Signals 4 · free daily AI digest

When Should a World Model Move? Loss-Conditioned State Execution

Paper recorded by Signals 4 on 2026-09-14 in cs.AI. Abstract reproduced from arXiv; link to the original below.

Published 2026-09-14 on arXiv · recorded by Signals 4 on 2026-09-15

Category: cs.AI · 人工智能 · first seen 2026-09-15

Abstract

We introduce loss-conditioned state execution, a model-agnostic method that decides whether to execute a world model's fixed feasible proposal or retain the current state. Predictive informativeness alone, however, does not establish whether an update will reduce downstream loss. Occurrence ranking can approach perfection while persistence remains the unique absolute-loss Bayes action. Two transit

Read on arXiv →

#80 most recent of 300 cs.AI papers we have recorded · ↑ newer: Delegating Authorization to Misaligned Agents: Coalitional Alignment a · ↓ older: Rethinking Heterogeneous System Disaggregation for Subquadratic Attent
Cite this page: When Should a World Model Move? Loss-Conditioned State Execution: the #80 most recent of 300 cs.AI papers we have recorded (as of 2026-09-14). Source: Signals 4 (Signals API) — https://data.jiangzhang.ca/signals4/t/papers/when-should-a-world-model-move-loss-conditioned-state-execution.html
Free to quote with attribution to “Signals 4 (Signals API)”. Machine-readable: papers.json
Related: More cs.AI papers · arXiv signals · All papers · Today in AI
Get 4 AI signals a day by email — free.
Subscribe free → See all plans →
Get 4 AI signals a day by email — free
All models · All repos · By company · Daily editions