thinking-map-spatial-agents

【开发与工程】Improve agent reasoning for spatial tasks by augmenting LLMs with map tools and parallel test-time exploration. Framework uses reinforcement learning to train agents to iteratively refine hypotheses using map feedback. Parallel exploration enables agents to test multiple candidate locations before committing to answers. Introduces MAPBench benchmark …

独立 GitHub 快照 · 自动分类 · 以原作者文档为准