AI Paper Atlas

Research map / Probabilistic and scientific modeling / Variational and generative sampling

LLM-Guided Evolutionary Program Synthesis for Quasi-Monte Carlo Design

Amir Sadikov

ICLR 2026 · Probabilistic and scientific modeling › Variational and generative sampling · approach: Sequential Monte Carlo for inference · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
evolve Sobol' direction numbers for dims 4-6 instead of Joe-Kuo parametersSobol' sequence · Asian option rQMC, training example, N=8192MSE: 4.523e-05 -> 4.104e-05Improved
evolved direction numbers, small sample sizesSobol' sequence · Asian option rQMC, N=32..256MSE: 0.2484 -> 0.2523 at N=32Hurt
evolved direction numbers, N>=512 on out-of-the-money optionSobol' sequence · Asian option out-of-the-money, N=1024MSE: 0.001457 -> 0.001313Improved
evolved direction numbers on in-the-money option, N=1024Sobol' sequence · Asian option in-the-moneyMSE: 0.000261 -> 0.000260 (p=0.2581)No clear effect
evolved direction numbers on Barrier optionsSobol' sequence · Barrier options, N>=512MSENo clear effect
evolved direction numbers on Lookback, Basket, Bermudan optionsSobol' sequence · exotic options, N>=512MSEImproved
LLM evolutionary search for 2D point sets N=100Fibonacci/MPMC/Clement · 2D point set N=100star discrepancy: 0.0188 -> 0.0150Improved
LLM evolutionary search for 2D N=16 versus known optimumClement et al. · 2D point set N=16star discrepancy: 0.0739 vs 0.0745Hurt
LLM search for 2D N=40Clement et al. · 2D point set N=40star discrepancy: 0.0332 -> 0.0331Improved
LLM search for 3D N=8Clement et al. · 3D point set N=8star discrepancy: 0.1875 vs 0.1937Hurt
add Phase 2 iterative numerical optimization after direct construction (ablation)LLM evolutionary search · 2D point set N=16star discrepancy: 0.0924 -> 0.0744Improved
add Phase 1 direct construction (tuned shifted Fibonacci lattice) over initial lattice (ablation)LLM evolutionary search · 2D point set N=16star discrepancy: 0.0962 -> 0.0924Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy