Mathematical Reasoning papers, 2023–2026

Key findings

• Mathematical Reasoning went from 57 papers in 2023 to 577 in 2026, roughly 10x in three years.
• NeurIPS publishes the most Mathematical Reasoning work: 469 papers from 2023 to 2026, 43% of the four-venue total.
• The fastest-growing overlap is with Reinforcement Learning: papers tagged with both rose from 3 in 2023 to 140 in 2026.
• Among the 5 topics under Neurosymbolic AI, it ranks #1 by 2026 paper count; the fastest grower in the group, Differentiable Reasoning, is up 2.5x versus 10x here.

Representative papers

Spread across years and venues so every edition shows up

• NeurIPS 2026A mathematical theory of balancing relational generalization and memorization
• ICML 2026ASyMOB: Algebraic Symbolic Mathematical Operations Benchmark
• ICLR 2026AutoGPS: Automated Geometry Problem Solving via Multimodal Formalization and Deductive Reasoning
• CVPR 2026Affine Perspective-Three-Point Problem
• NeurIPS 2025Are Language Models Efficient Reasoners? A Perspective from Logic Programming
• ICML 2025Autoformulation of Mathematical Optimization Models Using LLMs
• ICLR 2025Advancing Mathematical Reasoning in Language Models: The Impact of Problem-Solving Data, Data Synthesis Methods, and Training Stages
• CVPR 2025Bridging Viewpoint Gaps: Geometric Reasoning Boosts Semantic Correspondence
• NeurIPS 2024A Careful Examination of Large Language Model Performance on Grade School Arithmetic
• ICML 2024Accelerating Legacy Numerical Solvers by Non-intrusive Gradient-based Meta-solving
• ICLR 2024Don't Trust: Verify -- Grounding LLM Quantitative Reasoning with Autoformalization
• CVPR 2024E-GPS: Explainable Geometry Problem Solving via Top-Down Solver and Bottom-Up Generator
• NeurIPS 2023Evaluating and Improving Tool-Augmented Computation-Intensive Math Reasoning
• ICML 2023Automated Search for Conjectures on Mathematical Constants using Analysis of Integer Sequences
• ICLR 2023Differentiable Mathematical Programming for Object-Centric Representation Learning
• CVPR 2023Abstract Visual Reasoning: An Algebraic Approach for Solving Raven's Progressive Matrices
• NeurIPS 2026A Mechanistic Analysis of Looped Reasoning Language Models
• ICML 2026Beyond Theorem Proving: Formulation, Framework and Benchmark for Formal Problem-Solving
• ICLR 2026CogFlow: Bridging Perception and Reasoning through Knowledge Internalization for Visual Mathematical Problem Solving
• CVPR 2026Hilbert-Geo Solving Solid Geometric Problems by Neural-Symbolic Reasoning

