{"id":"https://openalex.org/W7125218161","doi":"https://doi.org/10.48550/arxiv.2601.14053","title":"LLMOrbit: A Circular Taxonomy of Large Language Models -From Scaling Walls to Agentic AI Systems","display_name":"LLMOrbit: A Circular Taxonomy of Large Language Models -From Scaling Walls to Agentic AI Systems","publication_year":2026,"publication_date":"2026-01-20","ids":{"openalex":"https://openalex.org/W7125218161","doi":"https://doi.org/10.48550/arxiv.2601.14053"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2601.14053","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2601.14053","pdf_url":"https://arxiv.org/pdf/2601.14053","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2601.14053","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5035714586","display_name":"Badri N. Patro","orcid":"https://orcid.org/0000-0002-2585-7014","observed_orcids":["https://orcid.org/0000-0002-2585-7014"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Patro, Badri N.","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5055130710","display_name":"Vijay Srinivas Agneeswaran","orcid":"https://orcid.org/0009-0009-9891-7645","observed_orcids":["https://orcid.org/0009-0009-9891-7645"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Agneeswaran, Vijay S.","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":2,"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":0.8515999913215637,"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":0.8515999913215637,"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":0.1096000000834465,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.014399999752640724,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/large-language-models","display_name":"large language models","score":0.9779999852180481},{"id":"https://openalex.org/keywords/agentic-ai","display_name":"agentic AI","score":0.6510000228881836},{"id":"https://openalex.org/keywords/test-time-compute","display_name":"test-time compute","score":0.7139999866485596},{"id":"https://openalex.org/keywords/model-quantization","display_name":"model quantization","score":0.7749999761581421},{"id":"https://openalex.org/keywords/edge-computing","display_name":"edge computing","score":0.6890000104904175},{"id":"https://openalex.org/keywords/model-merging","display_name":"model merging","score":0.8299999833106995},{"id":"https://openalex.org/keywords/efficient-training","display_name":"efficient training","score":0.9459999799728394},{"id":"https://openalex.org/keywords/reinforcement-learning-from-human-feedback","display_name":"reinforcement learning from human feedback","score":0.7260000109672546},{"id":"https://openalex.org/keywords/kv-cache-compression","display_name":"KV cache compression","score":0.9800000190734863},{"id":"https://openalex.org/keywords/training-costs","display_name":"training costs","score":0.44200000166893005},{"id":"https://openalex.org/keywords/energy-consumption","display_name":"energy consumption","score":0.9350000023841858},{"id":"https://openalex.org/keywords/data-scarcity","display_name":"data scarcity","score":0.7820000052452087},{"id":"https://openalex.org/keywords/tool-using-agents","display_name":"tool-using agents","score":0.6850000023841858},{"id":"https://openalex.org/keywords/multi-agent-systems","display_name":"multi-agent systems","score":0.6740000247955322},{"id":"https://openalex.org/keywords/retrieval-augmented-generation","display_name":"retrieval-augmented generation","score":0.746999979019165},{"id":"https://openalex.org/keywords/open-source-llms","display_name":"open-source LLMs","score":0.7260000109672546}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7070000171661377},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.5121999979019165},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5090000033378601},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.48489999771118164},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47999998927116394},{"id":"https://openalex.org/C58642233","wikidata":"https://www.wikidata.org/wiki/Q8269924","display_name":"Taxonomy (biology)","level":2,"score":0.44780001044273376},{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.42160001397132874},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.40310001373291016},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3862000107765198},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.38370001316070557},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.382999986410141},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.37599998712539673},{"id":"https://openalex.org/C2742236","wikidata":"https://www.wikidata.org/wiki/Q924713","display_name":"Efficient energy