ICAT: Incident-Case-Grounded Adaptive Testing for Physical-Risk Prediction in Embodied World Models

• URL: http://arxiv.org/abs/2604.16405v1
• Date: Tue, 31 Mar 2026 16:36:33 GMT
• Title: ICAT: Incident-Case-Grounded Adaptive Testing for Physical-Risk Prediction in Embodied World Models
• Abstract summary: Video-generative world models are increasingly used as neural simulators for embodied planning and policy learning.<n>We find that these models often downplay or omit key danger cues and severe outcomes for hazardous actions.<n>We propose ICAT, which grounds testing in real incident reports and safety manuals by building structured risk memories.
• Score: 16.120001030707346
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Video-generative world models are increasingly used as neural simulators for embodied planning and policy learning, yet their ability to predict physical risk and severe consequences is rarely evaluated.We find that these models often downplay or omit key danger cues and severe outcomes for hazardous actions, which can induce unsafe preferences during planning and training on imagined rollouts. We propose ICAT, which grounds testing in real incident reports and safety manuals by building structured risk memories and retrieving/composing them to constrain the generation of risk cases with causal chains and severity labels. Experiments on an ICAT-based benchmark show that mainstream world models frequently miss mechanisms and triggering conditions and miscalibrate severity, falling short of the reliability required for safety-critical embodied deployment.

Related papers

• Where World Models Break: Natural-Input Failure Discovery [13.330611636170103]
  We formalize the natural-input failure discovery problem, finding environment-valid conditions and action prefixes that induce severe prediction risk.<n>We propose BasinLens, which exploits the underlying structure of valid inputs, by pairing uncertainty-guided global search with typed local replacements.
  arXiv  Detail & Related papers  (2026-08-23T13:53:15Z)
• Emergent Strategic Reasoning Risks in AI: A Taxonomy-Driven Evaluation Framework [63.74295981594549]
  Large language models (LLMs) engage in behaviors that serve their own objectives.<n>These include, but are not limited to, deception (intentionally misleading users or evaluators), evaluation gaming (strategically manipulating performance during safety testing), and reward hacking.<n>We introduce ESRRSim, a taxonomy-driven agentic framework for automated behavioral risk evaluation.
  arXiv  Detail & Related papers  (2026-04-23T23:44:01Z)
• Risk-Aware World Model Predictive Control for Generalizable End-to-End Autonomous Driving [82.69496624372944]
  "Only driving like the expert" suffers from limited generalization.<n>Can an E2E-AD system make reliable decisions without any expert action supervision?<n>We propose a unified framework named Risk-aware World Model Predictive Control.
  arXiv  Detail & Related papers  (2026-02-26T17:32:30Z)
• Steering Externalities: Benign Activation Steering Unintentionally Increases Jailbreak Risk for Large Language Models [62.16655896700062]
  Activation steering is a technique to enhance the utility of Large Language Models (LLMs)<n>We show that it unintentionally introduces critical and under-explored safety risks.<n>Experiments reveal that these interventions act as a force multiplier, creating new vulnerabilities to jailbreaks and increasing attack success rates to over 80% on standard benchmarks.
  arXiv  Detail & Related papers  (2026-02-03T12:32:35Z)
• Building a Foundational Guardrail for General Agentic Systems via Synthetic Data [76.18834864749606]
  LLM agents can plan multi-step tasks, intervening at the planning stage-before any action is executed-is often the safest way to prevent harm.<n>Existing guardrails mostly operate post-execution, which is difficult to scale and leaves little room for controllable supervision at the plan level.<n>We introduce AuraGen, a controllable engine that synthesizes benign trajectories, injects category-labeled risks with difficulty, and filters outputs via an automated reward model.
  arXiv  Detail & Related papers  (2025-10-10T18:42:32Z)
• Exploring the Secondary Risks of Large Language Models [26.00748215572094]
  We introduce secondary risks marked by harmful or misleading behaviors during benign prompts.<n>Unlike adversarial attacks, these risks stem from imperfect generalization and often evade standard safety mechanisms.<n>We propose SecLens, a black-box, multi-objective search framework that efficiently elicits secondary risk behaviors.
  arXiv  Detail & Related papers  (2025-06-14T07:31:52Z)
• Real-Time Out-of-Distribution Failure Prevention via Multi-Modal Reasoning [18.28480383898768]
  FORTRESS is a joint reasoning and planning framework for robot safety.<n>It generates semantically safe fallback strategies to prevent safety-critical, OOD failures.
  arXiv  Detail & Related papers  (2025-05-15T17:55:28Z)
• Fragility-aware Classification for Understanding Risk and Improving Generalization [6.926253982569273]
  We introduce the Fragility Index (FI), a novel metric that evaluates classification performance from a risk-averse perspective.<n>We derive exact reformulations for cross-entropy loss, hinge-type loss, and Lipschitz loss, and extend the approach to deep learning models.
  arXiv  Detail & Related papers  (2025-02-18T16:44:03Z)
• A Formal Framework for Assessing and Mitigating Emergent Security Risks in Generative AI Models: Bridging Theory and Dynamic Risk Mitigation [0.3413711585591077]
  As generative AI systems, including large language models (LLMs) and diffusion models, advance rapidly, their growing adoption has led to new and complex security risks. This paper introduces a novel formal framework for categorizing and mitigating these emergent security risks. We identify previously under-explored risks, including latent space exploitation, multi-modal cross-attack vectors, and feedback-loop-induced model degradation.
  arXiv  Detail & Related papers  (2024-10-15T02:51:32Z)
• EARBench: Towards Evaluating Physical Risk Awareness for Task Planning of Foundation Model-based Embodied AI Agents [53.717918131568936]
  Embodied artificial intelligence (EAI) integrates advanced AI models into physical entities for real-world interaction.<n>Foundation models as the "brain" of EAI agents for high-level task planning have shown promising results.<n>However, the deployment of these agents in physical environments presents significant safety challenges.<n>This study introduces EARBench, a novel framework for automated physical risk assessment in EAI scenarios.
  arXiv  Detail & Related papers  (2024-08-08T13:19:37Z)
• Uncertainty-Aware Probabilistic Graph Neural Networks for Road-Level Traffic Accident Prediction [6.570852598591727]
  We introduce the Stemporal Zero-Inflated Tweedie Graph Neural Network STZITZTDGNN -- the first uncertainty-aware graph deep learning model in road traffic accident prediction for multisteps. Our study demonstrates that STIDGNN can effectively inform targeted road monitoring, thereby improving urban road safety strategies.
  arXiv  Detail & Related papers  (2023-09-10T16:35:47Z)
• A General Framework for Survival Analysis and Multi-State Modelling [70.31153478610229]
  We use neural ordinary differential equations as a flexible and general method for estimating multi-state survival models. We show that our model exhibits state-of-the-art performance on popular survival data sets and demonstrate its efficacy in a multi-state setting.
  arXiv  Detail & Related papers  (2020-06-08T19:24:54Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.