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 2 of 26

51. NeurIPS 2026CircuitSeer: Mining High-Quality Data by Probing Mathematical Reasoning Circuits in LLMs
52. NeurIPS 2026ClusQuant: Mitigating Outliers with Clustering-Based Representations for Low-Precision LRMs
53. NeurIPS 2026CME–SpectrumBench: Can LLMs Analyze Condensed Matter Spectral Data?
54. NeurIPS 2026Cognitive Firewalls: A Synthetic Account of Cross-Lingual Reasoning Collapse
55. NeurIPS 2026Collaborative Reasoning Distillation via Cross-Feedback and Coherent Curation
56. NeurIPS 2026Commit Then Explore: Reasoning Models Diversify, Not Converge
57. NeurIPS 2026Compute Aligned Training: Optimizing for Test Time Inference
58. NeurIPS 2026Compute Allocation Under Model-Provider Competition
59. NeurIPS 2026Compute Efficiency and Serial Runtime Tradeoffs for Stochastic Momentum Methods
60. NeurIPS 2026Compute-Optimal Pretrain--Fine-tune in Ridge Gradient Flow
61. NeurIPS 2026Concise Reasoning Through the Lens of Lagrangian Optimization
62. NeurIPS 2026Conditional misalignment: common interventions can hide emergent misalignment behind contextual triggers
63. NeurIPS 2026Confidence Estimation via Decoupled Smoothing for Dynamic LLM Routing and Aggregation
64. NeurIPS 2026Confidence-Calibrated Inference Expansion for Evaluator-Guided Test-Time Reasoning
65. NeurIPS 2026Consilience for Verifier-Free Test-Time Scaling
66. NeurIPS 2026Consolidating Reasoning with Test-Time Learning
67. NeurIPS 2026Context-Aware Autoregressive Image Generation for Emerging Reasoning Properties
68. NeurIPS 2026Contractive Restoring Flows: Robust Reasoning Distillation via Orbital Stability
69. NeurIPS 2026Contrastive Thinking Decoding: Steering Answer Generation in Reasoning Models
70. NeurIPS 2026ControlJEPA: Principled Trajectory Regularization via Lyapunov Tube Loss
71. NeurIPS 2026Controlling Temporal Pseudo-Label Marginals for Stable Online Test-Time Adaptation
72. NeurIPS 2026Convex Compositional Reasoning Models
73. NeurIPS 2026CoQuant: Covariance-Aware Rotation for 2-bit KV Cache Quantization
74. NeurIPS 2026CoRE-RL: Co-evolving Reasoning Trajectories and Evidence Subgraphs with Learned Evidence Projection
75. NeurIPS 2026Correct but Unselectable: The Hidden Interface Tax in Multi-Candidate Reasoning
76. NeurIPS 2026Corrupted Plans, Clean Traces: What Planning-Execution Decoupling Reveals About CoT Monitoring
77. NeurIPS 2026CoT-Guard: Small Models for Strong Monitoring
78. NeurIPS 2026CoTs as Probabilistic Programs: A Programmatic View of Thinking Step-by-Step in Language Models
79. NeurIPS 2026CoWorld-VLA: Thinking in a Multi-Expert World Model for Autonomous Driving
80. NeurIPS 2026CRANE: Constrained Reasoning Injection for Code Agents via Nullspace Editing
81. NeurIPS 2026Cross-Channel Agreement Beats Consensus: Compositional Verification for Geometry Reasoning
82. NeurIPS 2026Curriculum proof repair with learned counterexamples
83. NeurIPS 2026Data Diversity Drives the Emergence of Symbolic Mechanisms Supporting Abstract Reasoning
84. NeurIPS 2026Decoding the Critique Mechanism in Large Reasoning Models
85. NeurIPS 2026Decoupled Descent: Exact Test Error Tracking Via Approximate Message Passing
86. NeurIPS 2026DeltaPrompts: Escaping the Zero-Delta Trap in Multimodal Distillation
87. NeurIPS 2026Deployment-Memory LLM Test-Time Training Should Require Behavioral Evidence Beyond Perplexity
88. NeurIPS 2026Depth-Recurrent Attention Mixtures: Giving Latent Reasoning the Attention it Deserves
89. NeurIPS 2026Detect What You Need: Chain-of-Causal Reasoning for 3D Intent Grounding
90. NeurIPS 2026Diffusion Thinking for Fast Long-Form Spatial Reasoning in Vision--Language Models
91. NeurIPS 2026Distilling LLM Feedback for Lean Theorem Proving
92. NeurIPS 2026Do Deep Networks Forget Initialization? A Forgetting-Time View of Practical Inductive Bias
93. NeurIPS 2026Do Reasoning LLMs Refuse What They Infer in Long Contexts?
94. NeurIPS 2026Do Thinking Tokens Help with Safety?
95. NeurIPS 2026Does This Gradient Spark Joy?
96. NeurIPS 2026Early Signals, Strong Decisions: Prefix-Guided Sampling for Parallel Test-Time Scaling
97. NeurIPS 2026ECG-Reasoning-Benchmark: A Benchmark for Evaluating Clinical Reasoning Capabilities in ECG Interpretation
98. NeurIPS 2026Efficient Reasoning via Constrained Optimization in Latent Space
99. NeurIPS 2026Efficiently Representing Algorithms With Chain-of-Thought Transformers
100. NeurIPS 2026EmpathyChat: Structured Cognitive Reasoning in Empathetic Spoken Dialogue

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.