{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,20]],"date-time":"2026-06-20T16:53:48Z","timestamp":1781974428978,"version":"3.54.5"},"reference-count":137,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"DOI":"10.13039\/501100000038","name":"Natural Sciences and Engineering Research Council","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100000038","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/access.2025.3632686","type":"journal-article","created":{"date-parts":[[2025,11,13]],"date-time":"2025-11-13T18:45:07Z","timestamp":1763059507000},"page":"195187-195225","source":"Crossref","is-referenced-by-count":1,"title":["Comparative Evaluation of Reasoning and Inference in LLM-Based and Diffusion-Based Approaches"],"prefix":"10.1109","volume":"13","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6664-5632","authenticated-orcid":false,"given":"Weimin","family":"Zhao","sequence":"first","affiliation":[{"name":"Department of Electrical, Computer and Software Engineering, Ontario Tech University, Oshawa, ON, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0472-5757","authenticated-orcid":false,"given":"Qusay H.","family":"Mahmoud","sequence":"additional","affiliation":[{"name":"Department of Electrical, Computer and Software Engineering, Ontario Tech University, Oshawa, ON, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"From LLM reasoning to autonomous AI agents: A comprehensive review","author":"Amine Ferrag","year":"2025","journal-title":"arXiv:2504.19678"},{"key":"ref2","article-title":"A survey of frontiers in LLM reasoning: Inference scaling, learning to reason, and agentic systems","author":"Ke","year":"2025","journal-title":"arXiv:2504.09037"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/3774896"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-025-11116-x"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1201\/9781351006620-6"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-15-4095-0_15"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1613\/jair.1.15348"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2022.03.003"},{"key":"ref9","article-title":"A comprehensive survey of LLM alignment techniques: RLHF, RLAIF, PPO, DPO and more","author":"Wang","year":"2024","journal-title":"arXiv:2407.16216"},{"key":"ref10","article-title":"Discrete diffusion in large language and multimodal models: A survey","author":"Yu","year":"2025","journal-title":"arXiv:2506.13759"},{"key":"ref11","article-title":"ChatGPT is not all you need. A state of the art review of large generative AI models","author":"Gozalo-Brizuela","year":"2023","journal-title":"arXiv:2301.04655"},{"key":"ref12","article-title":"Multimodal chain-of-thought reasoning: A comprehensive survey","author":"Wang","year":"2025","journal-title":"arXiv:2503.12605"},{"key":"ref13","article-title":"GenPRM: Scaling test-time compute of process reward models via generative reasoning","author":"Zhao","year":"2025","journal-title":"arXiv:2504.00891"},{"key":"ref14","article-title":"Thinking machines: A survey of LLM based reasoning strategies","author":"Bandyopadhyay","year":"2025","journal-title":"arXiv:2503.10814"},{"key":"ref15","article-title":"Beyond chain-of-thought: A survey of chain-of-x paradigms for LLMs","author":"Xia","year":"2024","journal-title":"arXiv:2404.15676"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/j.procs.2024.09.178"},{"key":"ref17","article-title":"Retrieval-augmented generation for large language models: A survey","author":"Gao","year":"2023","journal-title":"arXiv:2312.10997"},{"key":"ref18","article-title":"Diffusion models in vision: A survey","author":"Croitoru","year":"2022","journal-title":"arXiv:2209.04747"},{"key":"ref19","article-title":"Diffusion model-based image editing: A survey","author":"Huang","year":"2024","journal-title":"arXiv:2402.17525"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/3626235"},{"key":"ref21","article-title":"Denoising diffusion probabilistic models","author":"Ho","year":"2020","journal-title":"arXiv:2006.11239"},{"key":"ref22","first-page":"45","article-title":"Pixel-level BPE for auto-regressive image generation","volume-title":"Proc. 1st Workshop Perform. Interpretability