Semantic Bayesian World Models

2026-09-03

AI Summary

为解决知识图谱与基础模型推理方式不匹配的问题，提出语义贝叶斯世界模型，通过概率信念更新和行动干预实现统一推理架构。

Abstract

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.

Problem

• Semantic Bayesian World Models
• knowledge graphs
• probabilistic reasoning
• foundation models
• autonomous agents

Innovation

• Semantic Bayesian World Models
• probabilistic reasoning
• knowledge graphs
• belief annotation
• probabilistic entailment