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

1,085 papers, page 5 of 22

201. ICLR 2026Reasoning Language Model Inference Serving Unveiled: An Empirical Study
202. ICLR 2026Reasoning Models Can be Accurately Pruned Via Chain-of-Thought Reconstruction
203. ICLR 2026Reasoning Scaffolding: Distilling the Flow of Thought from LLMs
204. ICLR 2026ReForm: Reflective Autoformalization with Prospective Bounded Sequence Optimization
205. ICLR 2026Reinforced Latent Reasoning for LLM-based Recommendation
206. ICLR 2026Reinforcement Mid-Training
207. ICLR 2026Reliable Fine-Grained Evaluation of Natural Language Math Proofs
208. ICLR 2026Rethinking LLM Reasoning: From Explicit Trajectories to Latent Representations
209. ICLR 2026Rewriting Pre-Training Data Boosts LLM Performance in Math and Code
210. ICLR 2026RFEval: Benchmarking Reasoning Faithfulness under Counterfactual Reasoning Intervention in Large Reasoning Models
211. ICLR 2026RLAD: Training LLMs to Discover Abstractions for Solving Reasoning Problems
212. ICLR 2026RLP: Reinforcement as a Pretraining Objective
213. ICLR 2026RLVMR: Reinforcement Learning with Verifiable Meta-Reasoning Rewards for Robust Long-Horizon Agents
214. ICLR 2026RM-R1: Reward Modeling as Reasoning
215. ICLR 2026Sample Smart, Not Hard: Correctness-First Decoding for Better Reasoning in LLMs
216. ICLR 2026Scaf-GRPO: Scaffolded Group Relative Policy Optimization for Enhancing LLM Reasoning
217. ICLR 2026Scalable Chain of Thoughts via Elastic Reasoning
218. ICLR 2026Scheduling Your LLM Reinforcement Learning with Reasoning Trees
219. ICLR 2026Segment-Level Attribution for Selective Learning of Long Reasoning Traces
220. ICLR 2026Selection, Reflection and Self-Refinement: Revisit Reasoning Tasks via a Causal Lens
221. ICLR 2026Self-Jailbreaking: Language Models Can Reason Themselves Out of Safety Alignment After Benign Reasoning Training
222. ICLR 2026Self-Refining Vision Language Model for Robotic Failure Detection and Reasoning
223. ICLR 2026SIM-CoT: Supervised Implicit Chain-of-Thought
224. ICLR 2026SLM-MUX: Orchestrating Small Language Models for Reasoning
225. ICLR 2026Slow-Fast Policy Optimization: Reposition-Before-Update for LLM Reasoning
226. ICLR 2026Smarter Not Harder: Generative Process Evaluation with Intrinsic-Signal Driving and Ability‑Adaptive Reward Shaping
227. ICLR 2026Soft Tokens, Hard Truths
228. ICLR 2026Solving the 2-norm k-hyperplane clustering problem via multi-norm formulations
229. ICLR 2026Stabilizing Policy Gradients for Sample-Efficient Reinforcement Learning in LLM Reasoning
230. ICLR 2026STITCH: Simultaneous Thinking and Talking with Chunked Reasoning for Spoken Language Models
231. ICLR 2026Strategic Obfuscation of Deceptive Reasoning in Language Models
232. ICLR 2026StreamingThinker: Large Language Models Can Think While Reading
233. ICLR 2026SwiReasoning: Switch-Thinking in Latent and Explicit for Pareto-Superior Reasoning LLMs
234. ICLR 2026T1: Tool-integrated Verification for Test-time Compute Scaling in Small Language Models
235. ICLR 2026TaTToo: Tool-Grounded Thinking PRM for Test-Time Scaling in Tabular Reasoning
236. ICLR 2026The First Impression Problem: Internal Bias Triggers Overthinking in Reasoning Models
237. ICLR 2026The Open Proof Corpus: A Large-Scale Study of LLM-Generated Mathematical Proofs
238. ICLR 2026THE PATH OF LEAST RESISTANCE: GUIDING LLM REASONING TRAJECTORIES WITH PREFIX CONSENSUS
239. ICLR 2026Think in Parallel, Answer as One: Logit Averaging for Open-Ended Reasoning
240. ICLR 2026Thinking on the Fly: Test-Time Reasoning Enhancement via Latent Thought Policy Optimization
241. ICLR 2026ThinkMorph: Emergent Properties in Multimodal Interleaved Chain-of-Thought Reasoning
242. ICLR 2026Token Hidden Reward: Steering Exploration-Exploitation in Group Relative Deep Reinforcement Learning
243. ICLR 2026TokUR: Token-Level Uncertainty Estimation for Large Language Model Reasoning
244. ICLR 2026Towards Quantization-Aware Training for Ultra-Low-Bit Reasoning LLMs
245. ICLR 2026Towards Safe Reasoning in Large Reasoning Models via Corrective Intervention
246. ICLR 2026Tracing the Traces: Latent Temporal Signals for Efficient and Accurate Reasoning
247. ICLR 2026Training Large Language Models To Reason In Parallel With Global Forking Tokens
248. ICLR 2026Training Large Reasoning Models Efficiently via Progressive Thought Encoding
249. ICLR 2026TRIM: Hybrid Inference via Targeted Stepwise Routing in Multi-Step Reasoning Tasks
250. ICLR 2026VERINA: Benchmarking Verifiable Code Generation

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.