{"id":"https://openalex.org/W4416243748","doi":"https://doi.org/10.48550/arxiv.2508.08816","title":"Efficient Agent: Optimizing Planning Capability for Multimodal Retrieval Augmented Generation","display_name":"Efficient Agent: Optimizing Planning Capability for Multimodal Retrieval Augmented Generation","publication_year":2025,"publication_date":"2025-08-12","ids":{"openalex":"https://openalex.org/W4416243748","doi":"https://doi.org/10.48550/arxiv.2508.08816"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2508.08816","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2508.08816","pdf_url":"https://arxiv.org/pdf/2508.08816","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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"},"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2508.08816","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102902110","display_name":"Yuechen Wang","orcid":"https://orcid.org/0000-0001-6098-6164"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Wang, Yuechen","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113062347","display_name":"Yuming Qiao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qiao, Yuming","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101525319","display_name":"Dan Meng","orcid":"https://orcid.org/0000-0003-1980-9283"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Meng, Dan","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103205273","display_name":"Jun Yang","orcid":"https://orcid.org/0000-0002-2124-0869"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yang, Jun","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007720098","display_name":"H. Lu","orcid":"https://orcid.org/0000-0001-6332-2785"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lu, Haonan","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100433331","display_name":"Zhenyu Yang","orcid":"https://orcid.org/0000-0002-8199-2720"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yang, Zhenyu","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5100441861","display_name":"Xudong Zhang","orcid":"https://orcid.org/0000-0003-1896-4898"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Xudong","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5102902110"],"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":0.5005000233650208,"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":0.5005000233650208,"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":0.34850001335144043,"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/T12031","display_name":"Speech and dialogue systems","score":0.03550000116229057,"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/key","display_name":"Key (lock)","score":0.6388999819755554},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6255999803543091},{"id":"https://openalex.org/keywords/relevance","display_name":"Relevance (law)","score":0.6154999732971191},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5906000137329102},{"id":"https://openalex.org/keywords/planner","display_name":"Planner","score":0.5360000133514404},{"id":"https://openalex.org/keywords/bridge","display_name":"Bridge (graph theory)","score":0.4165000021457672},{"id":"https://openalex.org/keywords/multimodality","display_name":"Multimodality","score":0.41449999809265137}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.795199990272522},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.6388999819755554},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6255999803543091},{"id":"https://openalex.org/C158154518","wikidata":"https://www.wikidata.org/wiki/Q7310970","display_name":"Relevance (law)","level":2,"score":0.6154999732971191},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5906000137329102},{"id":"https://openalex.org/C2776999362","wikidata":"https://www.wikidata.org/wiki/Q2349274","display_name":"Planner","level":2,"score":0.5360000133514404},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4961000084877014},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.43059998750686646},{"id":"https://openalex.org/C100776233","wikidata":"https://www.wikidata.org/wiki/Q2532492","display_name":"Bridge (graph theory)","level":2,"score":0.4165000021457672},{"id":"https://openalex.org/C2780910867","wikidata":"https://www.wikidata.org/wiki/Q1952416","display_name":"Multimodality","level":2,"score":0.41449999809265137},{"id":"https://openalex.org/C2776505523","wikidata":"https://www.wikidata.org/wiki/Q4785468","display_name":"Plan (archaeology)","level":2,"score":0.40049999952316284},{"id":"https://openalex.org/C180591056","wikidata":"https://www.wikidata.org/wiki/Q654437","display_name":"Executor","level":2,"score":0.3813000023365021},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.334199994802475},{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.3158999979496002},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.2782999873161316},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.26930001378059387},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.26600000262260437},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.26589998602867126},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.25600001215934753},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.2551000118255615},{"id":"https://openalex.org/C2778473407","wikidata":"https://www.wikidata.org/wiki/Q1459574","display_name":"Compendium","level":2,"score":0.25}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2508.08816","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2508.08816","pdf_url":"https://arxiv.org/pdf/2508.08816","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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.2508.08816","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2508.08816","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2508.08816","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2508.08816","pdf_url":"https://arxiv.org/pdf/2508.08816","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Multimodal":[0,16],"Retrieval-Augmented":[1],"Generation":[2],"(mRAG)":[3],"has":[4],"emerged":[5],"as":[6],"a":[7,58,72,86],"promising":[8],"solution":[9],"to":[10,62,79],"address":[11],"the":[12,104,112],"temporal":[13],"limitations":[14],"of":[15,41,107],"Large":[17],"Language":[18],"Models":[19],"(MLLMs)":[20],"in":[21],"real-world":[22,154],"scenarios":[23,155],"like":[24],"news":[25],"analysis":[26],"and":[27,39,71,124,144,163],"trending":[28],"topics.":[29],"However,":[30],"existing":[31],"approaches":[32],"often":[33],"suffer":[34],"from":[35],"rigid":[36],"retrieval":[37,95,132],"strategies":[38],"under-utilization":[40],"visual":[42],"information.":[43],"To":[44,101],"bridge":[45],"this":[46],"gap,":[47],"we":[48,110],"propose":[49],"E-Agent,":[50],"an":[51],"agent":[52],"framework":[53],"featuring":[54],"two":[55],"key":[56],"innovations:":[57],"mRAG":[59,82,88,108,114,141,158,175],"planner":[60],"trained":[61],"dynamically":[63],"orchestrate":[64],"multimodal":[65],"tools":[66,133],"based":[67],"on":[68],"contextual":[69],"reasoning,":[70],"task":[73],"executor":[74],"employing":[75],"tool-aware":[76],"execution":[77],"sequencing":[78],"implement":[80],"optimized":[81],"workflows.":[83],"E-Agent":[84],"adopts":[85],"one-time":[87],"planning":[89,105,142],"strategy":[90],"that":[91],"enables":[92],"efficient":[93],"information":[94],"while":[96,177],"minimizing":[97],"redundant":[98,179],"tool":[99],"invocations.":[100],"rigorously":[102],"assess":[103],"capabilities":[106],"systems,":[109],"introduce":[111],"Real-World":[113],"Planning":[115],"(RemPlan)":[116],"benchmark.":[117],"This":[118],"novel":[119],"benchmark":[120],"contains":[121],"both":[122],"retrieval-dependent":[123],"retrieval-independent":[125],"question":[126,146],"types,":[127],"systematically":[128],"annotated":[129],"with":[130],"essential":[131],"required":[134],"for":[135],"each":[136],"instance.":[137],"The":[138],"benchmark's":[139],"explicit":[140],"annotations":[143],"diverse":[145],"design":[147],"enhance":[148],"its":[149],"practical":[150],"relevance":[151],"by":[152,181],"simulating":[153],"requiring":[156],"dynamic":[157],"decisions.":[159],"Experiments":[160],"across":[161],"RemPlan":[162],"three":[164],"established":[165],"benchmarks":[166],"demonstrate":[167],"E-Agent's":[168],"superiority:":[169],"13%":[170],"accuracy":[171],"gain":[172],"over":[173],"state-of-the-art":[174],"methods":[176],"reducing":[178],"searches":[180],"37%.":[182]},"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-10-10T00:00:00"}