ACE-CaP-0: Real-World Code-as-Policies in the Era of Experience
cs.RO
Submitted: 2026-11-12
Updated: 2026-11-12
Project page: https://acerobotics2025.github.io/ACE-CaP/Demonstrations
Terminology
Sources
- $\pi_0$: A Vision-Language-Action Flow Model for General Robot Control
- World Action Models are Zero-shot Policies
- $\pi^{*}_{0.6}$: a VLA That Learns From Experience
- Agent as Policy for Robotic Manipulation
- Has GPT-6-Astra Achieved Embodied Intelligence?
- Make Code as Policy Great Again: Frontier Agents Write, Call, and Evolve Robot Tools
- ENPIRE: Agentic Robot Policy Self-Improvement in the Real World
- ASPIRE: Agentic /Skills Discovery for Robotics
- CaP-X: A Framework for Benchmarking and Improving Coding Agents for Robot Manipulation
- Encore: Few-Shot Agentic Discovery of Manipulation Strategies
- Embodied Turing Machines: Stateful Code for Robot Recursive Self-Improvement
- SimEX: Simulation-Integrated Robotics AutoResearch
- Robot Learning as an Empirical Science: Best Practices for Policy Evaluation
- In-Context Robot Learning with VLM Agents
- RAPID: Robot Agentic Programming from Demonstrations
- Evaluating Real-World Robot Manipulation Policies in Simulation
- RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control
- Scaling Online Exploration for Robot Agents
- CaPtain: A Pipeline for Post-Training Code-as-Policy Robot Agents
- Co-Evolving Robot Orchestrators and Policies through Deployment
Related papers
- Rethinking Actions: Continuity-Aware Priors for World-Model Planning
- MOSAIC: Modular Obstacle and Spatial-Aware Framework for Manipulation In Cluttered Scenes
- SAGAS: Semantic-Aware Graph-Assisted Stitching for Offline Temporal Logic Planning
- DexSeed: Expanding Human Hand-Object Interactions into Robot Demonstrations for Dexterous Policy Learning
- LaST0.5: A Generalist World Action Model with Interaction-Centric Latent Reasoning
- CIALLO: Learning Shared Intent Representations for Cross-Embodiment Manipulation