Eval. Multimodal, Multipurpose, Massive-Scale Models","author":"Razzhigaev"},{"key":"ref23","first-page":"1057","article-title":"Policy gradient methods for reinforcement learning with function approximation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Sutton"},{"key":"ref24","volume-title":"AlphaEvolve: A Gemini-Powered Coding Agent for Designing Advanced Algorithms","year":"2025"},{"key":"ref25","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017","journal-title":"arXiv:1707.06347"},{"key":"ref26","first-page":"1889","article-title":"Trust region policy optimization","volume-title":"Proc. 32nd Int. Conf. Mach. Learn.","author":"Schulman"},{"key":"ref27","first-page":"27730","article-title":"Training language models to follow instructions with human feedback","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Ouyang"},{"key":"ref28","first-page":"1054","article-title":"Truly proximal policy optimization","volume-title":"Proc. 35th Uncertainty Artif. Intell. Conf.","author":"Wang"},{"key":"ref29","article-title":"Coordinated proximal policy optimization","author":"Wu","year":"2021","journal-title":"arXiv:2111.04051"},{"key":"ref30","article-title":"Behavior proximal policy optimization","author":"Zhuang","year":"2023","journal-title":"arXiv:2302.11312"},{"key":"ref31","article-title":"Pairwise proximal policy optimization: Harnessing relative feedback for LLM alignment","author":"Wu","year":"2023","journal-title":"arXiv:2310.00212"},{"key":"ref32","article-title":"RLAIF vs. RLHF: Scaling reinforcement learning from human feedback with AI feedback","author":"Lee","year":"2023","journal-title":"arXiv:2309.00267"},{"key":"ref33","article-title":"Constitutional AI: Harmlessness from AI feedback","author":"Bai","year":"2022","journal-title":"arXiv:2212.08073"},{"key":"ref34","volume-title":"Comparison Between RLHF and RLAIF in Fine-Tuning a Large Language Model","author":"H\u00f6glund","year":"2025"},{"key":"ref35","article-title":"Absolute zero: Reinforced self-play reasoning with zero data","author":"Zhao","year":"2025","journal-title":"arXiv:2505.03335"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1145\/3531146.3533229"},{"key":"ref37","first-page":"53728","article-title":"Direct preference optimization: Your language model is secretly a reward model","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Rafailov"},{"key":"ref38","article-title":"Is DPO superior to PPO for LLM alignment? A comprehensive study","author":"Xu","year":"2024","journal-title":"arXiv:2404.10719"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.592"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.630"},{"key":"ref41","article-title":"Token-level direct preference optimization","author":"Zeng","year":"2024","journal-title":"arXiv:2404.11999"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.297"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.1266"},{"key":"ref44","first-page":"129944","article-title":"\u03b2-DPO: Direct preference optimization with dynamic \u03b2","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Wu"},{"key":"ref45","article-title":"DeepSeek-r1: Incentivizing reasoning capability in LLMs via reinforcement learning","author":"Guo","year":"2025","journal-title":"arXiv:2501.12948"},{"key":"ref46","article-title":"R1-VL: Learning to reason with multimodal large language models via step-wise group relative policy optimization","author":"Zhang","year":"2025","journal-title":"arXiv:2503.12937"},{"key":"ref47","article-title":"Adaptive group policy optimization: Towards stable training and token-efficient reasoning","author":"Li","year":"2025","journal-title":"arXiv:2503.15952"},{"key":"ref48","article-title":"Hybrid group relative policy optimization: A multi-sample approach to enhancing policy optimization","author":"Sane","year":"2025","journal-title":"arXiv:2502.01652"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/icgtspicc.2016.7955308"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1007\/s11063-022-11055-6"},{"key":"ref51","article-title":"Algorithm discovery with LLMs: Evolutionary search meets reinforcement learning","author":"Surina","year":"2025","journal-title":"arXiv:2504.05108"},{"key":"ref52","article-title":"Does reinforcement learning really incentivize reasoning capacity in LLMs beyond the base model?","author":"Yue","journal-title":"arXiv:2504.13837"},{"key":"ref53","article-title":"Attention is all you need","author":"Vaswani","year":"2017","journal-title":"arXiv:1706.03762"},{"key":"ref54","article-title":"Chain-of-thought prompting elicits reasoning in large language models","author":"Wei","year":"2022","journal-title":"arXiv:2201.11903"},{"key":"ref55","article-title":"Automatic chain of thought prompting in large language models","author":"Zhang","year":"2022","journal-title":"arXiv:2210.03493"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72344-5_22"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1007\/s44336-024-00009-2"},{"key":"ref58","first-page":"1","article-title":"Faithful chain-of-thought reasoning","volume-title":"Proc. 13th Int. Joint Conf. Natural Lang. Process. 3rd Conf. Asia\u2013Pacific Chapter Assoc. Comput. Linguistics (IJCNLP-AACL)","author":"Lyu"},{"key":"ref59","article-title":"Self-consistency improves chain of thought reasoning in language models","author":"Wang","year":"2022","journal-title":"arXiv:2203.11171"},{"key":"ref60","article-title":"Text and patterns: For effective chain of thought, it takes two to tango","author":"Madaan","year":"2022","journal-title":"arXiv:2209.07686"},{"key":"ref61","article-title":"Chain of thoughtlessness? An analysis of CoT in planning","author":"Stechly","year":"2024","journal-title":"arXiv:2405.04776"},{"key":"ref62","article-title":"Towards revealing the mystery behind chain of thought: A theoretical perspective","author":"Feng","year":"2023","journal-title":"arXiv:2305.15408"},{"key":"ref63","article-title":"Tree of thoughts: Deliberate problem solving with large language models","author":"Yao","year":"2023","journal-title":"arXiv:2305.10601"},{"key":"ref64","article-title":"Large language model guided tree-of-thought","author":"Long","year":"2023","journal-title":"arXiv:2305.08291"},{"key":"ref65","article-title":"Tree of uncertain thoughts reasoning for large language models","author":"Mo","year":"2023","journal-title":"arXiv:2309.07694"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-emnlp.835"},{"key":"ref67","article-title":"Empowering multi-step reasoning across languages via tree-of-thoughts","author":"Ranaldi","year":"2023","journal-title":"arXiv:2311.08097"},{"key":"ref68","article-title":"Prompt-based Monte Carlo tree search for mitigating hallucinations in large models","author":"Duan","year":"2025","journal-title":"arXiv:2501.13942"},{"key":"ref69","article-title":"Monte Carlo tree search for comprehensive exploration in LLM-based automatic heuristic design","author":"Zheng","year":"2025","journal-title":"arXiv:2501.08603"},{"key":"ref70","article-title":"Alpha-SQL: Zero-shot text-to-SQL using Monte Carlo tree search","author":"Li","year":"2025","journal-title":"arXiv:2502.17248"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i16.29720"},{"key":"ref72","article-title":"Beyond chain-of-thought, effective graph-of-thought reasoning in language models","author":"Yao","year":"2023","journal-title":"arXiv:2305.16582"},{"key":"ref73","article-title":"Cumulative reasoning with large language models","author":"Zhang","year":"2023","journal-title":"arXiv:2308.04371"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.acl-long.1137"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-emnlp.206"},{"key":"ref76","article-title":"Reasoning to learn from latent thoughts","author":"Ruan","year":"2025","journal-title":"arXiv:2503.18866"},{"key":"ref77","article-title":"Training chain-of-thought via latent-variable inference","author":"Hoffman","year":"2023","journal-title":"arXiv:2312.02179"},{"key":"ref78","article-title":"Retrieval-augmented generation for knowledge-intensive NLP tasks","author":"Lewis","year":"2020","journal-title":"arXiv:2005.11401"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.495"},{"key":"ref80","article-title":"Self-RAG: Learning to retrieve, generate, and critique through self-reflection","author":"Asai","year":"2023","journal-title":"arXiv:2310.11511"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.naacl-long.389"},{"key":"ref82","article-title":"From