EvolveNav: Proactive Preflection and Self-Evolving Memory for Zero-Shot Object Goal Navigation
English summary
EvolveNav is a self-evolving zero-shot object-goal navigation framework that continuously improves during test time by extracting actionable rules from past trajectories into an agentic rule memory. A retrieval strategy based on upper confidence bound selects effective rules by balancing semantic relevance with historical success. A memory-guided preflection module forecasts potential outcomes before action, reducing inefficient exploration. In experiments, EvolveNav outperforms existing zero-shot baselines, improving the success rate by 10.1% while taking fewer unnecessary steps.
Chinese summary
EvolveNav是一种自演化的零样本目标导航框架，可在测试时通过从过往轨迹中提炼可执行规则构建智能规则记忆，实现持续改进。基于上置信界的检索策略在语义相关性与历史成功率之间取得平衡，选出有效规则。记忆引导的预反思模块在行动前预测潜在结果，减少低效探索。实验表明，该方法优于现有零样本基线，将成功率提升10.1%，且减少了不必要的步数。
Key points
Constructs an agentic rule memory from past trajectories, enabling continuous test-time self-evolution.
从过往轨迹构建智能规则记忆，实现测试时持续自演化。
Retrieves rules using an upper-confidence-bound strategy that balances semantic relevance and historical success rates.
使用基于上置信界的检索策略，平衡语义相关性与历史成功率以选取规则。
Introduces a memory-guided preflection module that forecasts action outcomes to avoid inefficient exploration.
引入记忆引导的预反思模块，预测行动结果以减少低效探索。
Achieves a 10.1% success rate improvement over existing zero-shot baselines with fewer unnecessary navigation steps.
相对现有零样本基线，成功率提升10.1%，且降低了不必要的导航步数。