外观
论文arXiv 2610.2125113 天前
VLA真的遵循指令吗？诊断视觉-语言-动作模型中的How级指令跟随
原文链接：Do VLAs Really Follow Instructions? Diagnosing How-Level Instruction Following in Vision-Language-Action Models（arXiv 2610.21251 · 发布日期：2026-10-15）
Do VLAs Really Follow Instructions? Diagnosing How-Level Instruction Following in Vision-Language-Action Models
本文诊断VLA的How级指令跟随，提出段级增强指令训练，并在标准基准与SIMPLER-IN上验证。
核心要点
- 以往工作多关注说明任务的What级指令，较少检验说明执行方式的How级指令。
- 作者假设每个训练片段仅配一个指令会限制How级指令跟随能力。
- 段级丰富指令训练可让动作响应How级指令，但未稳定提升任务成功率。
- 提出SIMPLER-IN评测仅由指令给出的成功条件，显示响应性难以扩展到更难或分布外指令。
验证范围与局限：验证范围包括当前VLA、标准基准和SIMPLER-IN，摘要未说明真机或具体任务。
英文摘要 (Abstract)
Vision-language-action (VLA) models are expected to follow instructions like their language backbones, yet prior work has focused on What-level instructions that specify the task rather than How-level instructions that specify how to carry it out. Through our diagnoses, we find that How-level instructions do not help current VLAs and lower task success. We hypothesize that pairing each training episode with a single instruction limits How-level instruction following, and show that training with segment-level enriched instructions makes actions respond to such instructions without consistently raising task success. To measure How-level instruction following beyond standard benchmarks, we introduce SIMPLER-IN, where success requires conditions given only in the instruction. It shows that the gained responsiveness does not extend to demanding or out-of-distribution How-level instructions. How-level instruction following thus remains an open challenge.
作者：Sangwu Park, Wonjoong Kim, Yeonjun In, Chanyoung Park
来源
本页事实对应的公开页面，以原文为准。