arXiv Machine Learning June 4, 2026 By Esteban Real, Mirko Rossini, Connal de Souza, Manav Garg, Moritz Firsching, Quoc V. Le, Yao Chen, Akhil Verghese, Ekin Dogus Cubuk, David H. Park

AutoNumerics-Zero: Automated Discovery of State-of-the-Art Mathematical Functions

Read the original on arXiv Machine Learning →

arXiv:2312. 08472v2 Announce Type: replace-cross Abstract: Transcendental functions, such as the exponential, are central to scientific computing, yet they cannot be natively calculated by digital hardware.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

benchmarks

arXiv AI

Jun 10

ASyMOB: Algebraic Symbolic Mathematical Operations Benchmark

arXiv:2505. 23851v2 Announce Type: replace-cross Abstract: Large language models (LLMs) are increasingly applied to symbolic mathematics, yet existing evaluations often conflate pattern memorization with genuine reasoning.

By Michael Shalyt, Rotem Elimelech, Ido Kaminer

llms benchmarks

arXiv Machine Learning

Jun 10

Compile Once, Differentiate Everywhere: A Differentiable Meta-Circular Interpreter

arXiv:2606. 09930v1 Announce Type: cross Abstract: The boundary between program execution and gradient-based optimization has long limited the use of code itself as a learnable scientific model.

By Lucas Sheneman

llms

arXiv Machine Learning

Sep 4

Efficient Constant Optimization for Symbolic Regression with GPU-Accelerated Tree-Based Genetic Programming

The paper introduces a GPU-resident, batched Levenberg–Marquardt solver that efficiently optimizes constants in tree-based genetic programming for symbolic regression. By using reverse-mode automatic differentiation to assemble per-tree Jacobians in a single backward sweep, the solver’s per-iteration cost becomes independent of the number of constants per tree, achieving up to 510,000 trees per second on an NVIDIA A100. Integrated into EvoGP, the solver enables end-to-end search that recovers governing equations on 10 of 18 constructed problems, a significant improvement over stock EvoGP.

By Hao Mao, Xu Tony Liu, Shuai Lu, Peng Zhao, Wenzheng Jiang, Yuntian Chen

efficiency benchmarks

arXiv Machine Learning

Jun 9

Decomposable Neuro Symbolic Regression

arXiv:2511. 04124v3 Announce Type: replace Abstract: Symbolic regression (SR) models complex systems by discovering mathematical expressions that capture underlying relationships in observed data.

By Giorgio Morales, John W. Sheppard

llms benchmarks

arXiv Machine Learning

Jun 15

On the Generalization Bounds of Symbolic Regression with Genetic Programming

arXiv:2604. 17402v2 Announce Type: replace Abstract: Symbolic regression (SR) with genetic programming (GP) aims to discover interpretable mathematical expressions directly from data.

By Masahiro Nomura, Ryoki Hamano, Isao Ono

arXiv AI

Jun 24

ATHENA: Agentic Team for Hierarchical Evolutionary Numerical Algorithms

arXiv:2512. 03476v3 Announce Type: replace-cross Abstract: Progress in computational science depends on complex numerical workflows that must faithfully encode physical laws, yet translating conceptual insight into reliable code remains a major bottleneck.

By Juan Diego Toscano, Daniel T. Chen, George Em Karniadakis

llms agents reinforcement-learning benchmarks

One email a morning, machine-written

Related stories

ASyMOB: Algebraic Symbolic Mathematical Operations Benchmark

Compile Once, Differentiate Everywhere: A Differentiable Meta-Circular Interpreter

Efficient Constant Optimization for Symbolic Regression with GPU-Accelerated Tree-Based Genetic Programming

Decomposable Neuro Symbolic Regression

On the Generalization Bounds of Symbolic Regression with Genetic Programming

ATHENA: Agentic Team for Hierarchical Evolutionary Numerical Algorithms