use","level":2,"score":0.35749998688697815},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.3425999879837036},{"id":"https://openalex.org/C115537543","wikidata":"https://www.wikidata.org/wiki/Q165596","display_name":"Cache","level":2,"score":0.310699999332428},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.30140000581741333},{"id":"https://openalex.org/C177774035","wikidata":"https://www.wikidata.org/wiki/Q1246948","display_name":"Granularity","level":2,"score":0.2989000082015991},{"id":"https://openalex.org/C45493050","wikidata":"https://www.wikidata.org/wiki/Q7884934","display_name":"Unified Model","level":2,"score":0.2946999967098236},{"id":"https://openalex.org/C48659774","wikidata":"https://www.wikidata.org/wiki/Q4907197","display_name":"Bijection, injection and surjection","level":3,"score":0.29249998927116394},{"id":"https://openalex.org/C500882744","wikidata":"https://www.wikidata.org/wiki/Q269236","display_name":"Latent Dirichlet allocation","level":3,"score":0.2892000079154968},{"id":"https://openalex.org/C2776493592","wikidata":"https://www.wikidata.org/wiki/Q5158717","display_name":"Succinctness","level":2,"score":0.2802000045776367},{"id":"https://openalex.org/C2779439875","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Natural language understanding","level":3,"score":0.2793000042438507},{"id":"https://openalex.org/C2780165032","wikidata":"https://www.wikidata.org/wiki/Q16869822","display_name":"Energy consumption","level":2,"score":0.2696000039577484},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.26829999685287476},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.25780001282691956},{"id":"https://openalex.org/C2779808786","wikidata":"https://www.wikidata.org/wiki/Q6664603","display_name":"Locality","level":2,"score":0.2515000104904175},{"id":"https://openalex.org/C38935604","wikidata":"https://www.wikidata.org/wiki/Q4330363","display_name":"Stylized fact","level":2,"score":0.25130000710487366}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2601.14053","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2601.14053","pdf_url":"https://arxiv.org/pdf/2601.14053","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2601.14053","doi":"https://doi.org/10.48550/arxiv.2601.14053","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2601.14053","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2601.14053","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2601.14053","pdf_url":"https://arxiv.org/pdf/2601.14053","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7125218161.pdf","grobid_xml":"https://content.openalex.org/works/W7125218161.grobid-xml"},"referenced_works_count":94,"referenced_works":["https://openalex.org/W2242818861","https://openalex.org/W2581624817","https://openalex.org/W2736601468","https://openalex.org/W2795843265","https://openalex.org/W2798877128","https://openalex.org/W2896457183","https://openalex.org/W2896930824","https://openalex.org/W2940744433","https://openalex.org/W2988394319","https://openalex.org/W2997347790","https://openalex.org/W3001279689","https://openalex.org/W3006439205","https://openalex.org/W3015468748","https://openalex.org/W3034573343","https://openalex.org/W3083410900","https://openalex.org/W3168867926","https://openalex.org/W3174770825","https://openalex.org/W3177813494","https://openalex.org/W3206867351","https://openalex.org/W3210904070","https://openalex.org/W4221161695","https://openalex.org/W4224035735","https://openalex.org/W4281485151","https://openalex.org/W4281690148","https://openalex.org/W4283026156","https://openalex.org/W4283388932","https://openalex.org/W4304195432","https://openalex.org/W4306313145","https://openalex.org/W4307934016","https://openalex.org/W4310561894","https://openalex.org/W4310923309","https://openalex.org/W4311991106","https://openalex.org/W4312968147","https://openalex.org/W4319166707","https://openalex.org/W4320722432","https://openalex.org/W4320813768","https://openalex.org/W4322718191","https://openalex.org/W4327810158","https://openalex.org/W4366330503","https://openalex.org/W4379260375","https://openalex.org/W4381586770","https://openalex.org/W4384264726","https://openalex.org/W4384648484","https://openalex.org/W4384648639","https://openalex.org/W4384812233","https://openalex.org/W4384918448","https://openalex.org/W4385327683","https://openalex.org/W4385474529","https://openalex.org/W4385682136","https://openalex.org/W4385963839","https://openalex.org/W4385965642","https://openalex.org/W4386081870","https://openalex.org/W4387561453","https://openalex.org/W4387561528","https://openalex.org/W4387835442","https://openalex.org/W4388926373","https://openalex.org/W4388964563","https://openalex.org/W4388979610","https://openalex.org/W4389326242","https://openalex.org/W4389518760","https://openalex.org/W4390041933","https://openalex.org/W4390690464","https://openalex.org/W4