Review the Episodes, Refine the Lessons: Simple Memory Evolution for Embodied Agents
cs.RO, cs.AI, cs.LG
Submitted: 2026-11-08
Updated: 2026-11-08
Code: https://github.com/Awomo-WestlakeDI/Awomo-0.5
Project page: https://mmlab.hk/research/PhysicalRSI
Terminology
Sources
- RoboCat: A Self-Improving Generalist Agent for Robotic Manipulation
- 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
- Show-Harness: Just a VLM Agent Can Play Robots
- ASENA: Self-evolving Agents for Embodied Navigation
- In-Context Robot Learning with VLM Agents
- RHO: Your Coding Agent is Secretly a Roboticist
- CaP-X: A Framework for Benchmarking and Improving Coding Agents for Robot Manipulation
- HexaShell: A Universal Harness for Robot Coding Agents in Simulation and the Real World
- EBench: Elemental Diagnosis of Generalist Mobile Manipulation Policies
- Simple Baselines are Competitive with Code Evolution
- Transferring the Intelligence of VLMs to Robotic Control
- Video Prediction Policy 2: Predict Better, Act Better
- VISTA: A Visual Harness for Reasoning in an Interactive World
- VIA: Visual Interface Agent for Robot Control
- Embodied Turing Machines: Stateful Code for Robot Recursive Self-Improvement
- Scaling Online Exploration for Robot Agents
- Agent as Policy for Robotic Manipulation
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