How Much Can Repeated Running Buy? A Measured Variance Ceiling for LLM Code Evaluation

arXiv:2606.00920 · cs.LG, cs.AI, cs.SE · Submitted 2026-05-30 · Read on arXiv

cs.LG, cs.AI, cs.SE

Submitted: 2026-05-30

Updated: 2026-10-10

Terminology

• Accuracy — 4× in this paper · explained in 1 episode
• Benchmark — 2× in this paper · explained in 2 episodes
• Large Language Model (LLM) — 1× in this paper · explained in 3 episodes

Sources

• Do Repetitions Matter? Strengthening Reliability in LLM Evaluations
• Non-Determinism of "Deterministic" LLM Settings
• Program Synthesis with Large Language Models
• Evaluating Large Language Models Trained on Code
• SOK: A Taxonomy of Attack Vectors and Defense Strategies for Agentic Supply Chain Runtime

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: The Predictive Cost of ELBO Binding
• Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks