# SynthDemo-RL: Breaking the Zero-Reward Barrier in VLA Adaptation with LLM-Guided Synthetic Demonstrations

arXiv: https://arxiv.org/abs/2609.21650 · HTML: https://mlsanity.com/paper/2609.21650/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Reinforcement learning and post-training, one of 13 directions in Vision-language-action models.
- Builds on 28 of its 30 references that are in the map.
- First posted on arXiv 18 Sep 2026.

## Placed in

- Vision-language-action models / [Reinforcement learning and post-training](https://mlsanity.com/vla/reinforcement-learning-and-post-training/)

## Builds on (most cited first, 28 of 28)

- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [OpenVLA: An Open-Source Vision-Language-Action Model](https://mlsanity.com/paper/2406.09246/) (2024)
- [High-Dimensional Continuous Control Using Generalized Advantage Estimation](https://mlsanity.com/paper/1506.02438/) (2015)
- [π0.5: a Vision-Language-Action Model with Open-World Generalization](https://mlsanity.com/paper/2504.16054/) (2025)
- [LIBERO: Benchmarking Knowledge Transfer for Lifelong Robot Learning](https://mlsanity.com/paper/2306.03310/) (2023)
- [Fine-Tuning Vision-Language-Action Models: Optimizing Speed and Success](https://mlsanity.com/paper/2502.19645/) (2025)
- [Learning Complex Dexterous Manipulation with Deep Reinforcement Learning and Demonstrations](https://mlsanity.com/paper/1709.10087/) (2017)
- [Learning Quadrupedal Locomotion over Challenging Terrain](https://mlsanity.com/paper/2010.11251/) (2020)
- [Eureka: Human-Level Reward Design via Coding Large Language Models](https://mlsanity.com/paper/2310.12931/) (2023)
- [RoboTwin 2.0: A Scalable Data Generator and Benchmark with Strong Domain Randomization for Robust Bimanual Robotic Manipulation](https://mlsanity.com/paper/2506.18088/) (2025)
- [RoboCasa: Large-Scale Simulation of Everyday Tasks for Generalist Robots](https://mlsanity.com/paper/2406.02523/) (2024)
- [MimicGen: A Data Generation System for Scalable Robot Learning using Human Demonstrations](https://mlsanity.com/paper/2310.17596/) (2023)
- [RoboGen: Towards Unleashing Infinite Data for Automated Robot Learning via Generative Simulation](https://mlsanity.com/paper/2311.01455/) (2023)
- [LIBERO-PRO: Towards Robust and Fair Evaluation of Vision-Language-Action Models Beyond Memorization](https://mlsanity.com/paper/2510.03827/) (2025)
- [VLA-RL: Towards Masterful and General Robotic Manipulation with Scalable Reinforcement Learning](https://mlsanity.com/paper/2505.18719/) (2025)
- [Scaling Up and Distilling Down: Language-Guided Robot Skill Acquisition](https://mlsanity.com/paper/2307.14535/) (2023)
- [SimpleVLA-RL: Scaling VLA Training via Reinforcement Learning](https://mlsanity.com/paper/2509.09674/) (2025)
- [Self-Improving Vision-Language-Action Models with Data Generation via Residual RL](https://mlsanity.com/paper/2511.00091/) (2025)
- [VLA-RFT: Vision-Language-Action Reinforcement Fine-tuning with Verified Rewards in World Simulators](https://mlsanity.com/paper/2510.00406/) (2025)
- [ReWiND: Language-Guided Rewards Teach Robot Policies without New Demonstrations](https://mlsanity.com/paper/2505.10911/) (2025)
- [Robometer: Scaling General-Purpose Robotic Reward Models via Trajectory Comparisons](https://mlsanity.com/paper/2603.02115/) (2026)
- [GigaBrain-0: A World Model-Powered Vision-Language-Action Model](https://mlsanity.com/paper/2510.19430/) (2025)
- [GraspGen: A Diffusion-based Framework for 6-DOF Grasping with On-Generator Training](https://mlsanity.com/paper/2507.13097/) (2025)
- [RLinf-VLA: A Unified and Efficient Framework for Reinforcement Learning of Vision-Language-Action Models](https://mlsanity.com/paper/2510.06710/) (2025)
- [Refined Policy Distillation: From VLA Generalists to RL Experts](https://mlsanity.com/paper/2503.05833/) (2025)
- [Neural MP: A Generalist Neural Motion Planner](https://mlsanity.com/paper/2409.05864/) (2024)
- [Addressing the Orchestration Gap in Generalist Robots via Physical Agency](https://mlsanity.com/paper/2607.21725/) (2026)
- [Sequential Planning via Anchored Robotic Keypoints](https://mlsanity.com/paper/2606.30613/) (2026)

## Abstract (arXiv)

Fine-tuning Vision-Language-Action (VLA) models commonly relies on human teleoperation demonstrations, while reinforcement learning (RL) with sparse binary rewards faces an exploration challenge when successful trajectories are rarely sampled. We propose SynthDemo-RL, a teacher-student framework in which an automated teacher converts simulator-privileged state into successful manipulation trajectories, a VLA student is distilled from them by supervised fine-tuning (SFT), and PPO with binary task-success rewards refines the student. We study reward coverage, the fraction of tasks for which at least one success is observed under the fixed evaluation protocol, as a complement to the average success rate. On LIBERO-PRO, a public benchmark of perturbed LIBERO tasks for which no demonstrations exist, 27 of 57 scored tasks are at exactly 0% success for a pi_0.5 policy fine-tuned on the original LIBERO tasks. Direct PPO from this policy, under the same PPO recipe and the same RL compute as SynthDemo-RL's refinement stage, rescues 10 of these 27 tasks and leaves 17 at 0%. SynthDemo-RL, with 50 synthesized trajectories per task and no new human demonstrations, rescues all 27 and reaches average success rates of 97.8% and 97.1% on the Position and Task axes of LIBERO-PRO, respectively. On standard LIBERO, the same pipeline reaches 96.0% with no human demonstrations, within 1.7 points of pi_0.5 trained on 50 human demonstrations per task. We further validate the pipeline on RoboTwin 2.0 and verify that trajectories from a policy trained in a MuJoCo twin execute open-loop on a physical robot.