AtlasVA: 面向无教师VLM智能体的自进化视觉技能记忆

摘要

视觉语言模型智能体日益依赖记忆增强强化学习来在长周期任务中复用经验，然而现有多数框架将记忆存储为文本，并依赖专有教师模型来总结或精炼记忆。这种设计与空间决策任务不匹配：几何先验被压缩为有损语言，稀疏交互常通过延迟的文本反馈而非密集的视觉接地信号来监督。我们认为，视觉语言模型智能体可复用的经验应当保持视觉接地性。基于这一见解，我们提出AtlasVA——一种无教师的视觉技能记忆框架，将记忆组织为三个互补层次：空间热图、视觉范例和符号化文本技能。AtlasVA进一步从轨迹统计数据和轻量级网格启发式规则中直接演化出危险亲和力图谱，并将这些自演化图谱作为基于势能的塑形奖励用于强化学习。这在不依赖外部大语言模型监督的情况下，统一了感知、记忆与优化。在推箱子、冰冻湖、3D具身导航和3D机器人操作基准上的实验表明，AtlasVA始终优于以文本为中心的记忆基线和具有竞争力的视觉语言模型智能体，在空间密集型任务上尤其表现出显著优势。主页：https://wangpan-ustc.github.io/AtlasvaWeb

English

Vision-language model (VLM) agents increasingly rely on memory-augmented reinforcement learning to reuse experience across long-horizon tasks, yet most existing frameworks store memory as text and depend on proprietary teacher models to summarize or refine it. This design is poorly matched to spatial decision making: geometric priors are compressed into lossy language, and sparse interaction is often supervised through delayed textual feedback rather than dense visually grounded signals. We argue that reusable experience for VLM agents should remain visually grounded. Based on this insight, we propose AtlasVA, a teacher-free visual skill memory framework that organizes memory into three complementary layers: spatial heatmaps, visual exemplars, and symbolic text skills. AtlasVA further evolves danger and affinity atlases directly from trajectory statistics and lightweight grid heuristics, and reuses these self-evolving atlases as potential-based shaping rewards for reinforcement learning. This unifies perception, memory, and optimization without external LLM supervision. Experiments on Sokoban, FrozenLake, 3D embodied navigation, and 3D robotic manipulation benchmarks show that AtlasVA consistently outperforms text-centric memory baselines and competitive VLM agents, with especially strong gains on spatially intensive tasks. Homepage: https://wangpan-ustc.github.io/AtlasvaWeb