{"id":"https://openalex.org/W4417339179","doi":"https://doi.org/10.1109/ictai66417.2025.00122","title":"Towards Logically Sound Natural Language Reasoning with Logic-Enhanced Language Model Agents","display_name":"Towards Logically Sound Natural Language Reasoning with Logic-Enhanced Language Model Agents","publication_year":2025,"publication_date":"2025-11-03","ids":{"openalex":"https://openalex.org/W4417339179","doi":"https://doi.org/10.1109/ictai66417.2025.00122"},"language":null,"primary_location":{"id":"doi:10.1109/ictai66417.2025.00122","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ictai66417.2025.00122","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE 37th International Conference on Tools with Artificial Intelligence (ICTAI)","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/A5025112559","display_name":"Agnieszka Mensfelt","orcid":"https://orcid.org/0000-0002-2385-2017"},"institutions":[{"id":"https://openalex.org/I184558857","display_name":"Royal Holloway University of London","ror":"https://ror.org/04g2vpn86","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I184558857"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Agnieszka Mensfelt","raw_affiliation_strings":["Royal Holloway, Univ. of London,Department of Computer Science,Egham,Surrey,UK"],"affiliations":[{"raw_affiliation_string":"Royal Holloway, Univ. of London,Department of Computer Science,Egham,Surrey,UK","institution_ids":["https://openalex.org/I184558857"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035046930","display_name":"Kostas Stathis","orcid":"https://orcid.org/0000-0002-9946-4037"},"institutions":[{"id":"https://openalex.org/I184558857","display_name":"Royal Holloway University of London","ror":"https://ror.org/04g2vpn86","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I184558857"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Kostas Stathis","raw_affiliation_strings":["Royal Holloway, Univ. of London,Department of Computer Science,Egham,Surrey,UK"],"affiliations":[{"raw_affiliation_string":"Royal Holloway, Univ. of London,Department of Computer Science,Egham,Surrey,UK","institution_ids":["https://openalex.org/I184558857"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5107421530","display_name":"Vince Trencsenyi","orcid":null},"institutions":[{"id":"https://openalex.org/I184558857","display_name":"Royal Holloway University of London","ror":"https://ror.org/04g2vpn86","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I184558857"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Vince Trencsenyi","raw_affiliation_strings":["Royal Holloway, Univ. of London,Department of Computer Science,Egham,Surrey,UK"],"affiliations":[{"raw_affiliation_string":"Royal Holloway, Univ. of London,Department of Computer Science,Egham,Surrey,UK","institution_ids":["https://openalex.org/I184558857"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5025112559"],"corresponding_institution_ids":["https://openalex.org/I184558857"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.22376138,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"838","last_page":"842"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.2784999907016754,"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":0.2784999907016754,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.1670999974012375,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.07519999891519547,"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/correctness","display_name":"Correctness","score":0.6488000154495239},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.6376000046730042},{"id":"https://openalex.org/keywords/automated-reasoning","display_name":"Automated reasoning","score":0.5422000288963318},{"id":"https://openalex.org/keywords/dilemma","display_name":"Dilemma","score":0.49459999799728394},{"id":"https://openalex.org/keywords/natural-language-understanding","display_name":"Natural language understanding","score":0.4869000017642975},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4569000005722046},{"id":"https://openalex.org/keywords/deductive-reasoning","display_name":"Deductive reasoning","score":0.45419999957084656},{"id":"https://openalex.org/keywords/logical-consequence","display_name":"Logical consequence","score":0.4156000018119812},{"id":"https://openalex.org/keywords/logical-reasoning","display_name":"Logical reasoning","score":0.40119999647140503}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7245000004768372},{"id":"https://openalex.org/C55439883","wikidata":"https://www.wikidata.org/wiki/Q360812","display_name":"Correctness","level":2,"score":0.6488000154495239},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.6376000046730042},{"id":"https://openalex.org/C195344581","wikidata":"https://www.wikidata.org/wiki/Q2555318","display_name":"Automated reasoning","level":2,"score":0.5422000288963318},{"id":"https://openalex.org/C2778496695","wikidata":"https://www.wikidata.org/wiki/Q254128","display_name":"Dilemma","level":2,"score":0.49459999799728394},{"id":"https://openalex.org/C2779439875","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Natural language understanding","level":3,"score":0.4869000017642975},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4569000005722046},{"id":"https://openalex.org/C97364631","wikidata":"https://www.wikidata.org/wiki/Q484284","display_name":"Deductive