# Nipping the Drift in the Bud: Retrospective Rectification for Robust Vision-Language Navigation

arXiv: https://arxiv.org/abs/2602.06356 · HTML: https://mlsanity.com/paper/2602.06356/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 6 Feb 2026.

## Built on by (most cited first, 3 of 3)

- [LCGNav: Local Candidate-Aware Geometric Enhancement for General Topological Planning in Vision-Language Navigation](https://mlsanity.com/paper/2605.09053/) (2026)
- [ReflectVLN: Training Vision-Language Navigation Agents with Reflective Reasoning](https://mlsanity.com/paper/2607.12680/) (2026)
- [AVERT-VLN: Abstention-aware Visual Error Recovery and Training for Vision-and-Language Navigation](https://mlsanity.com/paper/2609.39579/) (2026)

## Abstract (arXiv)

Vision-Language Navigation (VLN) requires embodied agents to interpret natural language instructions and navigate through complex continuous 3D environments. However, the dominant imitation learning paradigm suffers from exposure bias, where minor deviations during inference lead to compounding errors. While DAgger-style approaches attempt to mitigate this by correcting error states, we identify a critical limitation: Instruction-State Misalignment. Forcing an agent to learn recovery actions from off-track states often creates supervision signals that semantically conflict with the original instruction. In response to these challenges, we introduce BudVLN, an online framework that learns from on-policy rollouts by constructing supervision to match the current state distribution. BudVLN performs retrospective rectification via counterfactual re-anchoring and decision-conditioned supervision synthesis, using a geodesic oracle to synthesize corrective trajectories that originate from valid historical states, ensuring semantic consistency. Experiments on the standard R2R-CE and RxR-CE benchmarks demonstrate that BudVLN consistently mitigates distribution shift and achieves state-of-the-art performance in both Success Rate and SPL.