{"id":"https://openalex.org/W4414359156","doi":"https://doi.org/10.24963/ijcai.2025/932","title":"EDGE: Efficient Data Selection for LLM Agents via Guideline Effectiveness","display_name":"EDGE: Efficient Data Selection for LLM Agents via Guideline Effectiveness","publication_year":2025,"publication_date":"2025-09-01","ids":{"openalex":"https://openalex.org/W4414359156","doi":"https://doi.org/10.24963/ijcai.2025/932"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2025/932","is_oa":false,"landing_page_url":"https://doi.org/10.24963/ijcai.2025/932","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"type":"article","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/A5059705832","display_name":"Yunxiao Zhang","orcid":"https://orcid.org/0000-0002-0090-1330"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yunxiao Zhang","raw_affiliation_strings":["Peking University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Peking University","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058469446","display_name":"Guanming Xiong","orcid":null},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guanming Xiong","raw_affiliation_strings":["Peking University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Peking University","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100742021","display_name":"Haochen Li","orcid":"https://orcid.org/0000-0001-7596-9578"},"institutions":[{"id":"https://openalex.org/I2799847335","display_name":"Art Institute of Portland","ror":"https://ror.org/01cb0jg64","country_code":"US","type":"education","lineage":["https://openalex.org/I2799847335","https://openalex.org/I2799969541"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Haochen Li","raw_affiliation_strings":["01.AI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"01.AI","institution_ids":["https://openalex.org/I2799847335"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5108592412","display_name":"Wen Zhao","orcid":"https://orcid.org/0009-0000-1112-5608"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wen Zhao","raw_affiliation_strings":["Peking University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Peking University","institution_ids":["https://openalex.org/I20231570"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.11836969,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"8384","last_page":"8392"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.8827999830245972,"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":0.8827999830245972,"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/T10215","display_name":"Semantic Web and Ontologies","score":0.8087999820709229,"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/T14351","display_name":"Statistical and Computational Modeling","score":0.7487999796867371,"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/sample","display_name":"Sample (material)","score":0.5745000243186951},{"id":"https://openalex.org/keywords/perspective","display_name":"Perspective (graphical)","score":0.5292999744415283},{"id":"https://openalex.org/keywords/missing-data","display_name":"Missing data","score":0.5164999961853027},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.5092999935150146},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.508899986743927},{"id":"https://openalex.org/keywords/guideline","display_name":"Guideline","score":0.45010000467300415}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7064999938011169},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.5745000243186951},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.5292999744415283},{"id":"https://openalex.org/C9357733","wikidata":"https://www.wikidata.org/wiki/Q6878417","display_name":"Missing data","level":2,"score":0.5164999961853027},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.5092999935150146},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.508899986743927},{"id":"https://openalex.org/C2780182762","wikidata":"https://www.wikidata.org/wiki/Q1630279","display_name":"Guideline","level":2,"score":0.45010000467300415},{"id":"https://openalex.org/C24756922","wikidata":"https://www.wikidata.org/wiki/Q1757694","display_name":"Data quality","level":3,"score":0.4447999894618988},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.4408000111579895},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44040000438690186},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.43220001459121704},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4242999851703644},{"id":"https://openalex.org/C148220186","wikidata":"https://www.wikidata.org/wiki/Q7111912","display_name":"Outcome (game theory)","level":2,"score":0.36579999327659607},{"id":"https://openalex.org/C133462117","wikidata":"https://www.wikidata.org/wiki/Q4929239","display_name":"Data collection","level":2,"score":0.35910001397132874},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.3089999854564667},{"id":"https://openalex.org/C129848803","wikidata":"https://www.wikidata.org/wiki/Q2564360","display_name":"Sample size determination","level":2,"score":0.28290000557899475},{"id":"https://openalex.org/C112930515","wikidata":"https://www.wikidata.org/wiki/Q4389547","display_name":"Risk analysis (engineering)","level":1,"score":0.2630999982357025}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.24963/ijcai.2025/932","is_oa":false,"landing_page_url":"https://doi.org/10.24963/ijcai.2025/932","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"}],"best_oa_location":null,"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":{"Large":[0],"Language":[1],"Models":[2],"(LLMs)":[3],"have":[4],"shown":[5],"remarkable":[6],"capabilities":[7],"as":[8],"AI":[9],"agents.":[10],"However,":[11],"existing":[12,152],"methods":[13],"for":[14,47,87,121],"enhancing":[15],"LLM-agent":[16,165],"abilities":[17],"often":[18],"lack":[19],"a":[20,44,88,157],"focus":[21],"on":[22,136,160],"data":[23,162],"quality,":[24],"leading":[25],"to":[26],"inefficiencies":[27],"and":[28,34,112,118,139,141,145],"suboptimal":[29],"results":[30,135],"in":[31,73],"both":[32,115],"fine-tuning":[33,119],"prompt":[35,116],"engineering.":[36],"To":[37],"address":[38],"this":[39],"issue,":[40],"we":[41,107],"introduce":[42],"EDGE,":[43],"novel":[45],"approach":[46],"identifying":[48],"informative":[49],"samples":[50,65,102],"without":[51],"needing":[52],"golden":[53],"answers.":[54],"We":[55,154],"propose":[56],"the":[57,68,83,93,96,110,126,137,161],"Guideline":[58],"Effectiveness":[59],"(GE)":[60],"metric,":[61],"which":[62],"selects":[63],"challenging":[64],"by":[66],"measuring":[67],"impact":[69],"of":[70,114,128,164],"human-provided":[71],"guidelines":[72],"multi-turn":[74],"interaction":[75],"tasks.":[76],"A":[77],"low":[78,104],"GE":[79,105],"score":[80],"indicates":[81],"that":[82],"human":[84],"expertise":[85],"required":[86],"sample":[89,97],"is":[90],"missing":[91],"from":[92],"guideline,":[94],"making":[95],"more":[98],"informative.":[99],"By":[100],"selecting":[101],"with":[103],"scores,":[106],"can":[108],"improve":[109],"efficiency":[111],"outcomes":[113],"engineering":[117],"processes":[120],"LLMs.":[122],"Extensive":[123],"experiments":[124],"validate":[125],"performance":[127],"our":[129],"method.":[130],"Our":[131],"method":[132],"achieves":[133],"competitive":[134],"HotpotQA":[138],"WebShop":[140],"datasets,":[142],"requiring":[143],"75%":[144],"50%":[146],"less":[147],"data,":[148],"respectively,":[149],"while":[150],"outperforming":[151],"methods.":[153],"also":[155],"provide":[156],"fresh":[158],"perspective":[159],"quality":[163],"fine-tuning.":[166]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}