mlsanityData to 14 Oct 2026

Semantic Bayesian World Models

arXiv 2609.03834 ↗First posted 3 Sep 2026cs.AI cs.DB cs.LGcited by 0

On the map: World models → World models for language agents

Abstract (arXiv)

Knowledge graphs describe reality in crisp assertions, while the systems now consuming them, foundation models and autonomous agents, reason natively in probabilities. We argue that this mismatch is why the integration of language models and knowledge graphs remains a data-feeding pipeline rather than a unified reasoning architecture. We envision Semantic Bayesian World Models (SBWMs): a Web that describes the world not as a database of facts but as a shared, evolving fabric of beliefs over knowledge graphs, where ontological axioms constrain priors, observations update beliefs by Bayesian conditioning, and actions intervene upon the world. We work through what an agent gains from such a model: a home-security agent deciding whether the figure at the gate is a courier or a burglar, an actuarial estimate aggregated by entailment rather than by string frequency, a planning task that language models reliably fail, and the estimation of quantities that no document has ever stated. We then set out what the community must build to make them possible: belief annotation over RDF~1.2, probabilistic entailment regimes, semantic calibration layers, and protocols by which agents that have never met can exchange, and disagree over, calibrated beliefs.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in World models for language agents, one of 11 directions in World models. Builds on 9 of its 26 references that are in the map. First posted on arXiv 3 Sep 2026.

Builds on

9 of 26 references.

Closest ancestors · 1

Same direction, newest first

  1. 2023From Word Models to World Models: Translating from Natural Language to the Probabilistic Language of Thought22 Jun

Other references · 8

  1. 2023Mastering Diverse Domains through World Modelscited by 1,253
  2. 2018Recurrent World Models Facilitate Policy Evolutioncited by 785
  3. 2024Genie: Generative Interactive Environmentscited by 747
  4. 2020Beta Embeddings for Multi-Hop Logical Reasoning in Knowledge Graphscited by 129
  5. 2015Hinge-Loss Markov Random Fields and Probabilistic Soft Logiccited by 63
  6. 2025Bayesian Teaching Enables Probabilistic Reasoning in Large Language Modelscited by 37
  7. 2024Incoherent Probability Judgments in Large Language Modelscited by 30
  8. 2025Leveraging Log Probabilities in Language Models to Forecast Future Eventscited by 2

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2021Towards General Natural Language Understanding with Probabilistic Worldbuilding
  2. 2025Bayesian Social Deduction with Graph-Informed Language Models
  3. 2025Active Confusion Expression in Large Language Models: Leveraging World Models toward Better Social Reasoning
  4. 2026Towards a Belief-Based World Model for LLM Agents
  5. 2024BayesAgent: Bayesian Agentic Reasoning Under Uncertainty via Verbalized Probabilistic Graphical Modeling
  6. 2026Ask the World Before Acting: Environment Probing for Calibrated Agent World Models
  7. 2026Stochastic Semantic Evidence Graphs: Uncertainty Propagation and Governance for Agentic AI
  8. 2024Understanding Epistemic Language with a Language-augmented Bayesian Theory of Mind