local to global: A graph RAG approach to query-focused summarization","author":"Edge","year":"2024","journal-title":"arXiv:2404.16130"},{"key":"ref83","article-title":"Graphusion: A RAG framework for knowledge graph construction with a global perspective","author":"Yang","year":"2024","journal-title":"arXiv:2410.17600"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1145\/3701716.3715240"},{"key":"ref85","article-title":"GNN-RAG: Graph neural retrieval for large language model reasoning","author":"Mavromatis","year":"2024","journal-title":"arXiv:2405.20139"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/ISCEIC63613.2024.10810209"},{"key":"ref87","article-title":"Don\u2019t forget to connect! Improving RAG with graph-based reranking","author":"Dong","year":"2024","journal-title":"arXiv:2405.18414"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1145\/3616855.3635804"},{"key":"ref89","article-title":"Reasoning on graphs: Faithful and interpretable large language model reasoning","author":"Luo","year":"2023","journal-title":"arXiv:2310.01061"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1145\/3701716.3715490"},{"key":"ref91","article-title":"When to solve, when to verify: Compute-optimal problem solving and generative verification for LLM reasoning","author":"Singhi","year":"2025","journal-title":"arXiv:2504.01005"},{"key":"ref92","volume-title":"LatentPaint: Image Inpainting in Latent Space With Diffusion Models","author":"Corneanu","year":"2025"},{"key":"ref93","volume-title":"SmartBrush: Text and Shape Guided Object Inpainting With Diffusion Model","author":"Xie","year":"2025"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1109\/tmm.2024.3382484"},{"key":"ref95","first-page":"8038","article-title":"Structure matters: Tackling the semantic discrepancy in diffusion models for image inpainting","volume-title":"Proc. CVPR","author":"Liu"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612191"},{"key":"ref97","article-title":"DiffEdit: Diffusion-based semantic image editing with mask guidance","author":"Couairon","year":"2022","journal-title":"arXiv:2210.11427"},{"key":"ref98","first-page":"7430","article-title":"Prompt tuning inversion for text-driven image editing using diffusion models","volume-title":"Proc. CVPR","author":"Dong"},{"key":"ref99","first-page":"9452","article-title":"Inversion-free image editing with language-guided diffusion models","volume-title":"Proc. CVPR","author":"Xu"},{"key":"ref100","first-page":"22532","article-title":"EDICT: Exact diffusion inversion via coupled transformations","volume-title":"Proc. CVPR","author":"Wallace"},{"key":"ref101","first-page":"7280","article-title":"End-to-end diffusion latent optimization improves classifier guidance","volume-title":"Proc. ICCV","author":"Wallace"},{"key":"ref102","first-page":"2426","article-title":"DiffusionCLIP: Text-guided diffusion models for robust image manipulation","volume-title":"Proc. CVPR","author":"Kim"},{"key":"ref103","article-title":"Diffusion models beat GANs on image synthesis","author":"Dhariwal","year":"2021","journal-title":"arXiv:2105.05233"},{"key":"ref104","article-title":"Elucidating the design space of classifier-guided diffusion generation","author":"Ma","year":"2023","journal-title":"arXiv:2310.11311"},{"key":"ref105","article-title":"Classifier-free diffusion guidance","author":"Ho","year":"2022","journal-title":"arXiv:2207.12598"},{"key":"ref106","first-page":"18381","article-title":"Paint by example: Exemplar-based image editing with diffusion models","volume-title":"Proc. CVPR","author":"Yang"},{"key":"ref107","first-page":"6027","article-title":"SINE: Single image editing with text-to-image diffusion models","volume-title":"Proc. CVPR","author":"Zhang"},{"key":"ref108","first-page":"8839","article-title":"DragDiffusion: Harnessing diffusion models for interactive point-based image editing","volume-title":"Proc. CVPR","author":"Shi"},{"key":"ref109","article-title":"No training, no problem: Rethinking classifier-free guidance for diffusion models","author":"Sadat","year":"2024","journal-title":"arXiv:2407.02687"},{"key":"ref110","article-title":"High-resolution image synthesis