论文/arXiv 2610.14720·18 天前

CAG-WAM：用于机器人操作的因果动作增益世界动作模型

针对WAM候选动作未来评估受环境演化混淆的问题，CAG-WAM用因果动作增益指导训练与推理，并在多个基准验证有效性。

AI 整理

• 端侧部署
• 评测与安全

原文链接：CAG-WAM: Causal Action-Gain World Action Models for Robot Manipulation（arXiv 2610.14720 · 发布日期：2026-10-10）

CAG-WAM: Causal Action-Gain World Action Models for Robot Manipulation

针对WAM候选动作未来评估受环境演化混淆的问题，CAG-WAM用因果动作增益指导训练与推理，并在多个基准验证有效性。

核心要点

• WAM预测未来混合动作诱发与环境驱动变化，直接评估可能误判候选动作。
• 论文构建SCM揭示环境演化的后门路径，并用干预与后门调整提供因果依据。
• CAG-WAM在同一当前观察下预测动作条件未来和环境未来，以评估差定义CAG。
• 训练中将CAG并入GRPO指导策略学习，推理时用CAG评估并按需修正初始动作。

验证范围与局限：实验仅概述为多个基准，摘要未说明仿真或真机及具体任务。

英文摘要 (Abstract)

World Action Models (WAMs) combine action generation with future prediction, allowing predicted futures to support action evaluation and robot decision making. However, the future associated with a candidate action may contain action-induced and environment-driven changes. Directly evaluating the predicted future may not fully characterize the future change associated with the candidate action. For example, a candidate action that worsens a favorable environmental future may still yield a favorable outcome, while one that improves an unfavorable environmental future may still yield an unfavorable outcome. To analyze this issue, we formulate a Structural Causal Model (SCM) for action evaluation in WAMs. The SCM formalizes how action-induced and environment-driven changes jointly shape future evaluation, and reveals a backdoor path through which environmental evolution can also affect the future evaluation associated with a candidate action. Intervention and backdoor adjustment account for this path, providing a causal basis for characterizing the future change associated with each candidate action. Based on this analysis, we propose Causal Action-Gain World Action Model (CAG-WAM). For each candidate action, CAG-WAM predicts an action-conditioned future and an environmental future under the same current observation, and defines their evaluation difference as causal action gain (CAG) for characterizing the future change associated with the candidate action. During training, we incorporate CAG into Group Relative Policy Optimization (GRPO) to guide robot policy learning. During inference, we evaluate the initial action with CAG and, when needed, revise it using predicted future information. Experiments on multiple benchmarks support the effectiveness of CAG-WAM.

作者：Peizheng Guo, Cheng Zhang, Xingyu Zhang, Changwen Zheng, Wenwen Qiang

来源

本页事实对应的公开页面，以原文为准。

1. arXiv 2610.14720：CAG-WAM: Causal Action-Gain World Action Models for Robot Manipulation访问 2026-10-21