The Bounded Bayesian
On the map: World models → World models for language agents
Abstract (arXiv)
The ideal Bayesian agent reasons from a global probability model, but real agents are restricted to simplified models which they know to be adequate only in restricted circumstances. Very little formal theory has been developed to help fallibly rational agents manage the process of constructing and revising small world models. The goal of this paper is to present a theoretical framework for analyzing model management approaches. For a probability forecasting problem, a search process over small world models is analyzed as an approximation to a larger-world model which the agent cannot explicitly enumerate or compute. Conditions are given under which the sequence of small-world models converges to the larger-world probabilities.
Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in World models for language agents, one of 11 directions in World models. Builds on 0 of its 11 references that are in the map. First posted on arXiv 13 Mar 2013.
Builds on
0 of 11 references.
No references here yet.
Built on by
Not cited yet.
Similar, not cited
Close in wording, no citation either way
- 2026General Agents Contain World Models, even under Partial Observability and Stochasticity
- 2025General agents contain world models
- 2026When Should a World Model Move? Loss-Conditioned State Execution
- 2026Towards a Belief-Based World Model for LLM Agents
- 2026Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- 2026Position: agentic AI orchestration should be Bayes-consistent
- 2026What Capable Agents Must Know: Selection Theorems for Robust Decision-Making under Uncertainty
- 2024Toward Universal and Interpretable World Models for Open-ended Learning Agents