{"id":"https://openalex.org/W7137959380","doi":"https://doi.org/10.1609/aaai.v40i13.38097","title":"DocR1: Evidence Page-Guided GRPO for Multi-Page Document Understanding","display_name":"DocR1: Evidence Page-Guided GRPO for Multi-Page Document Understanding","publication_year":2026,"publication_date":"2026-03-14","ids":{"openalex":"https://openalex.org/W7137959380","doi":"https://doi.org/10.1609/aaai.v40i13.38097"},"language":null,"primary_location":{"id":"doi:10.1609/aaai.v40i13.38097","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i13.38097","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/38097/42059","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://ojs.aaai.org/index.php/AAAI/article/download/38097/42059","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101368175","display_name":"Junyu Xiong","orcid":null},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Junyu Xiong","raw_affiliation_strings":["University of Science and Technology of China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129658573","display_name":"Yonghui Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yonghui Wang","raw_affiliation_strings":["University of Science and Technology of China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129696020","display_name":"Weichao Zhao","orcid":null},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weichao Zhao","raw_affiliation_strings":["University of Science and Technology of China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129733154","display_name":"Chenyu Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chenyu Liu","raw_affiliation_strings":["iFLYTEK Research"],"affiliations":[{"raw_affiliation_string":"iFLYTEK Research","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129719849","display_name":"Bing Yin","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bing Yin","raw_affiliation_strings":["iFLYTEK Research"],"affiliations":[{"raw_affiliation_string":"iFLYTEK Research","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129700574","display_name":"Wengang Zhou","orcid":null},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wengang Zhou","raw_affiliation_strings":["University of Science and Technology of China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5129675638","display_name":"Houqiang Li","orcid":null},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Houqiang Li","raw_affiliation_strings":["University of Science and Technology of China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China","institution_ids":["https://openalex.org/I126520041"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5101368175"],"corresponding_institution_ids":["https://openalex.org/I126520041"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.21567164,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"40","issue":"13","first_page":"11178","last_page":"11186"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.774399995803833,"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":0.774399995803833,"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/T10028","display_name":"Topic Modeling","score":0.10540000349283218,"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/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.026900000870227814,"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/pipeline","display_name":"Pipeline (software)","score":0.621399998664856},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5713000297546387},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.546999990940094},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.5317000150680542},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.5062999725341797},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.4846999943256378},{"id":"https://openalex.org/keywords/comprehension","display_name":"Comprehension","score":0.45010000467300415},{"id":"https://openalex.org/keywords/mechanism","display_name":"Mechanism (biology)","score":0.3776000142097473}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7810999751091003},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.621399998664856},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5713000297546387},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.546999990940094},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.5317000150680542},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.5062999725341797},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5059000253677368},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.4846999943256378},{"id":"https://openalex.org/C511192102","wikidata":"https://www.wikidata.org/wiki/Q5156948","display_name":"Comprehension","level":2,"score":0.45010000467300415},{"id":"https://openalex.org/C89611455","wikidata":"https://www.wikidata.org/wiki/Q6804646","display_name":"Mechanism (biology)","level":2,"score":0.3776000142097473},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.3637999892234802},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.35429999232292175},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3506999909877777},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.3379000127315521},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.3368000090122223},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.3280999958515167},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3264999985694885},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.3102000057697296},{"id":"https://openalex.org/C2992562121","wikidata":"https://www.wikidata.org/wiki/Q3817808","display_name":"Scientific reasoning","level":2,"score":0.2833999991416931},{"id":"https://openalex.org/C195344581","wikidata":"https://www.wikidata.org/wiki/Q2555318","display_name":"Automated reasoning","level":2,"score":0.27720001339912415},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.27649998664855957},{"id":"https://openalex.org/C77967617","wikidata":"https://www.wikidata.org/wiki/Q4677561","display_name":"Active learning (machine learning)","level":2,"score":0.26109999418258667},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.2551000118255615}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1609/aaai.v40i13.38097","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i13.38097","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/38097/42059","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1609/aaai.v40i13.38097","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i13.38097","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/38097/42059","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.6341774463653564,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7137959380.pdf","grobid_xml":"https://content.openalex.org/works/W7137959380.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Understanding":[0],"multi-page":[1,41,151],"documents":[2],"poses":[3],"a":[4,56,72,92,98,117,126,139],"significant":[5],"challenge":[6],"for":[7,32],"multimodal":[8],"large":[9],"language":[10],"models":[11],"(MLLMs),":[12],"as":[13],"it":[14],"requires":[15],"fine-grained":[16],"visual":[17],"comprehension":[18],"and":[19,97,124],"multi-hop":[20],"reasoning":[21,35,74],"across":[22,138],"pages.":[23],"While":[24],"prior":[25],"work":[26],"has":[27],"explored":[28],"reinforcement":[29],"learning":[30,100],"(RL)":[31],"enhancing":[33],"advanced":[34],"in":[36],"MLLMs,":[37],"its":[38],"application":[39],"to":[40,79],"document":[42],"understanding":[43],"remains":[44],"underexplored.":[45],"In":[46],"this":[47,110],"paper,":[48],"we":[49,90,112],"introduce":[50],"DocR1,":[51],"an":[52,66],"MLLM":[53],"trained":[54],"with":[55,106,121,128],"novel":[57],"RL":[58],"framework,":[59],"Evidence":[60],"Page-Guided":[61],"GRPO":[62],"(EviGRPO).":[63],"EviGRPO":[64],"incorporates":[65],"evidence-aware":[67],"reward":[68],"mechanism":[69],"that":[70,102,145],"promotes":[71],"coarse-to-fine":[73],"strategy,":[75],"guiding":[76],"the":[77],"model":[78],"first":[80],"retrieve":[81],"relevant":[82],"pages":[83],"before":[84],"generating":[85],"answers.":[86],"To":[87],"support":[88],"this,":[89],"design":[91],"rigorous":[93],"two-stage":[94],"annotation":[95],"pipeline":[96],"curriculum":[99],"strategy":[101],"enables":[103],"effective":[104],"training":[105,119],"limited":[107],"supervision.":[108],"Using":[109],"pipeline,":[111],"construct":[113],"two":[114],"datasets:":[115],"EviBench,":[116],"high-quality":[118],"set":[120],"4.8k":[122],"examples,":[123],"ArxivFullQA,":[125],"benchmark":[127],"8.6k":[129],"QA":[130],"examples":[131],"over":[132],"full":[133],"scientific":[134],"papers.":[135],"Extensive":[136],"experiments":[137],"wide":[140],"range":[141],"of":[142],"benchmarks":[143],"demonstrate":[144],"DocR1":[146],"achieves":[147],"state-of-the-art":[148],"performance":[149],"on":[150,157],"tasks":[152],"while":[153],"maintaining":[154],"strong":[155],"results":[156],"single-page":[158],"benchmarks.":[159]},"counts_by_year":[],"updated_date":"2026-03-20T20:47:17.329874","created_date":"2026-03-18T00:00:00"}