Recent advancements in vision-language-action (VLA) models have shown promise in robotic manipulation, yet they continue to struggle with long-horizon, multi-step tasks. Existing methods lack internal reasoning mechanisms that can identify task-relevant interaction cues or track progress within a subtask, leading to critical execution errors such as repeated actions, missed steps, and premature termination. To address these challenges, we introduce PALM, a VLA framework that structures policy learning around interaction-centric affordance reasoning and subtask progress cues. PALM distills complementary affordance representations that capture object relevance, contact geometry, spatial placements, and motion dynamics, and serve as task-relevant anchors for visuomotor control. To further stabilize long-horizon execution, PALM predicts continuous within-subtask progress, enabling seamless subtask transitions. Across extensive simulation and real-world experiments, PALM consistently outperforms baselines, achieving a 91.8% success rate on LIBERO-LONG, a 12.5% improvement in average length on CALVIN ABC->D, and a 2x improvement over real-world baselines across three long-horizon generalization settings.

翻译：近期视觉-语言-动作（VLA）模型在机器人操作领域展现出潜力，但在处理长时程、多步骤任务时仍面临困难。现有方法缺乏能够识别任务相关交互线索或在子任务内跟踪进展的内部推理机制，导致重复动作、步骤遗漏和过早终止等关键执行错误。为解决这些挑战，我们提出了PALM，这是一个围绕以交互为中心的可供性推理和子任务进展线索构建策略学习的VLA框架。PALM提炼出互补的可供性表征，这些表征捕捉物体相关性、接触几何、空间布局和运动动态，并作为视觉运动控制的任务相关锚点。为进一步稳定长时程执行，PALM预测连续的子任务内进展，从而实现无缝的子任务转换。在大量仿真和真实世界实验中，PALM始终优于基线方法，在LIBERO-LONG上实现了91.8%的成功率，在CALVIN ABC->D上平均长度提升了12.5%，并在三种长时程泛化设置中实现了相对于真实世界基线2倍的性能提升。