AdaEva: Accelerating LLM-Driven Algorithm Design with Adaptive Partial Evaluation
cs.LG, cs.NE
Submitted: 2026-10-02
Updated: 2026-10-02
Sources
- DEHB: Evolutionary Hyperband for Scalable, Robust and Efficient Hyperparameter Optimization
- AdaEvolve: Adaptive LLM Driven Zeroth-Order Optimization
- Qwen2.5-Coder Technical Report
- Janus: An Algorithm-Evaluator Co-Evolution Framework for LLM-Driven Discovery under Expensive Evaluation Budgets
- AlphaEvolve: A coding agent for scientific and algorithmic discovery
- Devstral: Fine-tuning Language Models for Coding Agent Applications
- Gemini: A Family of Highly Capable Multimodal Models
- Monte Carlo Tree Search for Comprehensive Exploration in LLM-Based Automatic Heuristic Design
- Dynamically Allocating Evaluation Effort for Model Ranking
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