reasoning","level":2,"score":0.45419999957084656},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4465999901294708},{"id":"https://openalex.org/C134752490","wikidata":"https://www.wikidata.org/wiki/Q374182","display_name":"Logical consequence","level":2,"score":0.4156000018119812},{"id":"https://openalex.org/C43971567","wikidata":"https://www.wikidata.org/wiki/Q3142865","display_name":"Logical reasoning","level":2,"score":0.40119999647140503},{"id":"https://openalex.org/C2776608160","wikidata":"https://www.wikidata.org/wiki/Q4785462","display_name":"Natural (archaeology)","level":2,"score":0.383899986743927},{"id":"https://openalex.org/C185954173","wikidata":"https://www.wikidata.org/wiki/Q4347052","display_name":"Object language","level":3,"score":0.37959998846054077},{"id":"https://openalex.org/C159032336","wikidata":"https://www.wikidata.org/wiki/Q2488768","display_name":"Non-monotonic logic","level":2,"score":0.3781000077724457},{"id":"https://openalex.org/C89288958","wikidata":"https://www.wikidata.org/wiki/Q7301504","display_name":"Reasoning system","level":2,"score":0.3716999888420105},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3499000072479248},{"id":"https://openalex.org/C37335422","wikidata":"https://www.wikidata.org/wiki/Q6888134","display_name":"Model-based reasoning","level":3,"score":0.3407999873161316},{"id":"https://openalex.org/C21847791","wikidata":"https://www.wikidata.org/wiki/Q191081","display_name":"Logical conjunction","level":2,"score":0.2969000041484833},{"id":"https://openalex.org/C102993220","wikidata":"https://www.wikidata.org/wiki/Q387196","display_name":"Description logic","level":2,"score":0.2831000089645386},{"id":"https://openalex.org/C193221554","wikidata":"https://www.wikidata.org/wiki/Q5153664","display_name":"Commonsense reasoning","level":2,"score":0.28200000524520874},{"id":"https://openalex.org/C66024118","wikidata":"https://www.wikidata.org/wiki/Q1122506","display_name":"Computational model","level":2,"score":0.2752000093460083},{"id":"https://openalex.org/C188147891","wikidata":"https://www.wikidata.org/wiki/Q147638","display_name":"Cognitive science","level":1,"score":0.2718000113964081},{"id":"https://openalex.org/C203702819","wikidata":"https://www.wikidata.org/wiki/Q17146953","display_name":"Logical data model","level":3,"score":0.25690001249313354},{"id":"https://openalex.org/C2775940519","wikidata":"https://www.wikidata.org/wiki/Q17067742","display_name":"Logic model","level":2,"score":0.25589999556541443},{"id":"https://openalex.org/C2983448237","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Language understanding","level":2,"score":0.2531999945640564}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ictai66417.2025.00122","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ictai66417.2025.00122","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE 37th International Conference on Tools with Artificial Intelligence (ICTAI)","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":5,"referenced_works":["https://openalex.org/W2169848499","https://openalex.org/W2911601159","https://openalex.org/W3123335860","https://openalex.org/W4389988531","https://openalex.org/W4393160233"],"related_works":[],"abstract_inverted_index":{"Large":[0],"language":[1,69],"models":[2,123],"(LLMs)":[3],"are":[4,92],"increasingly":[5],"explored":[6],"as":[7,103,107],"general-purpose":[8],"reasoners,":[9],"particularly":[10,142],"in":[11,28,124,133,143,150,154],"agentic":[12],"contexts.":[13],"However,":[14],"their":[15],"outputs":[16,33],"remain":[17],"prone":[18],"to":[19,62,85,95],"mathematical":[20],"and":[21,38,65,79,82,120,136,153],"logical":[22,97],"errors.":[23],"This":[24],"is":[25],"especially":[26],"challenging":[27],"open-ended":[29,159],"tasks,":[30],"where":[31],"unstructured":[32],"lack":[34],"explicit":[35],"ground":[36],"truth":[37],"may":[39],"contain":[40],"subtle":[41],"inconsistencies.":[42],"To":[43],"address":[44],"this":[45],"issue,":[46],"we":[47,109],"propose":[48],"Logic-Enhanced":[49],"Language":[50],"Model":[51],"Agents":[52],"(LELMA),":[53],"a":[54,80],"framework":[55],"that":[56],"integrates":[57],"LLMs":[58],"with":[59],"formal":[60],"logic":[61,89],"enable":[63],"validation":[64],"refinement":[66],"of":[67,113,156],"natural":[68],"reasoning.":[70,128],"LELMA":[71,129],"comprises":[72],"three":[73],"components:":[74],"an":[75,77],"LLM-Reasoner,":[76],"LLM-Translator,":[78],"Solver,":[81],"employs":[83],"autoformalization":[84,151],"translate":[86],"reasoning":[87,138,160],"into":[88],"representations,":[90],"which":[91],"then":[93],"used":[94],"assess":[96],"validity.":[98],"Using":[99],"game-theoretic":[100],"scenarios":[101],"such":[102],"the":[104,111],"Prisoner's":[105],"Dilemma":[106],"testbeds,":[108],"highlight":[110],"limitations":[112],"both":[114],"less":[115],"capable":[116],"(Gemini":[117],"1.0":[118],"Pro)":[119],"advanced":[121],"(GPT4o)":[122],"generating":[125],"logically":[126],"sound":[127],"achieves":[130],"high":[131],"accuracy":[132,152],"error":[134],"detection":[135],"improves":[137],"correctness":[139],"via":[140],"self-refinement,":[141],"GPT-4o.":[144],"The":[145],"study":[146],"also":[147],"highlights":[148],"challenges":[149],"evaluation":[155],"inherently":[157],"ambiguous":[158],"tasks.":[161]},"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-12-15T00:00:00"}