Preprint
Sep 2026
NavProbe: Evidence-Grounded Reasoning with Active Memory Retrieval for Zero-Shot Navigation
Long-horizon navigation requires an agent to revise its intermediate objectives as evidence accumulates. Full visual histories are costly to process, while compact summaries may omit details needed to reconsider earlier decisions. We introduce NavProbe, a hierarchical zero-shot navigation agent that couples a dynamic s...
Jing-Yang Liu, Su-Jia Yao, Jia-Yuan Gu et al.
· 0 citations