基于因果世界建模的自进化认知框架用于具身科学智能
Self-Evolving Cognitive Framework via Causal World Modeling for Embodied Scientific Intelligence
浏览论文内容
中文总结 AI 辅助
提出一种自进化认知框架，通过因果世界建模、干预驱动推理和持续认知精炼，使具身智能体在交互中不断构建和修正内部因果模型，实现从预测智能到认知智能的转变。
中文摘要 AI 辅助
当前的具身世界模型主要针对预测目标进行优化，限制了它们在分布偏移下的泛化能力以及对未见情况和假设干预的系统推理能力。我们认为，具身智能应超越预测性世界建模，转向自进化认知系统，通过与环境的交互持续构建和精炼内部因果表征。为此，我们提出一种基于因果世界建模的自进化认知框架用于具身科学智能，该框架整合了三个互补组件：因果世界建模、干预驱动的因果推理和持续认知精炼。所提出的框架通过因果发现、干预驱动反馈和反事实推理不断修正和扩展其内部因果世界模型，支持持续认知精炼，使认知本身随时间进化。此外，我们将具身交互重新解释为因果假设生成、干预驱动实验和持续知识获取的认识论过程，而不仅仅是轨迹优化的手段。这项工作为从预测智能向认知智能的转变提供了概念和理论基础，其中智能通过与环境的交互持续构建、修正和精炼因果世界模型而涌现。相应地，提出了一种干预驱动的因果-认识论基准范式，用于评估自进化的具身科学智能。
英文摘要
Current embodied world models are primarily optimized for predictive objectives, limiting their ability to generalize under distribution shifts and reason systematically about unseen situations and hypothetical interventions. We argue that embodied intelligence should move beyond predictive world modeling toward self-evolving cognitive systems that continually construct and refine internal causal representations through interaction with the environment. To this end, we propose a self-evolving cognitive framework via causal world modeling for embodied scientific intelligence, which integrates three complementary components: causal world modeling, intervention-driven causal reasoning, and continual cognitive refinement. The proposed framework continuously revises and expands its internal causal world model through causal discovery, intervention-driven feedback, and counterfactual reasoning, supporting continual cognitive refinement and enabling cognition itself to evolve over time. Furthermore, we reinterpret embodied interaction not merely as a means of trajectory optimization, but as an epistemic process for causal hypothesis generation, intervention-driven experimentation, and continual knowledge acquisition. This work provides a conceptual and theoretical foundation for a transition from predictive intelligence toward epistemic intelligence, in which intelligence emerges through the continual construction, revision, and refinement of causal world models via interaction with the environment. Accordingly, an intervention-driven causal-epistemic benchmarking paradigm is suggested for evaluating self-evolving embodied scientific intelligence.
发表机构
- Graduate School of Advanced Science and Engineering, Hiroshima University（广岛大学先进科学与工程研究生院）
- Advanced Intelligence and Robotics Research Center, Brain Science Institute, Tamagawa University（玉川大学脑科学研究所先进智能与机器人研究中心）
机构由 AI 辅助整理，请以论文原文为准。
