{"id":"https://openalex.org/W7130536028","doi":"https://doi.org/10.1109/fllm67465.2025.11391251","title":"Reasoning Capabilities of Large Language Models on Dynamic Tasks","display_name":"Reasoning Capabilities of Large Language Models on Dynamic Tasks","publication_year":2025,"publication_date":"2025-11-25","ids":{"openalex":"https://openalex.org/W7130536028","doi":"https://doi.org/10.1109/fllm67465.2025.11391251"},"language":null,"primary_location":{"id":"doi:10.1109/fllm67465.2025.11391251","is_oa":false,"landing_page_url":"https://doi.org/10.1109/fllm67465.2025.11391251","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 3rd International Conference on Foundation and Large Language Models (FLLM)","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/A5010989991","display_name":"Annie Wong","orcid":"https://orcid.org/0000-0002-8698-974X"},"institutions":[{"id":"https://openalex.org/I121797337","display_name":"Leiden University","ror":"https://ror.org/027bh9e22","country_code":"NL","type":"education","lineage":["https://openalex.org/I121797337"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Annie Wong","raw_affiliation_strings":["Leiden University,Leiden Institute of Advanced Computer Science,Leiden,The Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Leiden University,Leiden Institute of Advanced Computer Science,Leiden,The Netherlands","institution_ids":["https://openalex.org/I121797337"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062646838","display_name":"Thomas B\u00e4ck","orcid":"https://orcid.org/0000-0001-6768-1478"},"institutions":[{"id":"https://openalex.org/I121797337","display_name":"Leiden University","ror":"https://ror.org/027bh9e22","country_code":"NL","type":"education","lineage":["https://openalex.org/I121797337"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Thomas B\u00e4ck","raw_affiliation_strings":["Leiden University,Leiden Institute of Advanced Computer Science,Leiden,The Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Leiden University,Leiden Institute of Advanced Computer Science,Leiden,The Netherlands","institution_ids":["https://openalex.org/I121797337"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126397451","display_name":"Aske Plaat","orcid":null},"institutions":[{"id":"https://openalex.org/I121797337","display_name":"Leiden University","ror":"https://ror.org/027bh9e22","country_code":"NL","type":"education","lineage":["https://openalex.org/I121797337"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Aske Plaat","raw_affiliation_strings":["Leiden University,Leiden Institute of Advanced Computer Science,Leiden,The Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Leiden University,Leiden Institute of Advanced Computer Science,Leiden,The Netherlands","institution_ids":["https://openalex.org/I121797337"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111231256","display_name":"Niki van Stein","orcid":null},"institutions":[{"id":"https://openalex.org/I121797337","display_name":"Leiden University","ror":"https://ror.org/027bh9e22","country_code":"NL","type":"education","lineage":["https://openalex.org/I121797337"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Niki van Stein","raw_affiliation_strings":["Leiden University,Leiden Institute of Advanced Computer Science,Leiden,The Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Leiden University,Leiden Institute of Advanced Computer Science,Leiden,The Netherlands","institution_ids":["https://openalex.org/I121797337"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5004203337","display_name":"Anna V. Kononova","orcid":"https://orcid.org/0000-0002-4138-7024"},"institutions":[{"id":"https://openalex.org/I121797337","display_name":"Leiden University","ror":"https://ror.org/027bh9e22","country_code":"NL","type":"education","lineage":["https://openalex.org/I121797337"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Anna V. Kononova","raw_affiliation_strings":["Leiden University,Leiden Institute of Advanced Computer Science,Leiden,The Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Leiden University,Leiden Institute of Advanced Computer Science,Leiden,The Netherlands","institution_ids":["https://openalex.org/I121797337"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I121797337"],"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":"765","last_page":"772"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.19249999523162842,"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":0.19249999523162842,"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":0.16830000281333923,"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/T12090","display_name":"Language and cultural evolution","score":0.08619999885559082,"subfield":{"id":"https://openalex.org/subfields/3316","display_name":"Cultural Studies"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/visual-reasoning","display_name":"Visual reasoning","score":0.6050999760627747},{"id":"https://openalex.org/keywords/heuristic","display_name":"Heuristic","score":0.603600025177002},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.5874999761581421},{"id":"https://openalex.org/keywords/language-understanding","display_name":"Language understanding","score":0.46939998865127563},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.3547999858856201},{"id":"https://openalex.org/keywords/modeling-language","display_name":"Modeling language","score":0.3393999934196472},{"id":"https://openalex.org/keywords/automated-reasoning","display_name":"Automated reasoning","score":0.3336000144481659},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.3176000118255615},{"id":"https://openalex.org/keywords/computational-model","display_name":"Computational model","score":0.3156999945640564}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.769599974155426},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.6050999760627747},{"id":"https://openalex.org/C173801870","wikidata":"https://www.wikidata.org/wiki/Q201413","display_name":"Heuristic","level":2,"score":0.603600025177002},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5874999761581421},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5291000008583069},{"id":"https://openalex.org/C2983448237","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Language understanding","level":2,"score":0.46939998865127563},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4025000035762787},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.3547999858856201},{"id":"https://openalex.org/C179603123","wikidata":"https://www.wikidata.org/wiki/Q1941921","display_name":"Modeling language","level":3,"score":0.3393999934196472},{"id":"https://openalex.org/C195344581","wikidata":"https://www.wikidata.org/wiki/Q2555318","display_name":"Automated reasoning","level":2,"score":0.3336000144481659},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.32249999046325684},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.3176000118255615},{"id":"https://openalex.org/C66024118","wikidata":"https://www.wikidata.org/wiki/Q1122506","display_name":"Computational model","level":2,"score":0.3156999945640564},{"id":"https://openalex.org/C89288958","wikidata":"https://www.wikidata.org/wiki/Q7301504","display_name":"Reasoning system","level":2,"score":0.31360000371932983},{"id":"https://openalex.org/C182365436","wikidata":"https://www.wikidata.org/wiki/Q50701","display_name":"Variable (mathematics)","level":2,"score":0.3001999855041504},{"id":"https://openalex.org/C127705205","wikidata":"https://www.wikidata.org/wiki/Q5748245","display_name":"Heuristics","level":2,"score":0.2904999852180481},{"id":"https://openalex.org/C2779439875","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Natural language understanding","level":3,"score":0.28929999470710754},{"id":"https://openalex.org/C103057564","wikidata":"https://www.wikidata.org/wiki/Q4751139","display_name":"Analytic reasoning","level":3,"score":0.2833000123500824},{"id":"https://openalex.org/C94922259","wikidata":"https://www.wikidata.org/wiki/Q33215","display_name":"Constructed language","level":2,"score":0.2687999904155731},{"id":"https://openalex.org/C83725634","wikidata":"https://www.wikidata.org/wiki/Q7268699","display_name":"Qualitative reasoning","level":2,"score":0.2655999958515167},{"id":"https://openalex.org/C86827895","wikidata":"https://www.wikidata.org/wiki/Q7098582","display_name":"Opportunistic reasoning","level":4,"score":0.265500009059906},{"id":"https://openalex.org/C155911833","wikidata":"https://www.wikidata.org/wiki/Q3817354","display_name":"Spatial intelligence","level":2,"score":0.26409998536109924},{"id":"https://openalex.org/C2776502983","wikidata":"https://www.wikidata.org/wiki/Q690182","display_name":"Contrast (vision)","level":2,"score":0.25870001316070557},{"id":"https://openalex.org/C2993724205","wikidata":"https://www.wikidata.org/wiki/Q315","display_name":"Human language","level":2,"score":0.25440001487731934},{"id":"https://openalex.org/C74672266","wikidata":"https://www.wikidata.org/wiki/Q815859","display_name":"Language acquisition","level":2,"score":0.25209999084472656},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.25099998712539673},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.25049999356269836}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/fllm67465.2025.11391251","is_oa":false,"landing_page_url":"https://doi.org/10.1109/fllm67465.2025.11391251","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 3rd International Conference on Foundation and Large Language Models (FLLM)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4931544363498688,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":7,"referenced_works":["https://openalex.org/W2889787757","https://openalex.org/W3160638507","https://openalex.org/W4389519896","https://openalex.org/W4391876619","https://openalex.org/W4402671652","https://openalex.org/W4404316964","https://openalex.org/W4406800520"],"related_works":[],"abstract_inverted_index":{"Large":[0],"language":[1,92,142,158],"models":[2,38,61,68,80,159],"excel":[3],"on":[4,62,81,187],"static":[5,209],"benchmarks,":[6],"but":[7,43,84],"their":[8],"ability":[9],"as":[10],"self-learning":[11],"agents":[12],"in":[13,148,199],"dynamic":[14,29,194],"environments":[15],"remains":[16],"unclear.":[17],"We":[18,34],"evaluate":[19],"three":[20],"prompting":[21,46,75,172],"strategies:":[22],"self-reflection,":[23],"heuristic":[24],"mutation,":[25],"and":[26,113,120,152,179],"planning":[27,151],"across":[28],"tasks":[30],"with":[31],"open-source":[32],"models.":[33,93],"find":[35,96],"that":[36,44,97,156,164],"larger":[37,67],"generally":[39],"outperform":[40],"smaller":[41,60,79],"ones,":[42],"strategic":[45],"can":[47,57,121],"close":[48],"this":[49],"performance":[50,110,125,144],"gap.":[51],"Second,":[52],"an":[53],"overly":[54],"long":[55],"prompt":[56],"negatively":[58],"impact":[59],"basic":[63],"reactive":[64],"tasks,":[65],"while":[66,105,180],"show":[69],"more":[70],"robust":[71],"behaviour.":[72],"Third,":[73],"advanced":[74,98],"techniques":[76],"primarily":[77],"benefit":[78],"complex":[82],"games,":[83],"offer":[85],"less":[86],"improvement":[87],"for":[88],"already":[89],"high-performing":[90],"large":[91,141,157],"Yet,":[94],"we":[95],"reasoning":[99,112,186,201],"methods":[100,181],"yield":[101],"highly":[102],"variable":[103],"outcomes:":[104],"capable":[106],"of":[107,136,215],"significantly":[108],"improving":[109],"when":[111],"decision-making":[114],"align,":[115],"they":[116],"also":[117],"introduce":[118],"instability":[119],"lead":[122],"to":[123,128,206,211],"big":[124],"drops.":[126],"Compared":[127],"human":[129],"performance,":[130],"our":[131,191],"findings":[132,192],"reveal":[133],"little":[134],"evidence":[135],"true":[137],"emergent":[138],"reasoning.":[139,216],"Instead,":[140],"model":[143],"exhibits":[145],"persistent":[146],"limitations":[147],"areas":[149],"like":[150,182],"spatial":[153],"coordination,":[154],"suggesting":[155],"still":[160],"suffer":[161],"fundamental":[162],"shortcomings":[163,198],"may":[165],"not":[166],"be":[167],"fully":[168],"overcome":[169],"through":[170],"self-reflective":[171],"alone.":[173],"Reasoning":[174],"is":[175],"a":[176,204],"multi-faceted":[177],"task,":[178],"Chain-of-thought":[183],"improve":[184],"multi-step":[185],"math":[188],"word":[189],"problems,":[190],"using":[193],"benchmarks":[195,210],"highlight":[196],"important":[197],"general":[200],"capabilities,":[202],"indicating":[203],"need":[205],"move":[207],"beyond":[208],"capture":[212],"the":[213],"complexity":[214]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2026-02-20T00:00:00"}