":[8],"an":[9,31,127,157,189],"increasing":[10],"challenge.LLM-as-a-judge":[11],"approaches":[12],"are":[13,54],"brittle":[14],"and":[15,22,50,60,166,188],"gameable,":[16],"while":[17],"human":[18,102],"evaluation":[19,32],"is":[20],"expensive":[21],"hard":[23],"to":[24,57,101],"scale.To":[25],"address":[26],"this,":[27],"we":[28,74,154],"introduce":[29],"HorizonBench,":[30,73],"methodology":[33],"leveraging":[34],"future":[35],"scientific":[36],"discoveries.HorizonBench":[37],"uses":[38],"published":[39,71,82],"papers":[40,163],"as":[41,126],"ground":[42],"truth":[43],"for":[44,149],"quality.Specifically,":[46],"pretraining":[49],"context":[51],"retrieval":[52,138],"data":[53],"strictly":[55],"constrained":[56],"pre-publication":[58],"knowledge,":[59],"scored":[61],"on":[62,151,182],"how":[63],"well":[64],"their":[65],"predicted":[66],"ideas":[67],"align":[68],"with":[69,108],"subsequently":[70],"work.Using":[72],"conduct":[75],"the":[76,123,143,146,169,176,185],"first":[77],"unified":[78],"comparison":[79],"of":[80,145,175,193],"five":[81],"across":[85],"multiple":[86],"frontier":[87],"model":[88],"backbones.We":[89],"verify":[90],"that":[91,120,136,160],"our":[92],"soft":[93],"recall":[94],"metric":[95],"captures":[96],"meaningful":[97],"quality":[99],"aligned":[100],"judgement":[103],"via":[104],"a":[105,114,117],"user":[106],"study":[107],"51":[109],"domain":[110],"experts.We":[111],"then":[112],"uncover":[113],"surprising":[115],"finding:":[116],"na\u00efve":[118],"baseline":[119],"receives":[121],"only":[122],"research":[124,147,170],"goal":[125,148,171],"input":[128],"consistently":[129],"matches":[130],"or":[131,139],"outperforms":[132,178],"all":[133,179],"existing":[134],"require":[137],"multi-step":[140],"reasoning,":[141],"highlighting":[142],"importance":[144],"ideation.Based":[150],"this":[152],"result,":[153],"develop":[155],"OSCAR,":[156],"agent":[159],"distils":[161],"retrieved":[162],"into":[164],"insights":[165],"explicitly":[167],"reinforces":[168],"in":[172],"each":[173],"step":[174],"pipeline.OSCAR":[177],"evaluated":[180],"HorizonBench.We":[183],"publish":[184],"code":[186],"1":[187],"online":[190],"version":[191],"2":[192],"HorizonBench.":[194]},"counts_by_year":[],"updated_date":"2026-11-11T12:16:26.678958","created_date":"2026-11-10T00:00:00"}