{"id":"https://openalex.org/W7160941411","doi":"https://doi.org/10.48550/arxiv.2605.09100","title":"GRC: Unifying Reasoning-Driven Generation, Retrieval and Compression","display_name":"GRC: Unifying Reasoning-Driven Generation, Retrieval and Compression","publication_year":2026,"publication_date":"2026-05-09","ids":{"openalex":"https://openalex.org/W7160941411","doi":"https://doi.org/10.48550/arxiv.2605.09100"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2605.09100","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.09100","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":null,"license_id":null,"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.2605.09100","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100314856","display_name":"Zhongtao Miao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Miao, Zhongtao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135949099","display_name":"Qiyu Wu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wu, Qiyu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5064113904","display_name":"Yoshimasa Tsuruoka","orcid":"https://orcid.org/0000-0002-0707-1077"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tsuruoka, Yoshimasa","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/T10028","display_name":"Topic Modeling","score":0.5863999724388123,"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":0.5863999724388123,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.14569999277591705,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.12449999898672104,"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/inference","display_name":"Inference","score":0.636900007724762},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.5845999717712402},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.4758000075817108},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.46560001373291016},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.4431999921798706},{"id":"https://openalex.org/keywords/flexibility","display_name":"Flexibility (engineering)","score":0.4350000023841858},{"id":"https://openalex.org/keywords/software-deployment","display_name":"Software deployment","score":0.4214000105857849},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.38260000944137573}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8628000020980835},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.636900007724762},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5845999717712402},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4943000078201294},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.4758000075817108},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.46560001373291016},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.4431999921798706},{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.4350000023841858},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.4214000105857849},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3984000086784363},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.38260000944137573},{"id":"https://openalex.org/C180016635","wikidata":"https://www.wikidata.org/wiki/Q2712821","display_name":"Compression (physics)","level":2,"score":0.3790999948978424},{"id":"https://openalex.org/C78548338","wikidata":"https://www.wikidata.org/wiki/Q2493","display_name":"Data compression","level":2,"score":0.3734000027179718},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.3662000000476837},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.3596000075340271},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.3513999879360199},{"id":"https://openalex.org/C115537543","wikidata":"https://www.wikidata.org/wiki/Q165596","display_name":"Cache","level":2,"score":0.33709999918937683},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.33320000767707825},{"id":"https://openalex.org/C25797200","wikidata":"https://www.wikidata.org/wiki/Q828137","display_name":"Compression ratio","level":3,"score":0.31369999051094055},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.27959999442100525},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.2766999900341034},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.272599995136261},{"id":"https://openalex.org/C94835093","wikidata":"https://www.wikidata.org/wiki/Q3113333","display_name":"Data compression ratio","level":5,"score":0.27230000495910645}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2605.09100","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.09100","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2605.09100","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.09100","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Text":[0],"embedding":[1,225],"and":[2,24,33,42,48,64,78,83,129,133,153,163,202,211,226],"generative":[3,196],"tasks":[4,44,67,228],"are":[5],"usually":[6],"trained":[7,100],"separately":[8],"based":[9],"on":[10,192,215],"large":[11,19],"language":[12],"models":[13,101],"(LLMs)":[14],"nowadays.":[15],"This":[16,118],"causes":[17],"a":[18,31,79,89,107,145,154],"amount":[20],"of":[21,187,208],"training":[22,90],"cost":[23],"deployment":[25,123],"effort.":[26],"Context":[27],"compression":[28,66,227],"is":[29,37,170],"also":[30,177],"challenging":[32],"pressing":[34],"task,":[35],"which":[36],"vital":[38],"to":[39,57,182],"reasoning-driven":[40,59,223],"generation,":[41,60,160,224],"agentic":[43],"requiring":[45],"long":[46],"context":[47,65],"continual":[49],"learning.":[50],"In":[51],"this":[52,141],"paper,":[53],"we":[54,87],"explore":[55],"how":[56],"unify":[58],"reasoning-enhanced":[61],"text":[62,149],"representation":[63],"in":[68,106],"one":[69],"forward":[70,109],"pass":[71,110],"for":[72,125,148],"LLMs.":[73],"Through":[74],"meta":[75],"latent":[76,158],"tokens":[77],"unified":[80,218],"generative,":[81],"representative":[82],"compressive":[84],"tuning":[85],"approach,":[86],"propose":[88,178],"framework":[91,142],"named":[92],"GRC":[93],"that":[94,220],"bridges":[95],"the":[96,122,173,185,206,216],"three":[97,104,134],"tasks.":[98],"The":[99],"can":[102,221],"accomplish":[103],"objectives":[105],"single":[108],"while":[111],"maintaining":[112],"modular,":[113],"LEGO-style":[114],"flexibility":[115],"during":[116,138],"inference.":[117],"design":[119,143],"greatly":[120],"reduces":[121],"effort":[124],"retrieval-augmented":[126],"generation":[127,156],"(RAG)":[128],"achieves":[130],"efficient":[131],"inference":[132,186],"times":[135],"data":[136],"utilization":[137],"training.":[139],"Furthermore,":[140],"enables":[144],"new":[146,155],"paradigm":[147],"embedding:":[150],"self-reason-latent":[151],"embeds,":[152],"paradigm,":[157],"memory-augmented":[159],"where":[161],"compressed":[162],"internalized":[164],"KV":[165],"cache":[166],"with":[167],"O(1)":[168],"length":[169],"used":[171],"as":[172],"updatable":[174],"memory.":[175],"We":[176],"hybrid":[179],"paged":[180],"attention":[181],"speed":[183],"up":[184],"our":[188,209],"models.":[189],"Extensive":[190],"experiments":[191],"reasoning-intensive":[193],"retrieval":[194],"benchmarks,":[195],"tasks,":[197],"document":[198],"compression,":[199],"latency":[200],"evaluation,":[201],"RAG":[203],"settings":[204],"demonstrate":[205],"effectiveness":[207],"method":[210],"may":[212],"shed":[213],"light":[214],"truly":[217],"model":[219],"handle":[222],"seamlessly.":[229]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2026-05-13T00:00:00"}