with latent diffusion models","author":"Rombach","year":"2021","journal-title":"arXiv:2112.10752"},{"key":"ref111","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612200"},{"key":"ref112","first-page":"5432","article-title":"Personalized face inpainting with diffusion models by parallel visual attention","volume-title":"Proc. WACV","author":"Xu"},{"key":"ref113","first-page":"6007","article-title":"Imagic: Text-based real image editing with diffusion models","volume-title":"Proc. CVPR","volume":"23","author":"Kawar"},{"key":"ref114","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i7.32837"},{"key":"ref115","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2024.103928"},{"key":"ref116","article-title":"Denoising diffusion implicit models","author":"Song","year":"2020","journal-title":"arXiv:2010.02502"},{"key":"ref117","article-title":"Learning transferable visual models from natural language supervision","author":"Radford","year":"2021","journal-title":"arXiv:2103.00020"},{"key":"ref118","doi-asserted-by":"publisher","DOI":"10.7717\/peerj-cs.1905"},{"key":"ref119","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2023\/750"},{"key":"ref120","article-title":"Diffusion-LM improves controllable text generation","author":"Lisa Li","year":"2022","journal-title":"arXiv:2205.14217"},{"key":"ref121","article-title":"Latent diffusion for language generation","author":"Lovelace","year":"2022","journal-title":"arXiv:2212.09462"},{"key":"ref122","article-title":"Composable text controls in latent space with ODEs","author":"Liu","year":"2022","journal-title":"arXiv:2208.00638"},{"key":"ref123","article-title":"DiffuSeq: Sequence to sequence text generation with diffusion models","author":"Gong","year":"2022","journal-title":"arXiv:2210.08933"},{"key":"ref124","article-title":"Structured denoising diffusion models in discrete state-spaces","author":"Austin","year":"2021","journal-title":"arXiv:2107.03006"},{"key":"ref125","article-title":"DiffusionBERT: Improving generative masked language models with diffusion models","author":"He","year":"2022","journal-title":"arXiv:2211.15029"},{"key":"ref126","article-title":"Your absorbing discrete diffusion secretly models the conditional distributions of clean data","author":"Ou","year":"2024","journal-title":"arXiv:2406.03736"},{"key":"ref127","article-title":"Large language diffusion models","author":"Nie","year":"2025","journal-title":"arXiv:2502.09992"},{"key":"ref128","article-title":"Diffusion models are real-time game engines","author":"Valevski","year":"2024","journal-title":"arXiv:2408.14837"},{"key":"ref129","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i23.34674"},{"key":"ref130","article-title":"Ideas in inference-time scaling can benefit generative pre-training algorithms","author":"Song","year":"2025","journal-title":"arXiv:2503.07154"},{"key":"ref131","article-title":"LoRA: Low-rank adaptation of large language models","author":"Hu","year":"2021","journal-title":"arXiv:2106.09685"},{"key":"ref132","volume-title":"Designing for Inference in Future Generative Models-ProQuest","year":"2025"},{"key":"ref133","volume-title":"EBook-AI Inference: Balancing Cost, Latency, and Performance","year":"2025"},{"key":"ref134","article-title":"A survey on test-time scaling in large language models: What, how, where, and how well?","author":"Zhang","year":"2025","journal-title":"arXiv:2503.24235"},{"key":"ref135","doi-asserted-by":"publisher","DOI":"10.70777\/si.v2i6.15919"},{"key":"ref136","first-page":"96640","article-title":"Unveiling causal reasoning in large language models: Reality or mirage?","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Chi"},{"key":"ref137","doi-asserted-by":"publisher","DOI":"10.1016\/s0140-6736(25)00348-4"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6287639\/10820123\/11245490.pdf?arnumber=11245490","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,21]],"date-time":"2025-11-21T05:49:14Z","timestamp":1763704154000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11245490\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":137,"URL":"https:\/\/doi.org\/10.1109\/access.2025.3632686","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]}}}