Beyond Scripted Search: Sample-Efficient Reward Discovery via Agentic Black-box Optimization
cs.AI
Submitted: 2026-09-26
Updated: 2026-09-26
Code: https://github.com/eureka-research/Eureka
Terminology
Sources
- CodeEvolve: an open source evolutionary coding agent for algorithmic discovery and optimization
- RHO: Your Coding Agent is Secretly a Roboticist
- LLM and Simulation as Bilevel Optimizers: A New Paradigm to Advance Physical Scientific Discovery
- Isaac Gym: High Performance GPU-Based Physics Simulation For Robot Learning
- Isaac Lab: A GPU-Accelerated Simulation Framework for Multi-Modal Robot Learning
- AlphaEvolve: A coding agent for scientific and algorithmic discovery
- MemGPT: Towards LLMs as Operating Systems
- Evolving Agents in the Dark: Retrospective Harness Optimization via Self-Preference
- RL-VLM-F: Reinforcement Learning from Vision Language Foundation Model Feedback
- Reward Evolution with Graph-of-Thoughts: A Bi-Level Language Model Framework for Reinforcement Learning
- ReAct: Synergizing Reasoning and Acting in Language Models
- Language to Rewards for Robotic Skill Synthesis
- Learning Reward for Robot Skills Using Large Language Models via Self-Alignment
- EvoNav: Evolutionary Reward Function Design for Robot Navigation with Large Language Models
Related papers
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
- MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
- Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems
- VSAL: A Vision Solver with Adaptive Layouts for Graph Property Detection