390723197","https://openalex.org/W4391124766","https://openalex.org/W4391272793","https://openalex.org/W4391631327","https://openalex.org/W4392616695","https://openalex.org/W4392679398","https://openalex.org/W4393160302","https://openalex.org/W4395474395","https://openalex.org/W4399317953","https://openalex.org/W4401306886","https://openalex.org/W4402671236","https://openalex.org/W4402671950","https://openalex.org/W4402955413","https://openalex.org/W4403577621","https://openalex.org/W4404782689","https://openalex.org/W4404783473","https://openalex.org/W4405354744","https://openalex.org/W4405903187","https://openalex.org/W4409147637","https://openalex.org/W4414281281","https://openalex.org/W4414577520","https://openalex.org/W4415795271","https://openalex.org/W6910515245","https://openalex.org/W7133208539","https://openalex.org/W7133209886","https://openalex.org/W7133214447","https://openalex.org/W7133219754","https://openalex.org/W7133220558","https://openalex.org/W7133224126","https://openalex.org/W7133225605","https://openalex.org/W7133233472","https://openalex.org/W7133239970"],"related_works":["https://openalex.org/W7140086529","https://openalex.org/W7161603920","https://openalex.org/W7169195912","https://openalex.org/W7124262264","https://openalex.org/W7154587199","https://openalex.org/W7163695630","https://openalex.org/W7214972725","https://openalex.org/W4417122875","https://openalex.org/W4413933064","https://openalex.org/W4414500426"],"abstract_inverted_index":{"The":[0],"field":[1],"of":[2,29],"artificial":[3],"intelligence":[4],"has":[5],"undergone":[6],"a":[7,22],"revolution":[8,172],"from":[9,213],"foundational":[10],"Transformer":[11],"architectures":[12],"to":[13,83,216],"reasoning-capable":[14],"systems":[15],"approaching":[16],"human-level":[17],"performance.":[18],"We":[19,65,201],"present":[20],"LLMOrbit,":[21],"comprehensive":[23],"circular":[24],"taxonomy":[25],"navigating":[26],"the":[27,96],"landscape":[28],"large":[30],"language":[31],"models":[32,40,147],"spanning":[33],"2019-2025.":[34],"This":[35],"survey":[36],"examines":[37],"over":[38],"50":[39],"across":[41],"15":[42],"organizations":[43],"through":[44],"eight":[45],"interconnected":[46],"orbital":[47],"dimensions,":[48],"documenting":[49],"architectural":[50],"innovations,":[51],"training":[52,138],"methodologies,":[53],"and":[54,62,88,143,190,223],"efficiency":[55,171],"patterns":[56],"defining":[57],"modern":[58],"LLMs,":[59],"generative":[60],"AI,":[61],"agentic":[63],"systems.":[64],"identify":[66],"three":[67],"critical":[68],"crises:":[69],"(1)":[70,110,157],"data":[71],"scarcity":[72],"(9-27T":[73],"tokens":[74],"depleted":[75],"by":[76],"2026-2028),":[77],"(2)":[78,122,170],"exponential":[79],"cost":[80,131],"growth":[81],"($3M":[82],"$300M+":[84],"in":[85],"5":[86],"years),":[87],"(3)":[89,126,191],"unsustainable":[90],"energy":[91],"consumption":[92],"(22x":[93],"increase),":[94],"establishing":[95],"scaling":[97],"wall":[98],"limiting":[99],"brute-force":[100],"approaches.":[101],"Our":[102],"analysis":[103],"reveals":[104],"six":[105],"paradigms":[106],"breaking":[107],"this":[108],"wall:":[109],"test-time":[111],"compute":[112],"(o1,":[113],"DeepSeek-R1":[114,166],"achieve":[115],"GPT-4":[116,199],"performance":[117,186],"with":[118],"10x":[119],"inference":[120],"compute),":[121],"quantization":[123],"(4-8x":[124],"compression),":[125],"distributed":[127],"edge":[128],"computing":[129],"(10x":[130],"reduction),":[132],"(4)":[133],"model":[134],"merging,":[135],"(5)":[136],"efficient":[137],"(ORPO":[139],"reduces":[140],"memory":[141],"50%),":[142],"(6)":[144],"small":[145],"specialized":[146],"(Phi-4":[148],"14B":[149],"matches":[150],"larger":[151],"models).":[152],"Three":[153],"paradigm":[154],"shifts":[155],"emerge:":[156],"post-training":[158,225],"gains":[159],"(RLHF,":[160,206],"GRPO,":[161,209],"pure":[162],"RL":[163],"contribute":[164],"substantially,":[165],"achieving":[167],"79.8%":[168],"MATH),":[169],"(MoE":[173],"routing":[174],"18x":[175],"efficiency,":[176],"Multi-head":[177],"Latent":[178],"Attention":[179],"8x":[180],"KV":[181],"cache":[182],"compression":[183],"enables":[184],"GPT-4-level":[185],"at":[187],"$<$$0.30/M":[188],"tokens),":[189],"democratization":[192],"(open-source":[193],"Llama":[194],"3":[195],"88.6%":[196],"MMLU":[197],"surpasses":[198],"86.4%).":[200],"provide":[202],"insights":[203],"into":[204],"techniques":[205],"PPO,":[207],"DPO,":[208],"ORPO),":[210],"trace":[211],"evolution":[212],"passive":[214],"generation":[215],"tool-using":[217],"agents":[218],"(ReAct,":[219],"RAG,":[220],"multi-agent":[221],"systems),":[222],"analyze":[224],"innovations.":[226]},"counts_by_year":[{"year":2026,"cited_by_count":2}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-01-22T00:00:00"}