# Spatial Memory Agent：用经验记忆提升冻结VLM空间推理

- 来源：HuggingFace Daily Papers（社区热门论文）
- 发布时间：2026-08-13 08:00
- AIHOT 分数：49
- AIHOT 链接：https://aihot.virxact.com/items/cmssf8hxr05tgrod0zndi98mn
- 原文链接：https://arxiv.org/abs/2608.12743

## AI 摘要

Spatial Memory Agent（SMA）提出一种无需参数更新的空间推理自进化框架，通过验证器引导的反思将空间经验蒸馏为可迁移教训，并分配可校准的迁移可靠性评分（TRS）。在五个空间基准和四个基础VLM上，SMA在每个基础模型组中均取得最高宏平均准确率，在20项评测中多数达到最佳精度，为冻结模型的空间自进化提供了实用路径。

## 正文

Spatial intelligence is becoming a foundation for embodied agents, robotic planning, and multimodal assistants. To improve the spatial reasoning ability of VLM agents, existing work has mainly followed two lines. One line uses post-training methods, such as supervised fine-tuning and reinforcement learning. Another line adopts an agentic paradigm in which the model calls external spatial tools, such as depth estimation and 3D reconstruction tools, to gather intermediate spatial evidence. We study a complementary and underexplored route: Can a frozen VLM agent improve its spatial reasoning through parameter-update-free self-evolution, without depending on external expert spatial tools at inference time? We present Spatial Memory Agent (SMA), an experience-grounded runtime framework that converts verified spatial experience into reusable transferable lessons. In a verifiable spatial environment, SMA queries the frozen VLM, obtains a predicted answer and reward, and uses verifier-guided reflection to distill compact transferable lessons from spatial experience. SMA further assigns each lesson a Transfer Reliability Score (TRS), which is initialized uniformly and calibrated from later retrieval outcomes as visit evidence of future transfer reliability. During read-only deployment, SMA retrieves lessons by semantic filter and similarity-TRS combined ranking, allowing the retrieved memory to guide frozen model inference. Across five representative spatial benchmarks and four base VLMs, SMA achieves the highest macro average in every base-model block and the best accuracy among the evaluated methods in most of the 20 evaluations, establishing a practical parameter-update-free path for spatial self-evolution across the evaluated frozen model scales and environments.