# Find Something You Can't Do: Agentic Real-World Reinforcement Learning for Self-Improving VLA Models

arXiv: https://arxiv.org/abs/2609.32069 · HTML: https://mlsanity.com/paper/2609.32069/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Reinforcement learning and post-training, one of 13 directions in Vision-language-action models.
- Builds on 34 of its 40 references that are in the map.
- First posted on arXiv 25 Sep 2026.

## Placed in

- Vision-language-action models / [Reinforcement learning and post-training](https://mlsanity.com/vla/reinforcement-learning-and-post-training/)
- LLM agents and tool use / [Reinforcement learning for LLM agents](https://mlsanity.com/agents/reinforcement-learning-for-llm-agents/)

## Builds on (most cited first, 30 of 34)

- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control](https://mlsanity.com/paper/2307.15818/) (2023)
- [OpenVLA: An Open-Source Vision-Language-Action Model](https://mlsanity.com/paper/2406.09246/) (2024)
- [π0: A Vision-Language-Action Flow Model for General Robot Control](https://mlsanity.com/paper/2410.24164/) (2024)
- [Do As I Can, Not As I Say: Grounding Language in Robotic Affordances](https://mlsanity.com/paper/2204.01691/) (2022)
- [PaLM-E: An Embodied Multimodal Language Model](https://mlsanity.com/paper/2303.03378/) (2023)
- [π0.5: a Vision-Language-Action Model with Open-World Generalization](https://mlsanity.com/paper/2504.16054/) (2025)
- [Code as Policies: Language Model Programs for Embodied Control](https://mlsanity.com/paper/2209.07753/) (2022)
- [Inner Monologue: Embodied Reasoning through Planning with Language Models](https://mlsanity.com/paper/2207.05608/) (2022)
- [VoxPoser: Composable 3D Value Maps for Robotic Manipulation with Language Models](https://mlsanity.com/paper/2307.05973/) (2023)
- [Language to Rewards for Robotic Skill Synthesis](https://mlsanity.com/paper/2306.08647/) (2023)
- [Robots That Ask For Help: Uncertainty Alignment for Large Language Model Planners](https://mlsanity.com/paper/2307.01928/) (2023)
- [Randomized Ensembled Double Q-Learning: Learning Fast Without a Model](https://mlsanity.com/paper/2101.05982/) (2021)
- [Residual Reinforcement Learning for Robot Control](https://mlsanity.com/paper/1812.03201/) (2018)
- [Kimi K3: Open Frontier Intelligence](https://mlsanity.com/paper/2607.24653/) (2026)
- [Reset-Free Reinforcement Learning via Multi-Task Learning: Learning Dexterous Manipulation Behaviors without Human Intervention](https://mlsanity.com/paper/2104.11203/) (2021)
- [Leave no Trace: Learning to Reset for Safe and Autonomous Reinforcement Learning](https://mlsanity.com/paper/1711.06782/) (2017)
- [Self-Improving Vision-Language-Action Models with Data Generation via Residual RL](https://mlsanity.com/paper/2511.00091/) (2025)
- [Grounded Decoding: Guiding Text Generation with Grounded Models for Embodied Agents](https://mlsanity.com/paper/2303.00855/) (2023)
- [Residual Off-Policy RL for Finetuning Behavior Cloning Policies](https://mlsanity.com/paper/2509.19301/) (2025)
- [Robot Fine-Tuning Made Easy: Pre-Training Rewards and Policies for Autonomous Real-World Reinforcement Learning](https://mlsanity.com/paper/2310.15145/) (2023)
- [ASPIRE: Agentic /Skills Discovery for Robotics](https://mlsanity.com/paper/2607.00272/) (2026)
- [RL Token: Bootstrapping Online RL with Vision-Language-Action Models](https://mlsanity.com/paper/2604.23073/) (2026)
- [RLDG: Robotic Generalist Policy Distillation via Reinforcement Learning](https://mlsanity.com/paper/2412.09858/) (2024)
- [Fully Autonomous Real-World Reinforcement Learning with Applications to Mobile Manipulation](https://mlsanity.com/paper/2107.13545/) (2021)
- [Self-Improving Robots: End-to-End Autonomous Visuomotor Reinforcement Learning](https://mlsanity.com/paper/2303.01488/) (2023)
- [Autonomous Reinforcement Learning via Subgoal Curricula](https://mlsanity.com/paper/2107.12931/) (2021)
- [Practice Makes Perfect: Planning to Learn Skill Parameter Policies](https://mlsanity.com/paper/2402.15025/) (2024)
- [Demonstration-Bootstrapped Autonomous Practicing via Multi-Task Reinforcement Learning](https://mlsanity.com/paper/2203.15755/) (2022)
- [Robot Trains Robot: Automatic Real-World Policy Adaptation and Learning for Humanoids](https://mlsanity.com/paper/2508.12252/) (2025)

## Built on by (most cited first, 1 of 1)

- [AdaRSI: On-Demand Recursive Self-Improvement for Embodied Agents](https://mlsanity.com/paper/2610.20474/) (2026)

## Abstract (arXiv)

Vision--language--action (VLA) models provide strong priors for robotic manipulation but are typically deployed as frozen policies, unable to improve from their own failures. Real-world reinforcement learning (RL) offers a path to continued improvement, yet manual environment resets and task-success supervision hinder autonomous learning. We introduce FIND, an agentic real-world RL framework that closes the loop between scene understanding, weakness-aware practice, self-evaluation, and policy improvement in a persistent workspace. FIND reframes autonomous practice as a scene-conditioned, performance-aware task-selection problem: instead of restoring a predefined scene after each rollout, it uses the resulting scene to determine what to practice next. A vision--language agent identifies feasible tasks from a predefined library, prioritizes those with lower recent success rates, and evaluates outcomes using paired pre- and post-execution observations. We instantiate FIND with a frozen π0.5 VLA and residual off-policy RL. Across eight real-world manipulation tasks, the independent human-assessed success rate improves from 55% to 71.9%. A representative run completes 456 autonomous episodes within 6 hours of interaction, requiring 30 scene-recovery interventions and no human-provided reward labels during online learning. Ablations and systematic evaluations further examine key design choices, agent evaluation accuracy, and human intervention requirements. Our website is made publicly available at: FIND.github.io.