All Mathematical Reasoning papers

113 papers, page 2 of 3

51. ICML 2026How RL Unlocks the Aha Moment in Geometric Interleaved Reasoning
52. ICML 2026How to Fine-Tune a Reasoning Model? A Teacher–Student Cooperation Framework to Synthesize Student-Consistent SFT Data
53. ICML 2026ImgCoT: Compressing Long Chain of Thought into Compact Visual Tokens for Efficient Reasoning of Large Language Model
54. ICML 2026Inducing Overthink: Hierarchical Genetic Algorithm-based DoS Attack on Black-Box Large Language Reasoning Models
55. ICML 2026Intervene When It Doubts: Conjunction-Guided Interactive Reasoning
56. ICML 2026Intra-Modal Neighbors Never Lie: Rectifying Inter-Modal Noisy Correspondence via Graph-Based Intra-Modal Reasoning
57. ICML 2026LatentChem: From Textual CoT to Latent Thinking in Chemical Reasoning
58. ICML 2026Learning Structured Reasoning via Tractable Trajectory Control
59. ICML 2026Learning to Theorize the World from Observation
60. ICML 2026Less Is More: Fast and Accurate Reasoning with Cross-Head Unified Sparse Attention
61. ICML 2026MathlibLemma: Folklore Lemma Generation and Benchmark for Formal Mathematics
62. ICML 2026Mind the Gap: Catching Hallucinations via Evidence Drop on the Reasoning Manifold
63. ICML 2026miniF2F-Dafny: LLM-Guided Mathematical Theorem Proving via Auto-Active Verification
64. ICML 2026Mitigating Premature Exploitation in Particle-based Monte Carlo for Inference-Time Scaling
65. ICML 2026MixReasoning: Switching Modes to Think
66. ICML 2026Non-Parametric Structural Priors for Geometry Theorem Prediction
67. ICML 2026On the Intrinsic Limits of Transformer Image Embeddings in Non-Solvable Spatial Reasoning
68. ICML 2026Optimal Self-Consistency for Efficient Reasoning with Large Language Models
69. ICML 2026Procedural Pretraining: Warming Up Language Models with Abstract Data
70. ICML 2026Prompt Optimization with Minimal Unlabeled Input via Meta-Reasoning
71. ICML 2026Provable Benefits of RLVR over SFT for Reasoning Models: Learning to Backtrack Efficiently
72. ICML 2026QEDBench: Quantifying the Alignment Gap in Automated Evaluation of University-Level Mathematical Proofs
73. ICML 2026Reasoning about Reasoning: BAPO Bounds on Chain-of-Thought Token Complexity in LLMs
74. ICML 2026Reasoning Models Are Test Exploiters: Rethinking Multiple Choice
75. ICML 2026Reasoning Quality Emerges Early: Data Curation for Reasoning Models
76. ICML 2026Reliable Thinking with Images
77. ICML 2026ReQAT: Achieving Full-Precision Reasoning Accuracy with 4-bit Floating-Point Quantization-Aware Training
78. ICML 2026ResRL: Boosting LLM Reasoning via Negative Sample Projection Residual Reinforcement Learning
79. ICML 2026Retro-Expert: Collaborative Reasoning for Interpretable Retrosynthesis
80. ICML 2026RL with Learnable Textual Feedback: A Bilevel Approach
81. ICML 2026RuCL: Stratified Rubric-Based Curriculum Learning for Multimodal Large Language Model Reasoning
82. ICML 2026Scalable Power Sampling: Unlocking Efficient, Training-Free Reasoning for LLMs via Distribution Sharpening
83. ICML 2026Scientific logicality enriched methodology for LLM reasoning: A practice in physics
84. ICML 2026Search for Truth from Reasoning: A Dynamic Representation Editing Framework for Steering LLM Trajectories
85. ICML 2026Sim2Reason: Solving Physics Olympiad via Reinforcement Learning on Physics Simulators
86. ICML 2026SmartThinker: Progressive Chain-of-Thought Length Calibration for Efficient Large Language Model Reasoning
87. ICML 2026Solving Inverse Problems with Flow-based Models via Model Predictive Control
88. ICML 2026Solving the Offline and Online Min-Max Problem of Non-smooth Submodular-Concave Functions: A Zeroth-Order Approach
89. ICML 2026SpecExit: Accelerating Large Reasoning Model via Speculative Exit
90. ICML 2026Statistical Early Stopping for Reasoning Models
91. ICML 2026Step-Level Sparse Autoencoder for Reasoning Process Interpretation
92. ICML 2026Strategy Executability in Mathematical Reasoning: Leveraging Human–Model Differences for Effective Guidance
93. ICML 2026The Geometry of Reasoning: Self-Evaluation via Layerwise Trajectory Evolution
94. ICML 2026The Power of Power Law: Asymmetry Enables Compositional Reasoning
95. ICML 2026The Quality-Utility Paradox: Why High-Reward Data Impairs Small Model Mathematical Reasoning
96. ICML 2026The Signal is in the Steps: Local Scoring for Reasoning Data Selection
97. ICML 2026The Two-Hump Problem: Bridging the Difficulty Gap in Mathematical Reinforcement Learning
98. ICML 2026Think Deep, Not Just Long: Measuring LLM Reasoning Effort via Deep-Thinking Tokens
99. ICML 2026Think-at-Hard: Selective Latent Iterations to Improve Reasoning Language Models
100. ICML 2026Thinking in Flow: A Dissipative Stabilization Operator for Robust Autoregressive Reasoning

FAQ

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

1,085 in total: 57 in 2023, 137 in 2024, 314 in 2025, 577 in 2026.

How many Mathematical Reasoning papers are at NeurIPS 2026?

NeurIPS 2026 has 208 Mathematical Reasoning papers, versus 190 the year before.

How many Mathematical Reasoning papers are at ICLR 2026?

ICLR 2026 has 175 Mathematical Reasoning papers, versus 61 the year before.

How many Mathematical Reasoning papers are at ICML 2026?

ICML 2026 has 113 Mathematical Reasoning papers, versus 45 the year before.

How many Mathematical Reasoning papers are at CVPR 2026?

CVPR 2026 has 81 Mathematical Reasoning papers, versus 18 the year before.

Which conference publishes the most Mathematical Reasoning papers?

NeurIPS, with 469 papers from 2023 to 2026.