# Retrieve-then-Steer: Online Success Memory for Test-Time Adaptation of Generative VLAs

arXiv: https://arxiv.org/abs/2605.10094 · HTML: https://mlsanity.com/paper/2605.10094/

## Key facts

- Cited by 5 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 30 of its 32 references that are in the map.
- First posted on arXiv 11 May 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, 30 of 30)

- [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)
- [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)
- [RT-1: Robotics Transformer for Real-World Control at Scale](https://mlsanity.com/paper/2212.06817/) (2022)
- [π0.5: a Vision-Language-Action Model with Open-World Generalization](https://mlsanity.com/paper/2504.16054/) (2025)
- [Learning Fine-Grained Bimanual Manipulation with Low-Cost Hardware](https://mlsanity.com/paper/2304.13705/) (2023)
- [Octo: An Open-Source Generalist Robot Policy](https://mlsanity.com/paper/2405.12213/) (2024)
- [LIBERO: Benchmarking Knowledge Transfer for Lifelong Robot Learning](https://mlsanity.com/paper/2306.03310/) (2023)
- [Open X-Embodiment: Robotic Learning Datasets and RT-X Models](https://mlsanity.com/paper/2310.08864/) (2023)
- [FAST: Efficient Action Tokenization for Vision-Language-Action Models](https://mlsanity.com/paper/2501.09747/) (2025)
- [Evaluating Real-World Robot Manipulation Policies in Simulation](https://mlsanity.com/paper/2405.05941/) (2024)
- [CogACT: A Foundational Vision-Language-Action Model for Synergizing Cognition and Action in Robotic Manipulation](https://mlsanity.com/paper/2411.19650/) (2024)
- [LIBERO-Plus: In-depth Robustness Analysis of Vision-Language-Action Models](https://mlsanity.com/paper/2510.13626/) (2025)
- [HG-DAgger: Interactive Imitation Learning with Human Experts](https://mlsanity.com/paper/1810.02890/) (2018)
- [MemoryVLA: Perceptual-Cognitive Memory in Vision-Language-Action Models for Robotic Manipulation](https://mlsanity.com/paper/2508.19236/) (2025)
- [ConRFT: A Reinforced Fine-tuning Method for VLA Models via Consistency Policy](https://mlsanity.com/paper/2502.05450/) (2025)
- [Learning and Retrieval from Prior Data for Skill-based Imitation Learning](https://mlsanity.com/paper/2210.11435/) (2022)
- [Dita: Scaling Diffusion Transformer for Generalist Vision-Language-Action Policy](https://mlsanity.com/paper/2503.19757/) (2025)
- [A Vision-Language-Action-Critic Model for Robotic Real-World Reinforcement Learning](https://mlsanity.com/paper/2509.15937/) (2025)
- [ALOHA 2: An Enhanced Low-Cost Hardware for Bimanual Teleoperation](https://mlsanity.com/paper/2405.02292/) (2024)
- [RoboMonkey: Scaling Test-Time Sampling and Verification for Vision-Language-Action Models](https://mlsanity.com/paper/2506.17811/) (2025)
- [STRAP: Robot Sub-Trajectory Retrieval for Augmented Policy Learning](https://mlsanity.com/paper/2412.15182/) (2024)
- [Failure Prediction at Runtime for Generative Robot Policies](https://mlsanity.com/paper/2510.09459/) (2025)
- [Retrieval-Augmented Embodied Agents](https://mlsanity.com/paper/2404.11699/) (2024)
- [Verifier-free Test-Time Sampling for Vision-Language-Action Models](https://mlsanity.com/paper/2510.05681/) (2025)
- [Steering Vision-Language-Action Models as Anti-Exploration: A Test-Time Scaling Approach](https://mlsanity.com/paper/2512.02834/) (2025)
- [RoVer: Robot Reward Model as Test-Time Verifier for Vision-Language-Action Model](https://mlsanity.com/paper/2510.10975/) (2025)
- [Continually Evolving Skill Knowledge in Vision Language Action Model](https://mlsanity.com/paper/2511.18085/) (2025)
- [ExpReS-VLA: Specializing Vision-Language-Action Models Through Experience Replay and Retrieval](https://mlsanity.com/paper/2511.06202/) (2025)

## Built on by (most cited first, 5 of 5)

- [Imagining Recovery: Inference-Time Counterfactual Realignment for Vision-Language-Action Models](https://mlsanity.com/paper/2608.14822/) (2026)
- [Retrieve in Time, Correct in Frequency](https://mlsanity.com/paper/2608.04527/) (2026)
- [TraceFlow: Guiding Frozen Flow-Matching Robot Policies with Success and Failure Traces](https://mlsanity.com/paper/2609.20646/) (2026)
- [DataClaw0: Agentic Tailoring Multimodal Data from Raw Streams](https://mlsanity.com/paper/2606.21337/) (2026)
- [Sampling headroom is not selection gain: a compute-value audit of test-time scaling for video world models](https://mlsanity.com/paper/2609.13257/) (2026)

## Abstract (arXiv)

Vision-Language-Action (VLA) models show strong potential for general-purpose robotic manipulation, yet their closed-loop reliability often degrades under local deployment conditions. Existing evaluations typically treat test episodes as independent zero-shot trials. However, real robots often operate repeatedly in the same or slowly changing environments, where successful executions provide environment-verified evidence of reliable behavior patterns. We study this persistent-deployment setting, asking whether a partially competent frozen VLA can improve its reliability by reusing its successful test-time experience. We propose an online success-memory guided test-time adaptation framework for generative VLAs. During deployment, the robot stores progress-calibrated successful observation-action segments in a long-term memory. At inference, it retrieves state-relevant action chunks, filters inconsistent candidates via trajectory-level consistency, and aggregates them into an elite action prior. To incorporate this prior into action generation, we introduce confidence-adaptive prior guidance, which injects the elite prior into an intermediate state of the flow-matching action sampler and adjusts the guidance strength based on retrieval confidence. This design allows the frozen VLA to exploit environment-specific successful experience while preserving observation-conditioned generative refinement. This retrieve-then-steer mechanism enables lightweight, non-parametric test-time adaptation without requiring parameter updates. Simulation and real-world experiments show improved task success and closed-loop stability, especially in long-horizon and multi-stage tasks.