Finding Kissing Numbers with Game-theoretic Reinforcement Learning
cs.LG, cs.AI, math.CO, math.MG
Submitted: 2025-11-17
Updated: 2026-09-22
Code: https://github.com/CDM1619/PackingStar
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- Improved kissing numbers in seventeen through twenty-one dimensions
- AlphaEvolve: A coding agent for scientific and algorithmic discovery
- Optimality of spherical codes via exact semidefinite programming bounds
- Generative Language Modeling for Automated Theorem Proving
- DeepSeek-Prover: Advancing Theorem Proving in LLMs through Large-Scale Synthetic Data
- Gold-medalist Performance in Solving Olympiad Geometry with AlphaGeometry2
- $k$-point semidefinite programming bounds for equiangular lines
- Universal optimality of $T$-avoiding spherical codes and designs
Related papers
- Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
- AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
- Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
- Convergence issues in Relational Concept Analysis based on AOC-posets
- Beliefs Beyond Posteriors: Local-Consistency Optimisation for Bayesian Neural Networks
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks