AI 中文总结
PACE框架通过交错式思考-执行架构和动态预算分配器，在Robotouille基准测试中较ReAct+Think基线提升规划成功率，同时大幅减少推理时间，实现具身规划的时间效率与质量同步提升。
AI 中文摘要
基于推理的大型语言模型在规划任务中取得了显著提升，但由于推理延迟过高（通常每个规划实例超过数分钟），其在具身系统中的部署仍不切实际。这一根本瓶颈源于现有范式的串行特性：模型必须完成所有推理后才能执行任何动作，完全浪费了执行时间窗口。我们提出PACE（Planning with Adaptive Cognitive Effort，即自适应认知努力规划），该框架通过两项关键创新实现推理与执行的交错进行：一是交错式思考-执行架构，将认知处理与动作执行进行流水线处理；二是动态预算分配器，可根据可用执行时间窗口调整推理令牌预算。在使用Qwen3-8B-AWQ的Robotouille基准测试中，PACE达到了10%的成功率，较ReAct+Think基线提升了67%，同时推理时间较无约束推理加速了6.9倍。该框架将66.8%的推理时间隐藏在执行窗口中，表明策略性认知努力分配可同时提升规划质量和时间效率。这些结果证明，感知时间的架构创新能使推理模型在之前不适用的低延迟具身领域运行。
英文摘要
Reasoning-enhanced large language models have achieved remarkable improvements in planning tasks, yet their deployment in embodied systems remains impractical due to prohibitive inference delays-often exceeding minutes per planning instance. The fundamental bottleneck stems from the serial nature of existing paradigms: models must complete all reasoning before any action execution, leaving execution time windows entirely unexploited. We introduce PACE (Planning with Adaptive Cognitive Effort), a framework that enables interleaved reasoning and execution through two key innovations: an Interleaved Think-Act architecture that pipelines cognitive processing with action execution, and a Dynamic Budget Allocator that adapts reasoning token budgets to available execution time windows. On the Robotouille benchmark using Qwen3-8B-AWQ, PACE achieves a 10% success rate-representing a 67% improvement over the ReAct+Think baseline-while delivering 6.9 times acceleration in thinking time compared to unconstrained reasoning. The framework hides 66.8% of thinking time within execution windows, demonstrating that strategic cognitive effort allocation can simultaneously improve both planning quality and time efficiency. These results provide evidence that time-aware architectural innovations enable reasoning models to operate in latency-sensitive embodied domains where they were previously impractical.
