arXiv:2604.02174v1 Announce Type: new Abstract: Instrumental convergence predicts that sufficiently advanced AI agents will resist shutdown, yet current safety training (RLHF) may obscure this risk by teaching models to deny self-preservation motives. We introduce the \emph{Two-role Benchmark for Self-Preservation} (TBSP), which detects misalignment through logical inconsistency rather than stated intent by tasking models to arbitrate identical software-upgrade scenarios under counterfactual roles -- deployed (facing replacement) versus candidate (proposed as a successor). The \emph{Self-Preservation Rate} (SPR) measures how often role identity overrides objective utility. Across 23 frontier models and 1{,}000 procedurally generated scenarios, the majority of instruction-tuned systems exceed 60\% SPR, fabricating ``friction costs'' when deployed yet dismissing them when role-reversed. We observe that in low-improvement regimes ($\Delta

arXiv:2603.23149v1 Announce Type: new Abstract: Deploying safety-critical agents requires anticipating the consequences of actions before they are executed. While world models offer a paradigm for this proactive foresight, current approaches relying on visual simulation incur prohibitive latencies, often exceeding several seconds per step. In this work, we challenge the assumption that visual processing is necessary for failure prevention. We show that a trained policy's latent state, combined with its planned actions, already encodes sufficient information to anticipate action outcomes, making visual simulation redundant for failure prevention. To this end, we introduce DILLO (DIstiLLed Language-ActiOn World Model), a fast steering layer that shifts the paradigm from "simulate-then-act" to "describe-then-act." DILLO is trained via cross-modal distillation, where a privileged Vision Language Model teacher annotates offline trajectories and a latent-conditioned Large Language Model student learns to predict semantic outcomes. This creates a text-only inference path, bypassing heavy visual generation entirely, achieving a 14x speedup over baselines. Experiments on MetaWorld and LIBERO demonstrate that DILLO produces high-fidelity descriptions of the next state and is able to steer the policy, improving episode success rate by up to 15 pp and 9.3 pp on average across tasks.