发表机构
Korea Advanced Institute of Science and Technology; Cho Chun Shik Graduate School of Mobility（韩国科学技术院; 赵成植移动研究生院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本文针对安全关键具身系统，分析现有世界模型的三类结构不匹配，提出风险感知世界模型（RIWM），明确其核心能力与开放挑战，主张未来世界模型需转向关注重要未来与安全决策。
AI 中文摘要
世界模型已从紧凑的隐式动力学模型发展为具身环境的可生成、可控制且可交互的模拟器，然而高预测似然和视觉保真度并不一定能确保模型保留安全决策所需的证据。本视角指出当前世界建模存在三类结构不匹配：似然与风险、预测与干预、有限时域预测与累积后果。我们提出风险感知世界模型（RIWM）作为安全关键具身系统的决策导向研究方向，RIWM围绕后果、干预、认知不确定性和可恢复性组织世界建模，整合四项相互关联的能力：决策相关表示、反事实推理、安全关键情景记忆及运行时安全保障，区分物理、社会和操作后果，同时利用认知不确定性限定支撑行动的证据。我们进一步讨论了开放挑战：识别重要未来、验证反事实推理、维护可修订的安全记忆、将学习到的后果转化为可执行约束，以及确定何时证据足以行动。本视角主张，未来世界模型应超越预测可能的未来，转向识别哪些未来重要、通过经验修正判断，以及识别何时行动、修正、感知、推迟或弃权（不执行）。
英文摘要
World models have progressed from compact latent dynamics to generative, controllable, and interactive simulators of embodied environments. However, high predictive likelihood and visual fidelity do not necessarily ensure that a model preserves the evidence required for safe decision-making. This perspective identifies three structural mismatches in current world modeling: likelihood versus risk, prediction versus intervention, and finite-horizon prediction versus accumulated consequences. We propose the Risk-Informed World Model (RIWM) as a decision-centric research direction for safety-critical embodied systems. RIWM organizes world modeling around consequences, intervention, epistemic uncertainty, and recoverability, and integrates four interdependent capabilities: decision-relevant representation, counterfactual reasoning, safety-critical episodic memory, and runtime safety assurance. It distinguishes physical, social, and operational consequences while using epistemic uncertainty to qualify the evidence supporting action. We further discuss open challenges in identifying consequential futures, validating counterfactual reasoning, maintaining revisable safety memories, translating learned consequences into executable constraints, and determining when evidence is sufficient to act. This perspective argues that future world models should move beyond predicting likely futures toward identifying which futures matter, revising judgments through experience, and recognizing when to act, revise, sense, defer, or abstain.
Comments6 pages, 2 figures. Perspective article
