{"id":"https://openalex.org/W4406611172","doi":"https://doi.org/10.1109/smc54092.2024.10831260","title":"Try-Then-Eval: Equipping an LLM-based Agent with a Two-Phase Mechanism to Solve Computer Tasks","display_name":"Try-Then-Eval: Equipping an LLM-based Agent with a Two-Phase Mechanism to Solve Computer Tasks","publication_year":2024,"publication_date":"2024-10-06","ids":{"openalex":"https://openalex.org/W4406611172","doi":"https://doi.org/10.1109/smc54092.2024.10831260"},"language":"en","primary_location":{"id":"doi:10.1109/smc54092.2024.10831260","is_oa":false,"landing_page_url":"https://doi.org/10.1109/smc54092.2024.10831260","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Systems, Man, and Cybernetics (SMC)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5044067686","display_name":"Duy Minh Cao","orcid":null},"institutions":[{"id":"https://openalex.org/I23582244","display_name":"Ho Chi Minh City University of Science","ror":"https://ror.org/05jfbgm49","country_code":"VN","type":"education","lineage":["https://openalex.org/I123565023","https://openalex.org/I23582244"]}],"countries":["VN"],"is_corresponding":false,"raw_author_name":"Duy Cao","raw_affiliation_strings":["University of Science,Faculty of Information Technology,Ho Chi Minh City,Vietnam"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science,Faculty of Information Technology,Ho Chi Minh City,Vietnam","institution_ids":["https://openalex.org/I23582244"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081697591","display_name":"Phu Van Nguyen","orcid":"https://orcid.org/0000-0003-0209-6862"},"institutions":[{"id":"https://openalex.org/I23582244","display_name":"Ho Chi Minh City University of Science","ror":"https://ror.org/05jfbgm49","country_code":"VN","type":"education","lineage":["https://openalex.org/I123565023","https://openalex.org/I23582244"]}],"countries":["VN"],"is_corresponding":false,"raw_author_name":"Phu Nguyen","raw_affiliation_strings":["University of Science,Faculty of Information Technology,Ho Chi Minh City,Vietnam"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science,Faculty of Information Technology,Ho Chi Minh City,Vietnam","institution_ids":["https://openalex.org/I23582244"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048198457","display_name":"Vy Khoi Le","orcid":"https://orcid.org/0000-0002-0100-1633"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Vy Le","raw_affiliation_strings":["University of Information Technology,Faculty of Computer Science,Ho Chi Minh City,Vietnam"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Information Technology,Faculty of Computer Science,Ho Chi Minh City,Vietnam","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101729793","display_name":"Long Nguyen","orcid":"https://orcid.org/0000-0001-7673-7955"},"institutions":[{"id":"https://openalex.org/I23582244","display_name":"Ho Chi Minh City University of Science","ror":"https://ror.org/05jfbgm49","country_code":"VN","type":"education","lineage":["https://openalex.org/I123565023","https://openalex.org/I23582244"]}],"countries":["VN"],"is_corresponding":false,"raw_author_name":"Long Nguyen","raw_affiliation_strings":["University of Science,Faculty of Information Technology,Ho Chi Minh City,Vietnam"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science,Faculty of Information Technology,Ho Chi Minh City,Vietnam","institution_ids":["https://openalex.org/I23582244"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5091407554","display_name":"Vu Nguyen","orcid":"https://orcid.org/0000-0002-0594-4372"},"institutions":[{"id":"https://openalex.org/I23582244","display_name":"Ho Chi Minh City University of Science","ror":"https://ror.org/05jfbgm49","country_code":"VN","type":"education","lineage":["https://openalex.org/I123565023","https://openalex.org/I23582244"]}],"countries":["VN"],"is_corresponding":false,"raw_author_name":"Vu Nguyen","raw_affiliation_strings":["University of Science,Faculty of Information Technology,Ho Chi Minh City,Vietnam"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science,Faculty of Information Technology,Ho Chi Minh City,Vietnam","institution_ids":["https://openalex.org/I23582244"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"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":"1224","last_page":"1229"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10456","display_name":"Multi-Agent Systems and Negotiation","score":0.9610999822616577,"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/T10456","display_name":"Multi-Agent Systems and Negotiation","score":0.9610999822616577,"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/T10703","display_name":"Business Process Modeling and Analysis","score":0.9307000041007996,"subfield":{"id":"https://openalex.org/subfields/1404","display_name":"Management Information Systems"},"field":{"id":"https://openalex.org/fields/14","display_name":"Business, Management and Accounting"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.736775279045105},{"id":"https://openalex.org/keywords/mechanism","display_name":"Mechanism (biology)","score":0.6182606220245361},{"id":"https://openalex.org/keywords/phase","display_name":"Phase (matter)","score":0.410774290561676},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3766632378101349},{"id":"https://openalex.org/keywords/epistemology","display_name":"Epistemology","score":0.08358252048492432},{"id":"https://openalex.org/keywords/philosophy","display_name":"Philosophy","score":0.05943819880485535}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.736775279045105},{"id":"https://openalex.org/C89611455","wikidata":"https://www.wikidata.org/wiki/Q6804646","display_name":"Mechanism (biology)","level":2,"score":0.6182606220245361},{"id":"https://openalex.org/C44280652","wikidata":"https://www.wikidata.org/wiki/Q104837","display_name":"Phase (matter)","level":2,"score":0.410774290561676},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3766632378101349},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.08358252048492432},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.05943819880485535},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/smc54092.2024.10831260","is_oa":false,"landing_page_url":"https://doi.org/10.1109/smc54092.2024.10831260","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Systems, Man, and Cybernetics (SMC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":5,"referenced_works":["https://openalex.org/W4389520007","https://openalex.org/W4389520250","https://openalex.org/W4390874280","https://openalex.org/W4391609325","https://openalex.org/W4393065402"],"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":{"Building":[0],"an":[1,68],"autonomous":[2],"intelligent":[3],"agent":[4,69,85],"capable":[5],"of":[6,21,43,58,90,112],"carrying":[7],"out":[8],"web":[9],"automation":[10,30],"tasks":[11,75],"from":[12],"descriptions":[13],"in":[14,31],"natural":[15],"language":[16],"offers":[17],"a":[18],"wide":[19],"range":[20],"applications,":[22],"including":[23],"software":[24],"testing,":[25],"virtual":[26],"assistants,":[27],"and":[28],"task":[29],"general.":[32],"However,":[33],"recent":[34],"studies":[35],"addressing":[36],"this":[37,48],"problem":[38,53],"often":[39],"require":[40],"manually":[41],"constructing":[42],"prior":[44,103],"human":[45,79],"demonstrations.":[46,80,104],"In":[47],"paper,":[49],"we":[50],"approach":[51,97],"the":[52,56,63,87,109],"by":[54],"leveraging":[55],"idea":[57],"reinforcement":[59],"learning":[60],"(RL)":[61],"with":[62],"two-phase":[64],"mechanism":[65],"to":[66],"form":[67],"using":[70,86],"LLMs":[71],"for":[72],"automating":[73],"computer":[74],"without":[76,102],"relying":[77],"on":[78],"We":[81],"evaluate":[82],"our":[83,96],"LLM-based":[84],"MiniWob++":[88],"dataset":[89],"web-based":[91],"application":[92],"tasks,":[93],"showing":[94],"that":[95],"achieves":[98],"85%":[99],"success":[100],"rate":[101],"The":[105],"results":[106],"also":[107],"demonstrate":[108],"agent's":[110],"capability":[111],"self-improvement":[113],"through":[114],"training.":[115]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
