{"id":"https://openalex.org/W4414804284","doi":"https://doi.org/10.48550/arxiv.2510.00069","title":"OIG-Bench: A Multi-Agent Annotated Benchmark for Multimodal One-Image Guides Understanding","display_name":"OIG-Bench: A Multi-Agent Annotated Benchmark for Multimodal One-Image Guides Understanding","publication_year":2025,"publication_date":"2025-09-29","ids":{"openalex":"https://openalex.org/W4414804284","doi":"https://doi.org/10.48550/arxiv.2510.00069"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2510.00069","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2510.00069","pdf_url":"https://arxiv.org/pdf/2510.00069","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/2510.00069","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5043459237","display_name":"Jiancong Xie","orcid":"https://orcid.org/0000-0001-9030-0709","observed_orcids":["https://orcid.org/0000-0001-9030-0709"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xie, Jiancong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100636785","display_name":"Wenjin Wang","orcid":"https://orcid.org/0000-0001-7832-5444","observed_orcids":["https://orcid.org/0000-0001-7832-5444"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Wenjin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Zhang, Zhuomeng","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Zhuomeng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077660070","display_name":"Zihan Liu","orcid":"https://orcid.org/0000-0003-3175-1889","observed_orcids":["https://orcid.org/0000-0003-3175-1889"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Zihan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5106613302","display_name":"Qi Liu","orcid":"https://orcid.org/0000-0001-5378-6404","observed_orcids":["https://orcid.org/0000-0001-5378-6404"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Qi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Feng, Ke","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Feng, Ke","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067395825","display_name":"Zixun Sun","orcid":"https://orcid.org/0000-0003-4125-1909","observed_orcids":["https://orcid.org/0000-0003-4125-1909"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sun, Zixun","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5023539493","display_name":"Yuedong Yang","orcid":"https://orcid.org/0000-0002-6782-2813","observed_orcids":["https://orcid.org/0000-0002-6782-2813"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yang, Yuedong","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/T11714","display_name":"Multimodal Machine Learning Applications","score":1.0,"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"}},"topics":[{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":1.0,"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"}},{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.0,"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"}},{"id":"https://openalex.org/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.0,"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/multimodal-large-language-models","display_name":"multimodal large language models","score":0.9890000224113464},{"id":"https://openalex.org/keywords/image-text-pairs","display_name":"image-text pairs","score":0.6909999847412109},{"id":"https://openalex.org/keywords/image-captioning","display_name":"image captioning","score":0.9240000247955322},{"id":"https://openalex.org/keywords/model-evaluation","display_name":"model evaluation","score":0.4050000011920929}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8001000285148621},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.6990000009536743},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5976999998092651},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.5605999827384949},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4893999993801117},{"id":"https://openalex.org/C2780992000","wikidata":"https://www.wikidata.org/wiki/Q17016113","display_name":"Generator (circuit theory)","level":3,"score":0.46970000863075256},{"id":"https://openalex.org/C63882131","wikidata":"https://www.wikidata.org/wiki/Q17122954","display_name":"Strengths and weaknesses","level":2,"score":0.40470001101493835},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.4043000042438507},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.40059998631477356},{"id":"https://openalex.org/C199579030","wikidata":"https://www.wikidata.org/wiki/Q2851778","display_name":"Automatic image annotation","level":4,"score":0.38199999928474426},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.3513000011444092},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.35030001401901245},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.33480000495910645},{"id":"https://openalex.org/C62230096","wikidata":"https://www.wikidata.org/wiki/Q275969","display_name":"Crowdsourcing","level":2,"score":0.3280999958515167},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.31029999256134033},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.30230000615119934},{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.2896000146865845},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.28610000014305115},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.28540000319480896},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.25850000977516174},{"id":"https://openalex.org/C2985727698","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Semantic annotation","level":3,"score":0.25760000944137573},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.2540000081062317}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2510.00069","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2510.00069","pdf_url":"https://arxiv.org/pdf/2510.00069","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.2510.00069","doi":"https://doi.org/10.48550/arxiv.2510.00069","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2510.00069","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":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2510.00069","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2510.00069","pdf_url":"https://arxiv.org/pdf/2510.00069","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":[],"sustainable_development_goals_aurora":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Recent":[0],"advances":[1],"in":[2,19,90,103,149,181],"Multimodal":[3],"Large":[4],"Language":[5],"Models":[6],"(MLLMs)":[7],"have":[8,110],"demonstrated":[9],"impressive":[10],"capabilities.":[11],"However,":[12],"evaluating":[13],"their":[14],"capacity":[15],"for":[16,42,49,198],"human-like":[17],"understanding":[18,73,151],"One-Image":[20,25,71],"Guides":[21,26],"remains":[22],"insufficiently":[23],"explored.":[24],"are":[27,46,203],"a":[28,66,86,112,189,195],"visual":[29],"format":[30],"combining":[31],"text,":[32],"imagery,":[33],"and":[34,39,52,60,122,152,194],"symbols":[35],"to":[36,96,161],"present":[37,64],"reorganized":[38],"structured":[40],"information":[41],"easier":[43],"comprehension,":[44],"which":[45,91],"specifically":[47],"designed":[48],"human":[50,58],"viewing":[51],"inherently":[53],"embody":[54],"the":[55,79,131,134,173],"characteristics":[56],"of":[57,81,115,141],"perception":[59],"understanding.":[61],"Here,":[62],"we":[63,84,109,169],"OIG-Bench,":[65,108],"comprehensive":[67,113],"benchmark":[68],"focused":[69],"on":[70],"Guide":[72],"across":[74],"diverse":[75],"domains.":[76],"To":[77],"reduce":[78],"cost":[80],"manual":[82],"annotation,":[83],"developed":[85],"semi-automated":[87],"annotation":[88,176],"pipeline":[89],"multiple":[92],"intelligent":[93],"agents":[94],"collaborate":[95],"generate":[97],"preliminary":[98],"image":[99,182,191],"descriptions,":[100],"assisting":[101],"humans":[102],"constructing":[104],"image-text":[105],"pairs.":[106],"With":[107],"conducted":[111],"evaluation":[114],"29":[116],"state-of-the-art":[117],"MLLMs,":[118],"including":[119],"both":[120,188],"proprietary":[121],"open-source":[123],"models.":[124],"The":[125],"results":[126],"show":[127],"that":[128,156,172],"Qwen2.5-VL-72B":[129],"performs":[130],"best":[132],"among":[133],"evaluated":[135],"models,":[136],"with":[137],"an":[138],"overall":[139],"accuracy":[140],"77%.":[142],"Nevertheless,":[143],"all":[144,179],"models":[145],"exhibit":[146],"notable":[147],"weaknesses":[148],"semantic":[150],"logical":[153],"reasoning,":[154],"indicating":[155],"current":[157],"MLLMs":[158,180],"still":[159],"struggle":[160],"accurately":[162],"interpret":[163],"complex":[164],"visual-text":[165],"relationships.":[166],"In":[167],"addition,":[168],"also":[170],"demonstrate":[171],"proposed":[174],"multi-agent":[175],"system":[177],"outperforms":[178],"captioning,":[183],"highlighting":[184],"its":[185],"potential":[186],"as":[187],"high-quality":[190],"description":[192],"generator":[193],"valuable":[196],"tool":[197],"future":[199],"dataset":[200],"construction.":[201],"Datasets":[202],"available":[204],"at":[205],"https://github.com/XiejcSYSU/OIG-Bench.":[206]},"counts_by_year":[],"updated_date":"2026-10-16T09:59:22.235173","created_date":"2025-10-10T00:00:00"}