arXiv：cs.AI· Hongyu Shi, Sen Zhao, Zuyu Zhang, Lifeng Shen, Ding Zou, Xinyu He, Xu Zhang, Qinghua Zhang·· 4 小时前
FLOWMEM：为 VLA 模型重组与精炼潜在推理流
Recompose and Refine Latent Reasoning Flows for Vision-Language-Action Models
AI 导读
研究者提出 Reasoning and Flow Memory（FLOWMEM）VLA 模型，将执行成功的潜在计算转化为可复用的推理经验，动态检索并重组兼容的潜在片段，再结合当前视觉与本体感知证据精炼后生成动作。在 RoboMME 和 LIBERO-Plus 上，FLOWMEM 分别取得 48.0% 和 77.3% 的成功率，较无记忆策略提升 1.7 和 4.1 个百分点。
正文
Abstract:Latent reasoning enables vision-language-action (VLA) models to transform multimodal observations into task-relevant internal states before generating continuous robot actions. While existing methods learn to generate or refine such states for each policy query, they discard successful reasoning after execution and therefore reconstruct similar computation from scratch. We present Reasoning and Flow Memory (FLOWMEM), a unified VLA model that turns successful latent computation into reusable reasoning experience. Rather than appending a fixed retrieved context, FLOWMEM dynamically retrieves and recomposes compatible latent fragments as the embodied context evolves, forming a reasoning route that follows the temporal structure and progress of successful computation. The route is then refined using current visual and proprioceptive evidence before it conditions action generation. Experiments on RoboMME and LIBERO-Plus show that FLOWMEM attains 48.0% and 77.3% success, outperforming memory-free policies by 1.7 and 4.1 percentage points, respectively. These results demonstrate the value of reusing successful latent computation for closed-loop VLA control.
| Subjects: | Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2610.12090 [cs.AI] |
| (or arXiv:2610.12090v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2610.12090 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Sen Zhao [view email]
[v1]
Thu, 8 Oct 2026 15:00:34 UTC (487 KB)
来源：arXiv：cs.AI · arxiv.org