让智能体自动决定执行动作的持续时间，提升长序列推理效率与成功率。
When to Re-Commit: Temporal Abstraction Discovery for Long-Horizon Vision-Language Reasoning
- 将动作执行深度设为可学习的状态相关变量，动态调整策略。
- 在滑块拼图和推箱子任务中，解题成功率最高提升12.5个百分点，动作数减少约25%。
- 适用于需要长期规划的视觉语言任务，尤其适合追求高鲁棒性的应用。
长时序推理不仅需决定执行什么动作，还需确定在下一次观察前应闭环执行多少基础动作。本文将此定义为“承诺深度”：两次重规划间连续执行的基础动作数量。承诺深度在重规划开销与执行误差累积之间形成权衡，但现有系统多将其固定为人工设计的标量。本文提出将承诺深度作为策略本身的可学习、状态相关的变量。在原生视觉-语言策略中，模型同时预测执行内容与持续时间。在滑块拼图与推箱子任务上，该自适应策略在所有非退化固定深度基线中均实现帕累托最优，解题率最高提升12.5个百分点，每回合基础动作数减少约25%。尽管使用70亿参数骨干网络，其性能仍超越GPT-5.5与Claude Sonnet，而所有测试的开源视觉-语言模型零样本成功率均为0%。进一步的理论分析表明，在标准承诺深度代理下，状态相关的承诺深度严格优于任何固定深度，前提是局部最优深度随状态变化。
原文摘要 · Abstract (English)
Long-horizon reasoning requires deciding not only what actions to take, but how deeply to commit before the next observation. We formalize this as \emph{commitment depth}: the number of primitive actions executed open-loop between replans. Commitment depth induces a trade-off between replanning cost and compounding execution error, yet most existing long-horizon systems fix it as a hand-designed scalar. In this work, we instead treat commitment depth as a learnable, state-conditioned variable of the policy itself. We instantiate this within a model-native vision--language policy that jointly predicts both what to execute and for how long. Across Sliding Puzzle and Sokoban, the resulting adaptive policy Pareto-dominates every non-degenerate fixed-depth baseline, achieving up to 12.5 percentage points higher solve rate while using approximately 25\% fewer primitive actions per episode. Despite using a 7B backbone, our method outperforms GPT-5.5 and Claude Sonnet on both tasks, while every tested open-weight vision--language model achieves 0\% zero-shot success. We further present a theoretical analysis showing that, under the standard commitment-depth surrogate, state-conditioned commitment strictly dominates any fixed depth whenever the locally optimal depth varies across states.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。