视觉-语言导航中自改进智能体的平衡本质
The Essence of Balance for Self-Improving Agents in Vision-and-Language Navigation
AI总结：
本文提出SDB机制，通过平衡行为多样性与学习稳定性，提升视觉-语言导航中自改进性能，在R2R、SOON和REVERIE数据集上取得显著提升。
摘要：
在视觉-语言导航（VLN）中，自改进依赖于平衡行为多样性和学习稳定性，这决定了智能体能否提取可靠的改进信号。增加行为多样性有助于探索替代动作假设，但可能破坏策略诱导的学习信号；过于保守的稳定性约束会抑制探索并导致早期承诺，使可靠自改进困难。为此，我们提出Stability-Diversity Balance（SDB），通过应用受控的指令条件隐藏状态偏移，将每个决策步骤扩展为多个潜在行为假设，并进行可靠性感知的软评估和聚合，保留多样但指令一致的替代方案。一个显式正则化器进一步约束假设交互，防止假设多样性过度漂移或过早崩溃，从而稳定自改进而不牺牲训练信号。在R2R、SOON和REVERIE上的实验显示一致的提升；例如，在REVERIE val-unseen上，SDB将SPL从33.73提升到35.93，将OSR从51.07提升到54.25。
英文摘要：
In vision-and-language navigation (VLN), self-improvement from policy-induced experience, using only standard VLN action supervision, critically depends on balancing behavioral diversity and learning stability, which governs whether the agent can extract a reliable learning signal for improvement. Increasing behavioral diversity is necessary to expose alternative action hypotheses but can destabilize policy-induced learning signals, whereas overly conservative stability constraints suppress exploration and induce early commitment, making reliable self-improvement difficult. To address this challenge, we propose Stability-Diversity Balance (SDB), a plug-and-play mechanism for balanced self-improvement in VLN. SDB expands each decision step into multiple latent behavioral hypotheses by applying controlled shifts in the instruction-conditioned hidden states, and then performs reliability-aware soft evaluation and aggregation to retain diverse yet instruction-consistent alternatives during learning. An explicit regularizer further constrains hypothesis interactions, preventing excessive drift or premature collapse of hypothesis diversity and stabilizing self-improvement without discarding training signals. Experiments on R2R, SOON, and REVERIE show consistent improvements; for example, on REVERIE val-unseen, SDB improves SPL from 33.73 to 35.93 and OSR from 51.07 to 54.25.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
