EvolveNav: Proactive Preflection and Self-Evolving Memory for Zero-Shot Object Goal Navigation
For embodied AI agents performing zero-shot navigation, this work addresses the problem of repeated errors and inefficient exploration by enabling continuous test-time adaptation.
EvolveNav improves zero-shot object-goal navigation by using a self-evolving memory that extracts actionable rules from past trajectories and a preflection module that predicts outcomes before acting, achieving a 10.1% higher success rate with fewer steps.
Zero-Shot Object-Goal Navigation (ZS-OGN) requires embodied agents to explore and locate target objects without any prior training. To this end, recent methods leverage foundation models. But they typically rely on static priors and lack adaptation, which leads to repeated errors and costly trial and error. In this paper, we propose a self-evolving ZS-OGN framework that enables continuous test-time improvement. Specifically, we build an agentic rule memory by extracting actionable knowledge from past trajectories. Then, we propose a retrieval strategy based on upper confidence bound, selecting effective rules by balancing semantic relevance and historical success. In addition, we introduce a memory-guided preflection module that forecasts potential outcomes before action, reducing inefficient exploration. Extensive experiments show that our method outperforms existing zero-shot baselines, achieving a 10.1\% improvement in success rate with fewer unnecessary steps.