{"id":"https://openalex.org/W4416244824","doi":"https://doi.org/10.1145/3786335.3813154","title":"Learning from Supervision with Semantic and Episodic Memory: A Reflective Approach to Agent Adaptation","display_name":"Learning from Supervision with Semantic and Episodic Memory: A Reflective Approach to Agent Adaptation","publication_year":2026,"publication_date":"2026-05-22","ids":{"openalex":"https://openalex.org/W4416244824","doi":"https://doi.org/10.1145/3786335.3813154"},"language":null,"primary_location":{"id":"doi:10.1145/3786335.3813154","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3786335.3813154","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM Conference on AI and Agentic Systems","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3786335.3813154","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5119838999","display_name":"Jackson Hassell","orcid":null},"institutions":[{"id":"https://openalex.org/I872623138","display_name":"Search for Extraterrestrial Intelligence","ror":"https://ror.org/02dxgk712","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I872623138"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jackson Hassell","raw_affiliation_strings":["Megagon Labs, Mountain View, California, USA"],"raw_orcid":"https://orcid.org/0009-0004-5573-2759","affiliations":[{"raw_affiliation_string":"Megagon Labs, Mountain View, California, USA","institution_ids":["https://openalex.org/I872623138"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100456022","display_name":"Dan Zhang","orcid":"https://orcid.org/0000-0002-2662-2188"},"institutions":[{"id":"https://openalex.org/I872623138","display_name":"Search for Extraterrestrial Intelligence","ror":"https://ror.org/02dxgk712","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I872623138"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dan Zhang","raw_affiliation_strings":["Megagon Labs, Mountain View, California, USA"],"raw_orcid":"https://orcid.org/0000-0002-6330-0217","affiliations":[{"raw_affiliation_string":"Megagon Labs, Mountain View, California, USA","institution_ids":["https://openalex.org/I872623138"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033892266","display_name":"Hannah Kim","orcid":"https://orcid.org/0009-0001-0094-1201"},"institutions":[{"id":"https://openalex.org/I872623138","display_name":"Search for Extraterrestrial Intelligence","ror":"https://ror.org/02dxgk712","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I872623138"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hannah Kim","raw_affiliation_strings":["Megagon Labs, Mountain View, California, USA"],"raw_orcid":"https://orcid.org/0000-0002-0137-7171","affiliations":[{"raw_affiliation_string":"Megagon Labs, Mountain View, California, USA","institution_ids":["https://openalex.org/I872623138"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Tom Mitchell","orcid":"https://orcid.org/0000-0001-7373-0301"},"institutions":[{"id":"https://openalex.org/I872623138","display_name":"Search for Extraterrestrial Intelligence","ror":"https://ror.org/02dxgk712","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I872623138"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tom Mitchell","raw_affiliation_strings":["Megagon Labs, Mountain View, California, USA"],"raw_orcid":"https://orcid.org/0000-0001-7373-0301","affiliations":[{"raw_affiliation_string":"Megagon Labs, Mountain View, California, USA","institution_ids":["https://openalex.org/I872623138"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5056213327","display_name":"Estevam Hruschka","orcid":"https://orcid.org/0000-0003-1499-2808"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Estevam Hruschka","raw_affiliation_strings":["Megagon Labs, Mountain View, USA"],"raw_orcid":"https://orcid.org/0000-0003-1499-2808","affiliations":[{"raw_affiliation_string":"Megagon Labs, Mountain View, USA","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.0108093,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"276","last_page":"291"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.3052999973297119,"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":0.3052999973297119,"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.12790000438690186,"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/T11636","display_name":"Artificial Intelligence in Healthcare and Education","score":0.05649999901652336,"subfield":{"id":"https://openalex.org/subfields/2718","display_name":"Health Informatics"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.6362000107765198},{"id":"https://openalex.org/keywords/episodic-memory","display_name":"Episodic memory","score":0.6031000018119812},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.5101000070571899},{"id":"https://openalex.org/keywords/semantic-memory","display_name":"Semantic memory","score":0.3991999924182892},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.37540000677108765},{"id":"https://openalex.org/keywords/memory-model","display_name":"Memory model","score":0.3384999930858612}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6988999843597412},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.6362000107765198},{"id":"https://openalex.org/C88576662","wikidata":"https://www.wikidata.org/wiki/Q18646","display_name":"Episodic memory","level":3,"score":0.6031000018119812},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.576200008392334},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.5101000070571899},{"id":"https://openalex.org/C197914299","wikidata":"https://www.wikidata.org/wiki/Q18650","display_name":"Semantic memory","level":3,"score":0.3991999924182892},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.37540000677108765},{"id":"https://openalex.org/C188147891","wikidata":"https://www.wikidata.org/wiki/Q147638","display_name":"Cognitive science","level":1,"score":0.34150001406669617},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3407000005245209},{"id":"https://openalex.org/C12186640","wikidata":"https://www.wikidata.org/wiki/Q6815743","display_name":"Memory model","level":3,"score":0.3384999930858612},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.326200008392334},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.3244999945163727},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.29580000042915344},{"id":"https://openalex.org/C2983448237","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Language understanding","level":2,"score":0.2922999858856201},{"id":"https://openalex.org/C120936955","wikidata":"https://www.wikidata.org/wiki/Q2155640","display_name":"Empirical research","level":2,"score":0.2768000066280365},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.2630999982357025},{"id":"https://openalex.org/C198942812","wikidata":"https://www.wikidata.org/wiki/Q496618","display_name":"Semantic property","level":2,"score":0.25369998812675476}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1145/3786335.3813154","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3786335.3813154","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM Conference on AI and Agentic Systems","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2510.19897","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2510.19897","pdf_url":"https://arxiv.org/pdf/2510.19897","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":"pmh:oai:arXiv.org:2510.19897","is_oa":true,"landing_page_url":"https://arxiv.org/abs/2510.19897","pdf_url":"https://arxiv.org/pdf/2510.19897","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2510.19897","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2510.19897","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"doi:10.1145/3786335.3813154","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3786335.3813154","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM Conference on AI and Agentic Systems","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"We":[0],"investigate":[1],"how":[2],"agents":[3],"built":[4],"on":[5],"pretrained":[6],"large":[7],"language":[8],"models":[9],"(LLMs)":[10],"can":[11],"learn":[12],"target":[13],"classification":[14],"functions":[15],"from":[16],"labeled":[17,44],"examples":[18],"without":[19],"parameter":[20],"updates.":[21],"While":[22],"conventional":[23],"approaches":[24],"like":[25],"fine-tuning":[26],"are":[27],"often":[28],"costly,":[29],"inflexible,":[30],"and":[31],"opaque,":[32],"we":[33],"propose":[34],"a":[35],"memory-augmented":[36],"framework":[37,47],"that":[38],"leverages":[39],"LLM-generated":[40],"critiques":[41],"grounded":[42],"in":[43],"data.":[45],"Our":[46],"uses":[48],"episodic":[49],"memory":[50,59],"to":[51,60],"store":[52],"instance-level":[53],"critiques\u2014capturing":[54],"specific":[55],"past":[56],"experiences\u2014and":[57],"semantic":[58],"distill":[61],"these":[62],"into":[63],"reusable,":[64],"task-level":[65],"guidance.":[66]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-25T00:00:00"}
