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

469 papers, page 6 of 10

251. NeurIPS 2025Compositional Reasoning with Transformers, RNNs, and Chain of Thought
252. NeurIPS 2025Continuous Thought Machines
253. NeurIPS 2025Contrastive Representations for Temporal Reasoning
254. NeurIPS 2025Controlling Thinking Speed in Reasoning Models
255. NeurIPS 2025Counterfactual reasoning: an analysis of in-context emergence
256. NeurIPS 2025CPPO: Accelerating the Training of Group Relative Policy Optimization-Based Reasoning Models
257. NeurIPS 2025Creativity or Brute Force? Using Brainteasers as a Window into the Problem-Solving Abilities of Large Language Models
258. NeurIPS 2025Deliberation on Priors: Trustworthy Reasoning of Large Language Models on Knowledge Graphs
259. NeurIPS 2025Demystifying Reasoning Dynamics with Mutual Information: Thinking Tokens are Information Peaks in LLM Reasoning
260. NeurIPS 2025DisCO: Reinforcing Large Reasoning Models with Discriminative Constrained Optimization
261. NeurIPS 2025Diversity-Aware Policy Optimization for Large Language Model Reasoning
262. NeurIPS 2025DLoFT: Gradient-Decoupled Fine-Tuning for Generalizable Long Chain-of-Thought Reasoning
263. NeurIPS 2025Does Reinforcement Learning Really Incentivize Reasoning Capacity in LLMs Beyond the Base Model?
264. NeurIPS 2025Don’t Think Longer, Think Wisely: Optimizing Thinking Dynamics for Large Reasoning Models
265. NeurIPS 2025DreamPRM: Domain-reweighted Process Reward Model for Multimodal Reasoning
266. NeurIPS 2025DSRF: A Dynamic and Scalable Reasoning Framework for Solving RPMs
267. NeurIPS 2025DuetGraph: Coarse-to-Fine Knowledge Graph Reasoning with Dual-Pathway Global-Local Fusion
268. NeurIPS 2025DyFlow: Dynamic Workflow Framework for Agentic Reasoning
269. NeurIPS 2025DynaAct: Large Language Model Reasoning with Dynamic Action Spaces
270. NeurIPS 2025Efficiently Scaling LLM Reasoning Programs with Certaindex
271. NeurIPS 2025Enigmata: Scaling Logical Reasoning in Large Language Models with Synthetic Verifiable Puzzles
272. NeurIPS 2025EvaLearn: Quantifying the Learning Capability and Efficiency of LLMs via Sequential Problem Solving
273. NeurIPS 2025Evaluating the Inductive Abilities of Large Language Models: Why Chain-of-Thought Reasoning Sometimes Hurts More Than Helps
274. NeurIPS 2025Evolutionary Reasoning Does Not Arise in Standard Usage of Protein Language Models
275. NeurIPS 2025Execution Guided Line-by-Line Code Generation
276. NeurIPS 2025ExPO: Unlocking Hard Reasoning with Self-Explanation-Guided Reinforcement Learning
277. NeurIPS 2025Far from the Shallow: Brain-Predictive Reasoning Embedding through Residual Disentanglement
278. NeurIPS 2025First SFT, Second RL, Third UPT: Continual Improving Multi-Modal LLM Reasoning via Unsupervised Post-Training
279. NeurIPS 2025Flexible Realignment of Language Models
280. NeurIPS 2025From Euler to AI: Unifying Formulas for Mathematical Constants
281. NeurIPS 2025Generalizable Reasoning through Compositional Energy Minimization
282. NeurIPS 2025GPO: Learning from Critical Steps to Improve LLM Reasoning
283. NeurIPS 2025GRIP: A Graph-Based Reasoning Instruction Producer
284. NeurIPS 2025HARDMath2: A Benchmark for Applied Mathematics Built by Students as Part of a Graduate Class
285. NeurIPS 2025HELM: Hyperbolic Large Language Models via Mixture-of-Curvature Experts
286. NeurIPS 2025Heterogeneous Adversarial Play in Interactive Environments
287. NeurIPS 2025How Far Are We from Optimal Reasoning Efficiency?
288. NeurIPS 2025Hybrid Latent Reasoning via Reinforcement Learning
289. NeurIPS 2025Hybrid-Balance GFlowNet for Solving Vehicle Routing Problems
290. NeurIPS 2025Improve Temporal Reasoning in Multimodal Large Language Models via Video Contrastive Decoding
291. NeurIPS 2025Incentivizing Dual Process Thinking for Efficient Large Language Model Reasoning
292. NeurIPS 2025Incentivizing LLMs to Self-Verify Their Answers
293. NeurIPS 2025Incentivizing Reasoning for Advanced Instruction-Following of Large Language Models
294. NeurIPS 2025Ineq-Comp: Benchmarking Human-Intuitive Compositional Reasoning in Automated Theorem Proving of Inequalities
295. NeurIPS 2025IneqSearch: Hybrid Reasoning for Olympiad Inequality Proofs
296. NeurIPS 2025Is PRM Necessary? Problem-Solving RL Implicitly Induces PRM Capability in LLMs
297. NeurIPS 2025Knot So Simple: A Minimalistic Environment for Spatial Reasoning
298. NeurIPS 2025KTAE: A Model-Free Algorithm to Key-Tokens Advantage Estimation in Mathematical Reasoning
299. NeurIPS 2025Large Language Models Think Too Fast To Explore Effectively
300. NeurIPS 2025Latent Refinement via Flow Matching for Training-free Linear Inverse Problem Solving

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.