From Search to Signal: Online Post-Training in Automatic Heuristic Design
cs.LG, cs.AI, cs.NE
Submitted: 2026-09-30
Updated: 2026-09-30
Sources
- Training Verifiers to Solve Math Word Problems
- Reinforced Self-Training (ReST) for Language Modeling
- Evolution Fine-Tuning: Learning to Discover Across 371 Optimization Tasks
- LLM4AD: A Platform for Algorithm Design with Large Language Model
- AHD Agent: Agentic Reinforcement Learning for Automatic Heuristic Design
- AlphaEvolve: A coding agent for scientific and algorithmic discovery
- DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
- PACEvolve++: Improving Test-time Learning for Evolutionary Search Agents
- HeurAgenix: Leveraging LLMs for Solving Complex Combinatorial Optimization Challenges
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