Research Intelligence Mate ReviewsBriefingsTopics Sign in Request access
Topics · Automated Algorithm Discovery

Feedback and Reward Models for Algorithm Design

Execution feedback, process reward models, self-reflection, verbal gradients, unit tests, and trajectory scoring for improving generated algorithms

Track this topic →
Living review: Automated Algorithm Discovery
77 recent papers · updated 2026-09-03
Read the review →
Related topics in Automated Algorithm Discovery
Meta-Evolution Algorithm Evolution for Optimization GPU/TPU/NPU Kernel Evolution RL Tuning for Self-Improving Evolutionary Design Test-Time Training for Algorithm Design Agentic Algorithm Discovery Evolutionary Algorithm Design for Scientific Discovery Evolutionary Algorithm Design for Cloud and Systems Robustness and Generalization in Algorithm Discovery