RLE-Bench: A Qualifying Exam for Coding Agents as Robot Learning Engineers

arXiv:2609.34210 · cs.RO · Submitted 2026-09-28 · Read on arXiv

cs.RO

Submitted: 2026-09-28

Updated: 2026-09-29

Comments: 28 pages, 17 figures. Project website: https://rle-bench.github.io/

Project page: https://rle-bench.github.io/ABSTRACT

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Benchmark — 35× in this paper · explained in 2 episodes
• Verifier — 22× in this paper · explained in 2 episodes
• Robustness — 9× in this paper · explained in 5 episodes
• Machine Learning Engineering — 5× in this paper
• Scaffolding — 5× in this paper · explained in 3 episodes
• Benchmarking — 4× in this paper · explained in 4 episodes
• Grounding — 4× in this paper · explained in 3 episodes
• Agent Harness — 3× in this paper · explained in 2 episodes
• Calibration — 3× in this paper · explained in 7 episodes
• Resource Constraints — 3× in this paper · explained in 4 episodes
• Abstraction — 2× in this paper · explained in 1 episode
• Closed-Loop Control — 2× in this paper · explained in 3 episodes
• Information Leakage — 2× in this paper · explained in 2 episodes
• Reinforcement Learning — 2× in this paper · explained in 4 episodes
• Reward Function — 2× in this paper · explained in 4 episodes
• Verification — 2× in this paper · explained in 2 episodes
• Visual Grounding — 2× in this paper · explained in 2 episodes
• Accuracy — 1× in this paper · explained in 1 episode
• Action Flow — 1× in this paper · explained in 1 episode
• Adaptation — 1× in this paper · explained in 1 episode
• Agentic System — 1× in this paper · explained in 2 episodes
• Embodied AI — 1× in this paper · explained in 2 episodes
• Reheating — 1× in this paper · explained in 2 episodes
• Reward Shaping — 1× in this paper · explained in 2 episodes
• Transformer — 1× in this paper · explained in 2 episodes

Sources

• $\pi_0$: A Vision-Language-Action Flow Model for General Robot Control
• OpenAI Gym
• RT-1: Robotics Transformer for Real-World Control at Scale
• RoboTwin 2.0: A Scalable Data Generator and Benchmark with Strong Domain Randomization for Robust Bimanual Robotic Manipulation
• RoboDojo: A Unified Sim-and-Real Benchmark for Comprehensive Evaluation of Generalist Robot Manipulation Policies
• RHO: Your Coding Agent is Secretly a Roboticist
• CaP-X: A Framework for Benchmarking and Improving Coding Agents for Robot Manipulation
• MLAgentBench: Evaluating Language Agents on Machine Learning Experimentation
• VoxPoser: Composable 3D Value Maps for Robotic Manipulation with Language Models
• Nautilus: From One Prompt to Plug-and-Play Robot Learning
• Isaac Lab: A GPU-Accelerated Simulation Framework for Multi-Modal Robot Learning
• RoboCasa: Large-Scale Simulation of Everyday Tasks for Generalist Robots
• ManiSkill3: GPU Parallelized Robotics Simulation and Rendering for Generalizable Embodied AI
• DeepMind Control Suite
• ENPIRE: Agentic Robot Policy Self-Improvement in the Real World
• World Action Models are Zero-shot Policies
• robosuite: A Modular Simulation Framework and Benchmark for Robot Learning

Related papers

• FMT x: An Efficient and Asymptotically Optimal Extension of the Fast Marching Tree for Dynamic Replanning
• MPCFormer: A physics-informed data-driven approach for explainable socially-aware autonomous driving
• RoboLab: A High-Fidelity Simulation Benchmark for Analysis of Task Generalist Policies
• ARC: A Reasoning Recipe for Robot Foundation Models
• HRDexDB: A 4D Dexterous Grasping Dataset Across Human and Multiple Robot Embodiments
• APT: Action Expert Pretraining Improves Instruction Generalization of Vision-Language-Action Policies