{"id":"https://openalex.org/W7133311549","doi":"https://doi.org/10.48550/arxiv.2603.00686","title":"RAVEL: Reasoning Agents for Validating and Evaluating LLM Text Synthesis","display_name":"RAVEL: Reasoning Agents for Validating and Evaluating LLM Text Synthesis","publication_year":2026,"publication_date":"2026-02-28","ids":{"openalex":"https://openalex.org/W7133311549","doi":"https://doi.org/10.48550/arxiv.2603.00686"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2603.00686","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.00686","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2603.00686","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5127948511","display_name":"Andrew Zhuoer Feng","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Feng, Andrew Zhuoer","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5127966976","display_name":"Cunxiang Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Cunxiang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128023128","display_name":"Yu Luo","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Luo, Yu","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5127941245","display_name":"Bosi Wen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wen, Bosi","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5127892038","display_name":"Yidong Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Yidong","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5127899659","display_name":"Lin Fan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fan, Lin","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5127959025","display_name":"Yilin Zhou","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhou, Yilin","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124454141","display_name":"Zikang Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Zikang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5127918881","display_name":"Wenbo Yu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yu, Wenbo","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5127969038","display_name":"Lindong Wu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wu, Lindong","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128003481","display_name":"Hongning Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Hongning","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5128003039","display_name":"Minlie Huang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Huang, Minlie","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":12,"corresponding_author_ids":["https://openalex.org/A5127948511"],"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":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.4593000113964081,"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":0.4593000113964081,"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/T13629","display_name":"Text Readability and Simplification","score":0.07940000295639038,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.07609999924898148,"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/pipeline","display_name":"Pipeline (software)","score":0.6079000234603882},{"id":"https://openalex.org/keywords/semantic-reasoner","display_name":"Semantic reasoner","score":0.6036999821662903},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5479999780654907},{"id":"https://openalex.org/keywords/generator","display_name":"Generator (circuit theory)","score":0.49880000948905945},{"id":"https://openalex.org/keywords/bridge","display_name":"Bridge (graph theory)","score":0.44119998812675476},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.4268999993801117},{"id":"https://openalex.org/keywords/program-synthesis","display_name":"Program synthesis","score":0.4226999878883362},{"id":"https://openalex.org/keywords/plan","display_name":"Plan (archaeology)","score":0.4088999927043915}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6694999933242798},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.6079000234603882},{"id":"https://openalex.org/C9616225","wikidata":"https://www.wikidata.org/wiki/Q3929429","display_name":"Semantic reasoner","level":2,"score":0.6036999821662903},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5479999780654907},{"id":"https://openalex.org/C2780992000","wikidata":"https://www.wikidata.org/wiki/Q17016113","display_name":"Generator (circuit theory)","level":3,"score":0.49880000948905945},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44589999318122864},{"id":"https://openalex.org/C100776233","wikidata":"https://www.wikidata.org/wiki/Q2532492","display_name":"Bridge (graph theory)","level":2,"score":0.44119998812675476},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.4268999993801117},{"id":"https://openalex.org/C2776937632","wikidata":"https://www.wikidata.org/wiki/Q4117718","display_name":"Program