# Dual-Actor Fine-Tuning of VLA Models: A Talk-and-Tweak Human-in-the-Loop Approach

arXiv: https://arxiv.org/abs/2509.13774 · HTML: https://mlsanity.com/paper/2509.13774/

## Key facts

- Cited by 3 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 24 of its 27 references that are in the map.
- First posted on arXiv 17 Sep 2025.

## 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, 24 of 24)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [OpenVLA: An Open-Source Vision-Language-Action Model](https://mlsanity.com/paper/2406.09246/) (2024)
- [Diffusion Policy: Visuomotor Policy Learning via Action Diffusion](https://mlsanity.com/paper/2303.04137/) (2023)
- [π0: A Vision-Language-Action Flow Model for General Robot Control](https://mlsanity.com/paper/2410.24164/) (2024)
- [Consistency Models](https://mlsanity.com/paper/2303.01469/) (2023)
- [π0.5: a Vision-Language-Action Model with Open-World Generalization](https://mlsanity.com/paper/2504.16054/) (2025)
- [Octo: An Open-Source Generalist Robot Policy](https://mlsanity.com/paper/2405.12213/) (2024)
- [Supervised Contrastive Learning for Pre-trained Language Model Fine-tuning](https://mlsanity.com/paper/2011.01403/) (2020)
- [HG-DAgger: Interactive Imitation Learning with Human Experts](https://mlsanity.com/paper/1810.02890/) (2018)
- [Cal-QL: Calibrated Offline RL Pre-Training for Efficient Online Fine-Tuning](https://mlsanity.com/paper/2303.05479/) (2023)
- [SmolVLM: Redefining small and efficient multimodal models](https://mlsanity.com/paper/2504.05299/) (2025)
- [Grounding Large Language Models in Interactive Environments with Online Reinforcement Learning](https://mlsanity.com/paper/2302.02662/) (2023)
- [Precise and Dexterous Robotic Manipulation via Human-in-the-Loop Reinforcement Learning](https://mlsanity.com/paper/2410.21845/) (2024)
- [VLA-RL: Towards Masterful and General Robotic Manipulation with Scalable Reinforcement Learning](https://mlsanity.com/paper/2505.18719/) (2025)
- [Steering Your Diffusion Policy with Latent Space Reinforcement Learning](https://mlsanity.com/paper/2506.15799/) (2025)
- [ConRFT: A Reinforced Fine-tuning Method for VLA Models via Consistency Policy](https://mlsanity.com/paper/2502.05450/) (2025)
- [Yell At Your Robot: Improving On-the-Fly from Language Corrections](https://mlsanity.com/paper/2403.12910/) (2024)
- [From Imitation to Refinement -- Residual RL for Precise Assembly](https://mlsanity.com/paper/2407.16677/) (2024)
- [FLaRe: Achieving Masterful and Adaptive Robot Policies with Large-Scale Reinforcement Learning Fine-Tuning](https://mlsanity.com/paper/2409.16578/) (2024)
- [Boosting Continuous Control with Consistency Policy](https://mlsanity.com/paper/2310.06343/) (2023)
- [RLIF: Interactive Imitation Learning as Reinforcement Learning](https://mlsanity.com/paper/2311.12996/) (2023)
- [SRT-H: A Hierarchical Framework for Autonomous Surgery via Language Conditioned Imitation Learning](https://mlsanity.com/paper/2505.10251/) (2025)

## Built on by (most cited first, 3 of 3)

- [A Survey on Efficient Vision-Language-Action Models](https://mlsanity.com/paper/2510.24795/) (2025)
- [UniSteer: Unified Noise Steering for Efficient Human-Guided VLA Adaptation](https://mlsanity.com/paper/2605.10821/) (2026)
- [Keyframe-Guided Structured Rewards for Reinforcement Learning in Long-Horizon Laboratory Robotics](https://mlsanity.com/paper/2603.00719/) (2026)

## Abstract (arXiv)

Vision-language-action (VLA) models demonstrate strong generalization in robotic manipulation but face challenges in complex, real-world tasks. While supervised fine-tuning with demonstrations is constrained by data quality, reinforcement learning (RL) offers a promising alternative. We propose a human-in-the-loop dual-actor fine-tuning framework grounded in RL. The framework integrates a primary actor for robust multi-task performance with a refinement actor for latent-space adaptation. Beyond standard physical interventions, we introduce a lightweight talk-and-tweak scheme that converts human corrections into semantically grounded language commands, thereby generating a new dataset for policy learning. In real-world multi-task experiments, our approach achieves 100% success across three tasks within 101 minutes of online fine-tuning. For long-horizon tasks, it sustains a 50% success rate over 12 consecutive operations. Furthermore, the framework scales effectively to multi-robot training, achieving up to a 2 times improvement in efficiency when using dual robots. The experiment videos are available at https://sites.google.com/view/hil-daft/.