The Essence of Balance for Self-Improving Agents in Vision-and-Language Navigation

TL;DR

This paper introduces a novel mechanism called Stability-Diversity Balance (SDB) that enhances self-improvement in vision-and-language navigation agents by balancing behavioral diversity and learning stability.

Contribution

The paper proposes SDB, a plug-and-play method that generates multiple behavioral hypotheses and stabilizes learning, leading to improved navigation performance.

Findings

SDB improves SPL from 33.73 to 35.93 on REVERIE val-unseen.

SDB enhances OSR from 51.07 to 54.25 on REVERIE val-unseen.

Experiments on R2R, SOON, and REVERIE validate the effectiveness of SDB.

Abstract

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.