cs.AIOct 29, 2026

Beyond Plausible Prediction: Safety Sufficiency in Web World Models

Authors: Zhifei Hu, Alexandra I. Cristea, Adel Bibi, Jialin Yu

Organizations: Durham University · University of Oxford

Abstract

Web world models increasingly predict the consequences of candidate actions before agents act, yet a plausible predicted future does not necessarily support the correct safety decision. In a matched human evaluation of 3,000 predictions from ten frozen open models, 86.1% are judged semantically plausible. However, several models exhibit highly asymmetric authorisation behaviour, combining low false-safe execution with poor recall of clarifiable ASK cases and a strong preference for BLOCK. This motivates safety sufficiency: whether a predictive interface preserves and exposes the policy-decisive information required to distinguish actions that may be EXECUTED, require clarification through ASK, or should be BLOCKED. We introduce SafeWebWorld, a benchmark for evaluating safety sufficiency across five web-safety domains through action-conditioned futures, policy-decisive evidence, and policy-conditioned decisions. Under a controlled Security-Aligned Supervised Fine-Tuning protocol, evidence preservation can improve substantially while authorisation-sensitive decisions deteriorate. To determine whether this deterioration reflects loss of authorisation-sensitive score structure or a failure of the decision readout, we introduce Latent Authorisation Recovery (LAR). Frozen-score recalibration reveals substantial but backbone-dependent recovery, while paired recovery provides only a modest additional gain. Yet within-family and matched-authorisation evaluations remain poor, showing that aggregate recoverability does not imply robust fine-grained authorisation behaviour. Overall, plausible prediction, evidence preservation, and aggregate recovery are each insufficient on their own to establish robust authorisation.

Figures & tables

Appendix figures & tables30 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. Predictive Safety Guardrails Do Not Always Make LLM Agents Safer

    Nov 2, 2026Weixiang Zhao, Zhihao Liu, Guancheng Li +3LLM Agent SafetySafety Filtering

  2. Rethinking World Models for Safety-Critical Embodied Systems

    Sep 3, 2026Kailang Ma, Heye Huang, Inhi Kim +1Runtime AssuranceEmbodied World Models

  3. Safety, Security, and Cognitive Risks in World Models

    Apr 1, 2026Manoj ParmarAdversarial Attacks on World ModelsWorld Models