Reasoning Models papers, 2023–2026

Key findings

• Reasoning Models went from 470 papers in 2023 to 1,799 in 2026, roughly 3.8x in three years.
• NeurIPS publishes the most Reasoning Models work: 1,253 papers from 2023 to 2026, 36% of the four-venue total.
• The fastest-growing overlap is with Reinforcement Learning: papers tagged with both rose from 9 in 2023 to 437 in 2026.
• Among the 4 topics under Trending Systems, it ranks #3 by 2026 paper count; the fastest grower in the group, AI Agents, is up 12x versus 3.8x here.

Representative papers

Spread across years and venues so every edition shows up

• NeurIPS 2026A Mechanistic Analysis of Looped Reasoning Language Models
• ICML 2026A Formal Comparison Between Chain of Thought and Latent Thought
• ICLR 2026A Simple "Motivation" Can Enhance Reinforcement Finetuning of Large Reasoning Models
• CVPR 2026Asking like Socrates Socrates helps VLMs understand remote sensing images
• NeurIPS 2025A Frustratingly Simple Yet Highly Effective Attack Baseline: Over 90% Success Rate Against the Strong Black-box Models of GPT-4.5/4o/o1
• ICML 2025A Reasoning-Based Approach to Cryptic Crossword Clue Solving
• ICLR 2025A Formal Framework for Understanding Length Generalization in Transformers
• CVPR 2025Argus: Vision-Centric Reasoning with Grounded Chain-of-Thought
• NeurIPS 2024Are Large Language Models Good Statisticians?
• ICML 2024Algorithm of Thoughts: Enhancing Exploration of Ideas in Large Language Models
• ICLR 2024Amortizing intractable inference in large language models
• CVPR 2024Generate Subgoal Images before Act: Unlocking the Chain-of-Thought Reasoning in Diffusion Model for Robot Manipulation with Multimodal Prompts
• NeurIPS 2023A benchmark of categorical encoders for binary classification
• ICML 2023Can We Scale Transformers to Predict Parameters of Diverse ImageNet Models?
• ICLR 2023Automatic Chain of Thought Prompting in Large Language Models
• CVPR 2023ActMAD: Activation Matching To Align Distributions for Test-Time-Training
• NeurIPS 2026A Solvable Model of Chain-of-Thought in In-Context Learning
• ICML 2026A Narrowing Geometry in Contaminated Reasoning
• ICLR 2026A State-Transition Framework for Efficient LLM Reasoning
• CVPR 2026Beyond Weak Supervision MLLMs-Guided Graded Knowledge Distillation for Unsupervised Camouflaged

