Who Improves the Robot? Toward Physical Recursive Self-Improvement
cs.AI, cs.LG, cs.RO
Submitted: 2026-10-13
Updated: 2026-10-13
Code: https://github.com/SAIL-Research-Lab/Physical-RSI
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Sources
- CUPID: Curating Data your Robot Loves with Influence Functions
- Do As I Can, Not As I Say: Grounding Language in Robotic Affordances
- AutoRT: Embodied Foundation Models for Large Scale Orchestration of Robotic Agents
- EvoSkill: Automated Skill Discovery for Multi-Agent Systems
- $\pi^{*}_{0.6}$: a VLA That Learns From Experience
- Motus2: A Self-Evolving General World Model for Dexterous Manipulation
- $\pi_0$: A Vision-Language-Action Flow Model for General Robot Control
- Kintsugi: Learning Policies by Repairing Executable Knowledge Bases
- Closing the Sim-to-Real Loop: Adapting Simulation Randomization with Real World Experience
- Curating Demonstrations using Online Experience
- EvoTrainer: Co-Evolving LLM Policies and Training Harnesses for Autonomous Agentic Reinforcement Learning
- From Failed Trajectories to Reliable LLM Agents: Diagnosing and Repairing Harness Flaws
- Recursive Self-Improvement in AI: From Bounded Self-Refinement to Autonomous Research Loops
- SARM2: Multi-Task Stage Aware Reward Modeling for Self Improving Robotic Manipulation
- RoboDojo: A Unified Sim-and-Real Benchmark for Comprehensive Evaluation of Generalist Robot Manipulation Policies
- ConRFT: A Reinforced Fine-tuning Method for VLA Models via Consistency Policy
- Dual-Evolving Reinforcement Learning for Automated Reward Design
- Diffusion Policy: Visuomotor Policy Learning via Action Diffusion
- Scaling Sim-to-Real VLA Reinforcement Learning with Generative 3D Worlds
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
- Agents' Last Exam
- 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