NEXUS：用于安全和稳健体素规划的符号约束连续学习
NEXUS: Continual Learning of Symbolic Constraints for Safe and Robust Embodied Planning
AI总结：
NEXUS通过模块化框架实现体素代理的连续学习，将符号 artifacts 用于符号 grounding 和知识演化，将概率风险评估转化为确定性硬约束，提升任务成功率并抵御对抗攻击。
摘要：
尽管大型语言模型（LLMs）在体素智能方面推动了进步，但其内在的概率不确定性与物理世界所需的严格确定性和可验证安全性之间存在根本性差距。为缓解这一差距，本文引入了NEXUS，一个用于体素代理连续学习的模块化框架。与以往将符号 artifacts 仅视为静态接口的不同，NEXUS利用它们进行符号 grounding 和知识演化。该框架明确解耦了物理可行性与安全规范：通过闭环执行反馈提高代理能力，同时将概率风险评估 grounded 到确定性硬约束中，以建立严格的预行动防御。在SafeAgentBench上的实验表明，NEXUS在实现更高任务成功率的同时，有效拒绝不安全指令，表现出对对抗攻击的稳健防御，并通过知识积累逐步提高规划效率。
英文摘要：
While Large Language Models (LLMs) have catalyzed progress in embodied intelligence, a fundamental gap between their inherent probabilistic uncertainty and the strict determinism and verifiable safety required in the physical world. To mitigate this gap, this paper introduces NEXUS, a modular framework designed for continual learning in embodied agents. Different from prior works that treat symbolic artifacts merely as static interfaces, NEXUS leverages them for symbolic grounding and knowledge evolution. The framework explicitly decouples physical feasibility from safety specifications: capability of agents is improved through closed-loop execution feedback, while probabilistic risk assessments are grounded into deterministic hard constraints to establish a rigorous pre-action defense. Experiments on SafeAgentBench demonstrate that NEXUS achieves superior task success rates while effectively refusing unsafe instructions, exhibiting robust defense against adversarial attacks, and progressively improving planning efficiency through knowledge accumulation.
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。
