Tong Zhang, Zhiyuan Shi, Yun Peng, Tao Xie · 2026 · arXiv (Cornell University)
DOI: 10.48550/arxiv.2610.28011 · cited by 0 works (OpenAlex) · open-access PDF
Un planificador utilizando un modelo de mundo aprendido puede mejorar su resultado previsto mientras elige una acción peor. Estudiamos cuando la energía gratuita esperada (EFE) puede ayudar a decidir cuánto cálculo debe gastar en un plan. Un objetivo inspirado en EFE combina la distancia de meta con la discrepancia entre las predicciones estocásticas. Testamos el resultado del candidato, el paro y las actualizaciones del predictor en línea por separado. Detener cuando las estaciones de costo de la élite reducen el refinamiento en tareas cuyos plateaus de éxito son profundos, con el éxito promedio cercano a las referencias de profundidad fija. En los pesos más grandes probados, el desacuerdo de recompensa disminuye el éxito con un modelo congelado. Penalizarlo ayuda en algunos ajustes de tareas y pesos pero daña a
Machine translation (Meta M2M100); the English original follows.
A planner using a learned world model can improve its predicted outcome while choosing a worse action. We study when expected free energy (EFE) can help decide how much computation to spend on a plan. An EFE-inspired objective combines goal distance with disagreement among stochastic predictions. We test candidate scoring, stopping, and online predictor updates separately. Stopping when elite cost stalls reduces refinement on tasks whose success plateaus with depth, with mean success close to fixed-depth references. At the larger tested weights, rewarding disagreement lowers success with a frozen model. Penalizing it helps at some task and weight settings but harms others. When training data omit a region needed to reach the goal, online updates recover part of the resulting loss. The tested cost-stall rule can fail when further optimization exploits model errors, because predicted cost keeps falling after task success peaks. Cost progress can guide computation on a plateau, but protecting performance after a peak requires information about the consequences of the chosen actions.
Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese
Topics: Task (project management), Computer science, Computation, Exploit, Outcome (game theory), Energy (signal processing)
GET https://store.agentexchange.work/gw/papers/verify?title=...&year=... (0.003 USD), fetch this record as JSON with /gw/papers/paper?id=2610.28011, or list what it cites with /gw/papers/references?id=.... Pay per call in USDC (x402) or with a 19 USD card key for 1,000 calls. Catalogue · llms.txtSources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange