机器人决策新思路：先想后果再行动
机器人决策新思路：先想后果再行动。当前视觉-语言-动作模型（VLA）虽然经过大规模预训练，但泛化能力远不如大语言模型。研究者发现，问题不在于模型不会做动作，而在于它不会评估动作的后果——在32次尝试中，成功率能从33%飙升到92%，说明好动作其实藏在模型内部，只是没被选出来。他们提出的SVA框架，先用蒙特卡洛树搜索在模拟器中探索模型的各种可能动作及其长期结果，然后训练一个轻量级的Q值模型来预测每个候选动作的后果，最后让冻结的VLA模型提出多个动作，由Q值模型选出最优。这样既保留了预训练模型的泛化能力，又大幅提升了任务成功率。实验显示，一个9B参数的VLA模型加上SVA，性能超过了27B的更大模型，且推理延迟降低27%。这不是你明天就能用的技术，但它揭示了一个趋势：在机器人领域，与其盲目扩大模型规模，不如在决策时多花点时间思考后果。
📄 原文摘要(英文)
Vision-Language-Action (VLA) models acquire broad embodied capabilities through large-scale pretraining, yet their generalization remains far more fragile than that of LLMs and VLMs. The prevailing remedy, post-training via supervised fine-tuning or reinforcement learning, improves task-specific performance but narrows the generalist capability that makes pretraining valuable. We identify a key bottleneck: VLA failures stem not only from action generation but also from action evaluation. A diagnostic pass@k study confirms that frozen VLAs already contain competent behaviors in their output distribution, with overall success rates rising from 33% at pass@1 to 92% at pass@32. Inspired by this, we propose SVA (Search, Value, and Act), a simple framework that equips frozen VLA policies with long-term consequence awareness. SVA first uses Monte-Carlo tree search in simulation to fully explore the VLA's output distribution and collect diverse trajectories annotated with empirical returns; this knowledge is then distilled into a lightweight Q-value model that predicts the expected consequence of candidate actions; at deployment, the frozen VLA proposes multiple candidates and the evaluator selects the one with the highest uncertainty-regularized Q-value, requiring no simulator access. By decoupling action proposal from consequence evaluation, SVA preserves the generalization capacity of the VLA backbone while substantially improving task success rates. Experiments across embodied benchmarks show that SVA consistently improves generalization on unseen tasks and exhibits strong test-time scaling behavior. Strikingly, SVA enables a 9B VLA to outperform a 27B VLA by 7 points at 27% lower inference latency, suggesting that scaling test-time evaluation is more cost-effective than scaling model size.