Frontier coding agents surpass published Nature-family SOTA on only 17.8% of 90 sealed scientific tasks, mostly by recasting problems as supervised ML rather than inventing methods.
Canonical reference
Discovering faster matrix multiplication algorithms with reinforcement learning
Canonical reference. 80% of citing Pith papers cite this work as background.
11
Pith papers citing it
450
external citations · OpenAlex
Background
80% of classified citations
citation-role summary
background 4
baseline 1
citation-polarity summary
representative citing papers
Equivariant RL agent synthesizes near-optimal Clifford circuits up to 30 qubits with lower two-qubit gate counts than Qiskit baselines.
PMCTS is a new parallel MCTS variant that preserves formal policy improvement guarantees and scales with parallel compute, outperforming heuristic baselines in tested domains.
AI coding agents evolve simple ground-state protocols into improved versions for VQE, DMRG, and AFQMC on spin models and molecules by using executable energy scores under fixed compute budgets.
AlphaEvolve is an LLM-orchestrated evolutionary coding agent that discovered a 4x4 complex matrix multiplication algorithm using 48 scalar multiplications, the first improvement over Strassen's algorithm in 56 years, plus optimizations for Google data centers and hardware.
A rubric-guided GRPO pipeline fine-tunes a 7B LLM to synthesize quantum circuits achieving 3.31x T-gate compression with <1% hardware-constraint violations, validated on IBM and IonQ processors.
FalconGEMM delivers a framework with deployment, group-parallel execution, and analytical decision modules that makes lower-complexity matrix multiplication practical, beating cuBLAS and similar libraries by 7.59-17.85% on LLM tasks.
FactorLibrary stores reusable subexpressions to help RL agents (especially PPO+MCTS top-down) find certified optimal arithmetic circuits for polynomials up to complexity 8 at 91.8% success rate.
Human-AI collaboration expanded a meta-idea on rational approximation into sign-embedding quantum algorithms for matrix problems, with humans retaining final judgment on routes and refinements.
Exploits special structural features in tensor decompositions to lower the matrix multiplication exponent for 6x6 matrices from 2.8075 to 2.8019.
TSMCTS applies Sequential Monte Carlo in two stages for tree search, claiming better performance, favorable scaling with depth, lower variance, and reduced path degeneracy than SMC and modern MCTS baselines across discrete and continuous environments.
citing papers explorer
-
NatureBench: Can Coding Agents Match the Published SOTA of Nature-Family Papers?
Frontier coding agents surpass published Nature-family SOTA on only 17.8% of 90 sealed scientific tasks, mostly by recasting problems as supervised ML rather than inventing methods.
-
Equivariant Reinforcement Learning for Clifford Quantum Circuit Synthesis
Equivariant RL agent synthesizes near-optimal Clifford circuits up to 30 qubits with lower two-qubit gate counts than Qiskit baselines.
-
PMCTS: Particle Monte Carlo Tree Search for Principled Parallelized Inference Time Scaling
PMCTS is a new parallel MCTS variant that preserves formal policy improvement guarantees and scales with parallel compute, outperforming heuristic baselines in tested domains.
-
Optimizing ground state preparation protocols with autoresearch
AI coding agents evolve simple ground-state protocols into improved versions for VQE, DMRG, and AFQMC on spin models and molecules by using executable energy scores under fixed compute budgets.
-
AlphaEvolve: A coding agent for scientific and algorithmic discovery
AlphaEvolve is an LLM-orchestrated evolutionary coding agent that discovered a 4x4 complex matrix multiplication algorithm using 48 scalar multiplications, the first improvement over Strassen's algorithm in 56 years, plus optimizations for Google data centers and hardware.
-
RubriQ: Rubric-Guided Group Relative Policy Optimization for Constraint-Aware Quantum Circuit Synthesis
A rubric-guided GRPO pipeline fine-tunes a 7B LLM to synthesize quantum circuits achieving 3.31x T-gate compression with <1% hardware-constraint violations, validated on IBM and IonQ processors.
-
FalconGEMM: Surpassing Hardware Peaks with Lower-Complexity Matrix Multiplication
FalconGEMM delivers a framework with deployment, group-parallel execution, and analytical decision modules that makes lower-complexity matrix multiplication practical, beating cuBLAS and similar libraries by 7.59-17.85% on LLM tasks.
-
FactorLibrary: From Polynomials to Circuits via Recursive Subgoals
FactorLibrary stores reusable subexpressions to help RL agents (especially PPO+MCTS top-down) find certified optimal arithmetic circuits for polynomials up to complexity 8 at 91.8% success rate.
-
From Meta Idea to Advanced Mathematical Discovery -- Human-AI Co-Discovery of Sign-Embedding Quantum Algorithms
Human-AI collaboration expanded a meta-idea on rational approximation into sign-embedding quantum algorithms for matrix problems, with humans retaining final judgment on routes and refinements.
-
Exploiting the Structure in Tensor Decompositions for Matrix Multiplication
Exploits special structural features in tensor decompositions to lower the matrix multiplication exponent for 6x6 matrices from 2.8075 to 2.8019.
-
Twice Sequential Monte Carlo for Tree Search
TSMCTS applies Sequential Monte Carlo in two stages for tree search, claiming better performance, favorable scaling with depth, lower variance, and reduced path degeneracy than SMC and modern MCTS baselines across discrete and continuous environments.