{"id":"https://openalex.org/W4415799296","doi":"https://doi.org/10.52202/079017-0019","title":"AutoManual: Constructing Instruction Manuals by LLM Agents via Interactive Environmental Learning","display_name":"AutoManual: Constructing Instruction Manuals by LLM Agents via Interactive Environmental Learning","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4415799296","doi":"https://doi.org/10.52202/079017-0019"},"language":"en","primary_location":{"id":"doi:10.52202/079017-0019","doi":"https://doi.org/10.52202/079017-0019","is_oa":false,"landing_page_url":"https://doi.org/10.52202/079017-0019","pdf_url":null,"source":{"id":"https://openalex.org/S4363606243","display_name":"neural information processing systems","issn_l":"1049-5258","issn":["1049-5258"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","norway-2"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Advances in Neural Information Processing Systems 37","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2405.16247","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100594484","display_name":"Minghao Chen","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Minghao Chen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Yihang Li","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yihang Li","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114169614","display_name":"Yanting Yang","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yanting Yang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113918016","display_name":"Shiyu Yu","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shiyu Yu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101368176","display_name":"Binbin Lin","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Binbin Lin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":null,"display_name":"Xiaofei He","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiaofei He","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":5.5252,"has_fulltext":true,"cited_by_count":35,"citation_normalized_percentile":{"value":0.97044429,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":88,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"589","last_page":"631"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.1339000016450882,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.1339000016450882,"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/T10906","display_name":"AI-based Problem Solving and Planning","score":0.1005999967455864,"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/T10028","display_name":"Topic Modeling","score":0.05290000140666962,"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/user-manual","display_name":"user manual","score":0.7459999918937683},{"id":"https://openalex.org/keywords/large-language-models","display_name":"large language models","score":0.843999981880188},{"id":"https://openalex.org/keywords/llm-based-agents","display_name":"LLM agents","score":0.8709999918937683},{"id":"https://openalex.org/keywords/interactive-learning","display_name":"interactive learning","score":0.656000018119812},{"id":"https://openalex.org/keywords/environmental-learning","display_name":"environmental learning","score":0.6890000104904175},{"id":"https://openalex.org/keywords/knowledge-construction","display_name":"knowledge construction","score":0.3630000054836273}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5590000152587891},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.4564000070095062},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.43309998512268066},{"id":"https://openalex.org/C43141900","wikidata":"https://www.wikidata.org/wiki/Q948732","display_name":"Environmental education","level":2,"score":0.4207000136375427},{"id":"https://openalex.org/C77967617","wikidata":"https://www.wikidata.org/wiki/Q4677561","display_name":"Active learning (machine learning)","level":2,"score":0.3165999948978424},{"id":"https://openalex.org/C37228920","wikidata":"https://www.wikidata.org/wiki/Q1307600","display_name":"Experiential learning","level":2,"score":0.3127000033855438},{"id":"https://openalex.org/C2776716048","wikidata":"https://www.wikidata.org/wiki/Q6045290","display_name":"Interactive Learning","level":2,"score":0.30880001187324524},{"id":"https://openalex.org/C2778365744","wikidata":"https://www.wikidata.org/wiki/Q2426689","display_name":"Learning environment","level":2,"score":0.2969000041484833},{"id":"https://openalex.org/C145420912","wikidata":"https://www.wikidata.org/wiki/Q853077","display_name":"Mathematics education","level":1,"score":0.2897999882698059},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.27320000529289246},{"id":"https://openalex.org/C3019723476","wikidata":"https://www.wikidata.org/wiki/Q1068473","display_name":"Electronic learning","level":3,"score":0.2678999900817871},{"id":"https://openalex.org/C88610354","wikidata":"https://www.wikidata.org/wiki/Q1813494","display_name":"Teaching method","level":2,"score":0.2549999952316284},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.25110000371932983}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.52202/079017-0019","doi":"https://doi.org/10.52202/079017-0019","is_oa":false,"landing_page_url":"https://doi.org/10.52202/079017-0019","pdf_url":null,"source":{"id":"https://openalex.org/S4363606243","display_name":"neural information processing systems","issn_l":"1049-5258","issn":["1049-5258"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","norway-2"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Advances in Neural Information Processing Systems 37","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2405.16247","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2405.16247","pdf_url":"https://arxiv.org/pdf/2405.16247","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,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2405.16247","doi":"https://doi.org/10.48550/arxiv.2405.16247","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2405.16247","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,"listed_in":[],"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":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2405.16247","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2405.16247","pdf_url":"https://arxiv.org/pdf/2405.16247","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,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G2101641620","display_name":null,"funder_award_id":"62273303","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4415799296.pdf","grobid_xml":"https://content.openalex.org/works/W4415799296.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7166831912","https://openalex.org/W4389519896","https://openalex.org/W4410641171","https://openalex.org/W7117983813","https://openalex.org/W4409657210","https://openalex.org/W4386501856","https://openalex.org/W4394947983","https://openalex.org/W4385965642","https://openalex.org/W7164648835","https://openalex.org/W7165007513"],"abstract_inverted_index":{"Large":[0],"Language":[1],"Models":[2],"(LLM)":[3],"based":[4,85],"agents":[5,24,49],"have":[6],"shown":[7],"promise":[8],"in":[9,35,72,117],"autonomously":[10,51],"completing":[11],"tasks":[12,34],"across":[13],"various":[14],"domains,":[15,37],"e.g.,":[16],"robotics,":[17],"games,":[18],"and":[19,29,57,69,110,175],"web":[20],"navigation.":[21],"However,":[22],"these":[23,134],"typically":[25],"require":[26],"elaborate":[27],"design":[28],"expert":[30],"prompts":[31],"to":[32,50,59],"solve":[33],"specific":[36],"which":[38],"limits":[39],"their":[40,53],"adaptability.":[41],"We":[42],"introduce":[43,121],"AutoManual,":[44],"a":[45,101,122,137],"framework":[46],"enabling":[47],"LLM":[48],"build":[52],"understanding":[54],"through":[55,100],"interaction":[56],"adapt":[58],"new":[60],"environments.":[61],"AutoManual":[62,165],"categorizes":[63],"environmental":[64],"knowledge":[65],"into":[66,136],"diverse":[67],"rules":[68,88,99,135],"optimizes":[70],"them":[71],"an":[73],"online":[74,107],"fashion":[75],"by":[76],"two":[77],"agents:":[78],"1)":[79],"The":[80,95,140,183],"Planner":[81],"codes":[82],"actionable":[83],"plans":[84],"on":[86,179],"current":[87],"for":[89,126],"interacting":[90],"with":[91,173,177],"the":[92,98,127,130,147,152],"environment.":[93],"2)":[94],"Builder":[96],"updates":[97],"well-structured":[102],"rule":[103,108],"system":[104],"that":[105],"facilitates":[106],"management":[109],"essential":[111],"detail":[112],"retention.":[113],"To":[114],"mitigate":[115],"hallucinations":[116],"managing":[118],"rules,":[119],"we":[120],"*case-conditioned":[123],"prompting*":[124],"strategy":[125],"Builder.":[128],"Finally,":[129],"Formulator":[131],"agent":[132],"compiles":[133],"comprehensive":[138],"manual.":[139],"self-generated":[141],"manual":[142],"can":[143],"not":[144],"only":[145,161],"improve":[146],"adaptability":[148],"but":[149],"also":[150],"guide":[151],"planning":[153],"of":[154],"smaller":[155],"LLMs":[156],"while":[157],"being":[158],"human-readable.":[159],"Given":[160],"one":[162],"simple":[163],"demonstration,":[164],"significantly":[166],"improves":[167],"task":[168],"success":[169],"rates,":[170],"achieving":[171],"97.4\\%":[172],"GPT-4-turbo":[174],"86.2\\%":[176],"GPT-3.5-turbo":[178],"ALFWorld":[180],"benchmark":[181],"tasks.":[182],"code":[184],"is":[185],"available":[186],"at":[187],"https://github.com/minghchen/automanual.":[188]},"counts_by_year":[{"year":2026,"cited_by_count":19},{"year":2025,"cited_by_count":15},{"year":2024,"cited_by_count":1}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2025-11-03T00:00:00"}