RoboACE: Adversarial Co-Evolution for Robot Self-Improvement
cs.RO, cs.AI, cs.CV
Submitted: 2026-11-09
Updated: 2026-11-09
Code: https://github.com/DeLin1001/RoboACE
Terminology
Sources
- VoLo: A Physical Orchestrator for Open-Vocabulary Long-Horizon Manipulation
- DynaHarness: A Dynamic Physical Harness for Self-Evolving Robot Agents
- From VLM Planners to Robotic Agents: Self-Evolving Harnesses for History-Dependent Manipulation
- GenEnv: Difficulty-Aligned Co-Evolution Between LLM Agents and Environment Simulators
- Scaling Online Exploration for Robot Agents
- Cosmos Policy: Fine-Tuning Video Models for Visuomotor Control and Planning
- EmbodiedEvo: Self-Evolving Coding Agent For Physical Intelligence
- FastHarness: Experience-Driven Review Scheduling for Vision-Language-Action Policies
- ASPIRE: Agentic /Skills Discovery for Robotics
- Asymmetric self-play for automatic goal discovery in robotic manipulation
- EmbodiedRSI: Active Continual Robot Learning Through Hypothesis-Guided Co-Evolution
- Reconstruct, Practice, Go Real: Guided Self-Improvement for Embodied Agents
- RoboRSI: Stable, efficient, and reusable robot self-evolution in complex real-world environments
- Harness VLA: Steering Frozen VLAs into Reliable Manipulation Primitives via Memory-Guided Agents
- LIBERO-PRO: Towards Robust and Fair Evaluation of Vision-Language-Action Models Beyond Memorization
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