arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2604.08232cs.AI
收藏

HiRO-Nav：混合推理实现高效具身导航

HiRO-Nav: Hybrid ReasOning Enables Efficient Embodied Navigation

Nanyang Technological University（南洋理工大学）；Tencent（腾讯）；Independent Researcher（独立研究员）

He Zhao, Yijun Yang, Zichuan Lin, Deheng Ye, Chunyan Miao

阅读 PDF
arXiv 页面 ↗HTML 原文 ↗

AI总结：

HiRO-Nav通过混合推理策略，在导航任务中根据动作熵动态决定是否进行推理，提升决策质量并降低计算开销。

摘要：

基于大推理模型的具身导航代理能够处理复杂多模态环境输入，并通过每步基础推理提升长周期任务的决策能力。然而，如何高效利用大推理模型的推理能力仍是一个关键问题。在简单场景中，代理应进行反射式行动，而在复杂场景中应先进行深度推理再行动。为此，我们引入了混合推理导航（HiRO-Nav）代理，该代理能够根据自身动作熵动态决定是否进行推理。通过分析导航轨迹中代理动作熵的变化，发现只有少量动作具有高熵，这些动作通常引导代理进入新场景或关键物体。进一步研究动作熵与任务完成（即Q值）的关系，发现提高高熵动作对任务成功贡献更大。因此，我们提出了一种混合监督微调加在线强化学习的训练流程，通过混合推理策略显式激活高熵动作的推理，显著降低计算开销并提升决策质量。在CHORES-S ObjectNav基准测试中，HiRO-Nav在成功率和token效率之间取得了更好的平衡。

英文摘要：

Embodied navigation agents built upon large reasoning models (LRMs) can handle complex, multimodal environmental input and perform grounded reasoning per step to improve sequential decision-making for long-horizon tasks. However, a critical question remains: \textit{how can the reasoning capabilities of LRMs be harnessed intelligently and efficiently for long-horizon navigation tasks?} In simple scenes, agents are expected to act reflexively, while in complex ones they should engage in deliberate reasoning before acting.To achieve this, we introduce \textbf{H}ybr\textbf{i}d \textbf{R}eas\textbf{O}ning \textbf{Nav}igation (\textbf{HiRO-Nav}) agent, the first kind of agent capable of adaptively determining whether to perform thinking at every step based on its own action entropy. Specifically, by examining how the agent's action entropy evolves over the navigation trajectories, we observed that only a small fraction of actions exhibit high entropy, and these actions often steer the agent toward novel scenes or critical objects. Furthermore, studying the relationship between action entropy and task completion (i.e., Q-value) reveals that improving high-entropy actions contributes more positively to task success.Hence, we propose a tailored training pipeline comprising hybrid supervised fine-tuning as a cold start, followed by online reinforcement learning with the proposed hybrid reasoning strategy to explicitly activate reasoning only for high-entropy actions, significantly reducing computational overhead while improving decision quality. Extensive experiments on the \textsc{CHORES}-$\mathbb{S}$ ObjectNav benchmark showcases that HiRO-Nav achieves a better trade-off between success rates and token efficiency than both dense-thinking and no-thinking baselines.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。

↑