{"id":"https://openalex.org/W4412887782","doi":"https://doi.org/10.18653/v1/2025.findings-acl.989","title":"MemBench: Towards More Comprehensive Evaluation on the Memory of LLM-based Agents","display_name":"MemBench: Towards More Comprehensive Evaluation on the Memory of LLM-based Agents","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4412887782","doi":"https://doi.org/10.18653/v1/2025.findings-acl.989"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.findings-acl.989","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.989","pdf_url":"https://aclanthology.org/2025.findings-acl.989.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: ACL 2025","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.findings-acl.989.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5035969755","display_name":"Haoran Tan","orcid":"https://orcid.org/0000-0003-4127-8896"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Haoran Tan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100358736","display_name":"Zeyu Zhang","orcid":"https://orcid.org/0000-0002-7157-6272"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zeyu Zhang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100652421","display_name":"Man Chen","orcid":"https://orcid.org/0009-0006-4599-7328"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen Ma","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101755392","display_name":"Xu Chen","orcid":"https://orcid.org/0000-0003-0144-1775"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xu Chen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048783161","display_name":"Quanyu Dai","orcid":"https://orcid.org/0000-0001-7578-2738"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Quanyu Dai","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5021124418","display_name":"Zhenhua Dong","orcid":"https://orcid.org/0000-0002-2231-4663"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhenhua Dong","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":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"19336","last_page":"19352"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10215","display_name":"Semantic Web and Ontologies","score":0.7860999703407288,"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/T10215","display_name":"Semantic Web and Ontologies","score":0.7860999703407288,"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/T10456","display_name":"Multi-Agent Systems and Negotiation","score":0.7757999897003174,"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/T12761","display_name":"Data Stream Mining Techniques","score":0.7318000197410583,"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/computer-science","display_name":"Computer science","score":0.6657974720001221},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.344203382730484}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6657974720001221},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.344203382730484}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.findings-acl.989","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.989","pdf_url":"https://aclanthology.org/2025.findings-acl.989.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: ACL 2025","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.findings-acl.989","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.989","pdf_url":"https://aclanthology.org/2025.findings-acl.989.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: ACL 2025","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320322499","display_name":"Renmin University of China","ror":"https://ror.org/041pakw92"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412887782.pdf","grobid_xml":"https://content.openalex.org/works/W4412887782.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"Recent":[0],"works":[1],"have":[2],"highlighted":[3],"the":[4,36,50,72,108,124],"significance":[5],"of":[6,38,75,111],"memory":[7,26,39,51,73,81,84,109],"mechanisms":[8],"in":[9,59],"LLM-based":[10,112],"agents,":[11],"which":[12],"enable":[13],"them":[14],"to":[15,21,48,70,106],"store":[16],"observed":[17],"information":[18],"and":[19,41,68,82,88,91,121,131],"adapt":[20],"dynamic":[22],"environments.However,":[23],"evaluating":[24],"their":[25,118],"capabilities":[27,52],"still":[28],"remains":[29],"challenges.Previous":[30],"evaluations":[31],"are":[32],"commonly":[33],"limited":[34],"by":[35],"diversity":[37],"levels":[40],"interactive":[42,95],"scenarios.They":[43],"also":[44],"lack":[45],"comprehensive":[46,66],"metrics":[47],"reflect":[49],"from":[53,114],"multiple":[54,115],"aspects.To":[55],"address":[56],"these":[57],"problems,":[58],"this":[60],"paper,":[61],"we":[62,100,127],"construct":[63],"a":[64,102],"more":[65],"dataset":[67,78,130],"benchmark":[69],"evaluate":[71,107],"capability":[74,110],"LLMbased":[76],"agents.Our":[77],"incorporates":[79],"factual":[80],"reflective":[83],"as":[85,93],"different":[86],"levels,":[87],"proposes":[89],"participation":[90],"observation":[92],"various":[94],"scenarios.Based":[96],"on":[97],"our":[98,129],"dataset,":[99],"present":[101],"benchmark,":[103],"named":[104],"MemBench,":[105],"agents":[113],"aspects,":[116],"including":[117],"effectiveness,":[119],"efficiency,":[120],"capacity.To":[122],"benefit":[123],"research":[125],"community,":[126],"release":[128],"project":[132],"at":[133],"https:":[134],"//github.com/import-myself/Membench.":[135]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}