synthesis","level":2,"score":0.4226999878883362},{"id":"https://openalex.org/C2776505523","wikidata":"https://www.wikidata.org/wiki/Q4785468","display_name":"Plan (archaeology)","level":2,"score":0.4088999927043915},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.3781000077724457},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.3709000051021576},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.36480000615119934},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.36070001125335693},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.357699990272522},{"id":"https://openalex.org/C132964779","wikidata":"https://www.wikidata.org/wiki/Q2110223","display_name":"Raw data","level":2,"score":0.3467999994754791},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.2825999855995178},{"id":"https://openalex.org/C2778348673","wikidata":"https://www.wikidata.org/wiki/Q739302","display_name":"Production (economics)","level":2,"score":0.2750000059604645},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.273499995470047},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.273499995470047},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.27079999446868896},{"id":"https://openalex.org/C161301231","wikidata":"https://www.wikidata.org/wiki/Q3478658","display_name":"Knowledge representation and reasoning","level":2,"score":0.2700999975204468},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2646999955177307},{"id":"https://openalex.org/C134121241","wikidata":"https://www.wikidata.org/wiki/Q899301","display_name":"Yield (engineering)","level":2,"score":0.25450000166893005},{"id":"https://openalex.org/C154690210","wikidata":"https://www.wikidata.org/wiki/Q1668499","display_name":"Rewriting","level":2,"score":0.25189998745918274}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2603.00686","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.00686","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2603.00686","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.00686","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.5219764113426208}],"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],"have":[3],"evolved":[4],"from":[5,90],"single-round":[6],"generators":[7],"into":[8],"long-horizon":[9],"agents,":[10],"capable":[11],"of":[12,46,114],"complex":[13],"text":[14,147],"synthesis":[15,28,69,148],"scenarios.":[16],"However,":[17],"current":[18],"evaluation":[19],"frameworks":[20],"lack":[21],"the":[22,26,41,60,152,178],"ability":[23],"to":[24,39,63,99,173],"assess":[25],"actual":[27,42],"operations,":[29,70],"such":[30,145],"as":[31,140],"outlining,":[32,72],"drafting,":[33,73],"and":[34,43,66,75,109,185],"editing.":[35],"Consequently,":[36],"they":[37],"fail":[38],"evaluate":[40],"detailed":[44],"capabilities":[45,102],"LLMs.":[47],"To":[48],"bridge":[49],"this":[50,78,190],"gap,":[51],"we":[52,80,117,142,162],"introduce":[53],"RAVEL,":[54],"an":[55],"agentic":[56,146],"framework":[57],"that":[58,119,125,144,164],"enables":[59],"LLM":[61],"testers":[62],"autonomously":[64],"plan":[65],"execute":[67],"typical":[68],"including":[71],"reviewing,":[74],"refining.":[76],"Complementing":[77],"framework,":[79],"present":[81],"C3EBench,":[82],"a":[83,96,165,170],"comprehensive":[84],"benchmark":[85],"comprising":[86],"1,258":[87],"samples":[88],"derived":[89],"professional":[91],"human":[92],"writings.":[93],"We":[94],"utilize":[95],"\"reverse-engineering\"":[97],"pipeline":[98],"isolate":[100],"specific":[101],"across":[103],"four":[104],"tasks:":[105],"Cloze,":[106],"Edit,":[107],"Expand,":[108],"End-to-End.":[110],"Through":[111],"our":[112],"analysis":[113],"14":[115],"LLMs,":[116],"uncover":[118],"most":[120],"LLMs":[121,139],"struggle":[122],"with":[123,137],"tasks":[124],"demand":[126],"contextual":[127],"understanding":[128],"under":[129],"limited":[130],"or":[131],"under-specified":[132],"instructions.":[133],"By":[134],"augmenting":[135],"RAVEL":[136],"SOTA":[138],"operators,":[141],"find":[143,163],"is":[149],"dominated":[150],"by":[151],"LLM's":[153],"reasoning":[154],"capability":[155],"rather":[156],"than":[157],"raw":[158],"generative":[159],"capacity.":[160],"Furthermore,":[161],"strong":[166],"reasoner":[167],"can":[168],"guide":[169],"weaker":[171],"generator":[172],"yield":[174],"higher-quality":[175],"results,":[176],"whereas":[177],"inverse":[179],"does":[180],"not":[181],"hold.":[182],"Our":[183],"code":[184],"data":[186],"are":[187],"available":[188],"at":[189],"link:":[191],"https://github.com/ZhuoerFeng/RAVEL-Reasoning-Agents-Text-Eval.":[192]},"counts_by_year":[],"updated_date":"2026-03-04T07:09:34.246503","created_date":"2026-03-04T00:00:00"}