All Reasoning Models papers

1,253 papers, page 7 of 26

301. NeurIPS 2026Structured Sparse Memory for Recurrent Reasoning
302. NeurIPS 2026SWE-Chain: Benchmarking Coding Agents on Chained Release-Level Package Upgrades
303. NeurIPS 2026Taming CoT Obfuscation in VLMs: From Mechanistic Evidence to Activation-Level Enforcement
304. NeurIPS 2026TaskGround: Structured Executable Task Inference for Full-Scene Household Reasoning
305. NeurIPS 2026Tatemae: Detecting Alignment Faking via Tool Selection in LLMs
306. NeurIPS 2026Teach-to-Reason: Competition-Guided Reasoning with a Self-Improving Teacher
307. NeurIPS 2026Teaching Large Language Models When Not to Know: Learning Temporal Critique for Ex-Ante Reasoning
308. NeurIPS 2026Teaching VLMs What to Say, Not How to Reason: Rethinking Counterfactual Reasoning in Autonomous Driving
309. NeurIPS 2026Temporal Backtracking Search for Test-time Generative Video Reasoning
310. NeurIPS 2026TERMINATOR: Learning Optimal Exit Points for Early Stopping in Chain-of-Thought Reasoning
311. NeurIPS 2026Test Time Search Requires Training for Diversity
312. NeurIPS 2026Test time training enhances in-context learning of nonlinear functions
313. NeurIPS 2026Test-Time Compute Games
314. NeurIPS 2026Test-Time Graph Anomaly Detection via Shifted Augmentation with Dynamic Objective Scheduling
315. NeurIPS 2026Test-Time Prompt-Agnostic Decomposition
316. NeurIPS 2026Test-Time Scaling in the Wild: Why Exploitation, Not Exploration, Is the Bottleneck
317. NeurIPS 2026The Capability Frontier of GRPO
318. NeurIPS 2026The Communication Bottleneck: A Round-Trip Study of Compositional Serialization in Language Models
319. NeurIPS 2026Thinking with Images as Continuous Policy: Numerical Visual Chain-of-Thought
320. NeurIPS 2026Thinking with Imagination: Agentic Visual Spatial Reasoning with World Simulators
321. NeurIPS 2026Thinking with Visual Primitives
322. NeurIPS 2026ThinkJEPA: Empowering Latent World Models with Large Vision-Language Reasoning Model
323. NeurIPS 2026ThinkSafe: Self-Generated Safety Alignment for Reasoning Models
324. NeurIPS 2026TIDES: Implicit Time-Awareness in Selective State Space Models
325. NeurIPS 2026Tio: Language Models with Parallel Streams of Thoughts, Inputs and Outputs
326. NeurIPS 2026To Think or Not to Think: Pre-Decisional Reasoning Budgets for Referring Audio-Visual Segmentation
327. NeurIPS 2026TokenSwap: Benchmarking and Reducing the Modality Gap in Multimodal LLMs
328. NeurIPS 2026Tool Verification for Test-Time Reinforcement Learning
329. NeurIPS 2026Topological Periodicity Test (TopPT) via Confidence Bound of Time-Delay Embeddings
330. NeurIPS 2026Topology-Aware Optimal Transport for Source-Free Test-Time Adaptation in Anomaly Segmentation
331. NeurIPS 2026Toward Cognitive Supersensing in Multimodal Large Language Models
332. NeurIPS 2026Towards Error-Free EHRs: Reasoning-Intensive Consistency Verification Between Clinical Notes and Structured Tables in Electronic Health Records
333. NeurIPS 2026Towards Generalizable Data Valuation: Learning an End-to-end Deep Model to Compute Shapley Values
334. NeurIPS 2026Towards Principled Efficient Rollout Allocation in Test-Time Training
335. NeurIPS 2026Train at the Moving Edge: Rollout-Efficient RL for Large Reasoning Models
336. NeurIPS 2026Training on Documents About Monitoring Leads to CoT Obfuscation
337. NeurIPS 2026Training Quality Determines Efficiency Boundaries in Test-Time Reasoning
338. NeurIPS 2026Training with Harnesses: On-Policy Harness Self-Distillation for Complex Reasoning
339. NeurIPS 2026TTB: Test-time MLP Baking for Efficient Rendering of Decoder-only View Synthesis Models
340. NeurIPS 2026Understanding the Out-of-Distribution Generalization of Chain-of-Thought Reasoning in LLMs
341. NeurIPS 2026Uniform-in-Time Weak Propagation of Chaos in Shallow Neural Networks
342. NeurIPS 2026Unifying Reasoning and Planning through Energy Minimization
343. NeurIPS 2026UniPath: Adaptive Coordination of Understanding and Generation for Unified Multimodal Reasoning
344. NeurIPS 2026Universal and Efficient Computation with 2D Attention
345. NeurIPS 2026UniVLR: Unifying Text and Vision in Visual Latent Reasoning for Multimodal LLMs
346. NeurIPS 2026Value-Aware Stochastic KV Cache Eviction for Reasoning Models
347. NeurIPS 2026Vision to Geometry: 3D Spatial Memory for Sequential Embodied MLLM Reasoning and Exploration
348. NeurIPS 2026Visual Enhanced Depth Scaling for Multimodal Latent Reasoning
349. NeurIPS 2026Voronoi-Markov chain and spatial entropy for point pattern analysis
350. NeurIPS 2026Walking Through 3D Spaces: Spatial Routing for Referring 3D Gaussian Splatting Segmentation

FAQ

How many Reasoning Models papers were published at NeurIPS, ICLR, ICML and CVPR from 2023 to 2026?

3,512 in total: 470 in 2023, 311 in 2024, 932 in 2025, 1,799 in 2026.

How many Reasoning Models papers are at NeurIPS 2026?

NeurIPS 2026 has 361 Reasoning Models papers, versus 500 the year before.

How many Reasoning Models papers are at ICLR 2026?

ICLR 2026 has 652 Reasoning Models papers, versus 203 the year before.

How many Reasoning Models papers are at ICML 2026?

ICML 2026 has 582 Reasoning Models papers, versus 159 the year before.

How many Reasoning Models papers are at CVPR 2026?

CVPR 2026 has 204 Reasoning Models papers, versus 70 the year before.

Which conference publishes the most Reasoning Models papers?

NeurIPS, with 1,253 papers from 2023 to 2026.