General Agents Contain World Models, even under Partial Observability and Stochasticity

• URL: http://arxiv.org/abs/2602.03146v1
• Date: Tue, 03 Feb 2026 06:00:41 GMT
• Title: General Agents Contain World Models, even under Partial Observability and Stochasticity
• Abstract summary: We show that agents cannot avoid learning their environment through the usage of randomization.<n>We weaken the notion of generality, proving that less powerful agents already contain a model of the world in which they operate.
• Score: 0.913755431537592
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Deciding whether an agent possesses a model of its surrounding world is a fundamental step toward understanding its capabilities and limitations. In [10], it was shown that, within a particular framework, every almost optimal and general agent necessarily contains sufficient knowledge of its environment to allow an approximate reconstruction of it by querying the agent as a black box. This result relied on the assumptions that the agent is deterministic and that the environment is fully observable. In this work, we remove both assumptions by extending the theorem to stochastic agents operating in partially observable environments. Fundamentally, this shows that stochastic agents cannot avoid learning their environment through the usage of randomization. We also strengthen the result by weakening the notion of generality, proving that less powerful agents already contain a model of the world in which they operate.

Related papers

• Agent-World: Scaling Real-World Environment Synthesis for Evolving General Agent Intelligence [122.8626256816085]
  textbfAgent-World is a self-evolving training arena for advancing general agent intelligence through scalable environments.<n>Agent-World-8B and 14B consistently outperforms strong proprietary models and environment scaling baselines.
  arXiv  Detail & Related papers  (2026-04-20T14:01:10Z)
• What Capable Agents Must Know: Selection Theorems for Robust Decision-Making under Uncertainty [1.6868147729303773]
  We prove "selection theorems" showing that low "average-case regret" forces an agent to implement a predictive, structured internal state.<n>We show that regret bounds limit probability mass on suboptimal bets, enforcing the predictive distinctions needed to separate high-margin outcomes.
  arXiv  Detail & Related papers  (2026-03-03T00:47:58Z)
• What Do LLM Agents Know About Their World? Task2Quiz: A Paradigm for Studying Environment Understanding [50.35012849818872]
  Large language model (LLM) agents have demonstrated remarkable capabilities in complex decision-making and tool-use tasks.<n>We propose Task-to-Quiz (T2Q), a deterministic and automated evaluation paradigm designed to decouple task execution from world-state understanding.<n>Our experiments reveal that task success is often a poor proxy for environment understanding, and that current memory machanism can not effectively help agents acquire a grounded model of the environment.
  arXiv  Detail & Related papers  (2026-01-14T14:09:11Z)
• Current Agents Fail to Leverage World Model as Tool for Foresight [61.82522354207919]
  Generative world models offer a promising remedy: agents could use them to foresee outcomes before acting.<n>This paper empirically examines whether current agents can leverage such world models as tools to enhance their cognition.
  arXiv  Detail & Related papers  (2026-01-07T13:15:23Z)
• Embedded Universal Predictive Intelligence: a coherent framework for multi-agent learning [57.23345786304694]
  We introduce a framework for prospective learning and embedded agency centered on self-prediction.<n>We show that in multi-agent settings, self-prediction enables agents to reason about others running similar algorithms.<n>We extend the theory of AIXI, and study universally intelligent embedded agents which start from a Solomonoff prior.
  arXiv  Detail & Related papers  (2025-11-27T08:46:48Z)
• Wisdom of Crowds Through Myopic Self-Confidence Adaptation [1.1060425537315088]
  The wisdom of crowds is an umbrella term for phenomena suggesting that the collective judgment or decision of a large group can be more accurate than the individual judgments or decisions of the group members.<n>In this paper, we consider a group of agents who initially possess uncorrelated and unbiased measurements of a common state of the world.<n>Assume these agents iteratively update their estimates according to a simple non-Bayesian learning rule, commonly known in sociology as the French-DeGroot dynamics or iterative opinion pooling.
  arXiv  Detail & Related papers  (2025-06-22T22:55:17Z)
• Disentangling Representations through Multi-task Learning [0.0]
  We provide experimental and theoretical results guaranteeing the emergence of disentangled representations in agents that optimally solve classification tasks.<n>We experimentally validate these predictions in RNNs trained to multi-task, which learn disentangled representations in the form of continuous attractors.<n>We find that transformers are particularly suited for disentangling representations, which might explain their unique world understanding abilities.
  arXiv  Detail & Related papers  (2024-07-15T21:32:58Z)
• Information is Power: Intrinsic Control via Information Capture [110.3143711650806]
  We argue that a compact and general learning objective is to minimize the entropy of the agent's state visitation estimated using a latent state-space model. This objective induces an agent to both gather information about its environment, corresponding to reducing uncertainty, and to gain control over its environment, corresponding to reducing the unpredictability of future world states.
  arXiv  Detail & Related papers  (2021-12-07T18:50:42Z)
• A General Framework for Distributed Inference with Uncertain Models [14.8884251609335]
  We study the problem of distributed classification with a network of heterogeneous agents. We build upon the concept of uncertain models to incorporate the agents' uncertainty in the likelihoods.
  arXiv  Detail & Related papers  (2020-11-20T22:17:12Z)
• Empirically Verifying Hypotheses Using Reinforcement Learning [58.09414653169534]
  This paper formulates hypothesis verification as an RL problem. We aim to build an agent that, given a hypothesis about the dynamics of the world, can take actions to generate observations which can help predict whether the hypothesis is true or false.
  arXiv  Detail & Related papers  (2020-06-29T01:01:10Z)
• Maximizing Information Gain in Partially Observable Environments via Prediction Reward [64.24528565312463]
  This paper tackles the challenge of using belief-based rewards for a deep RL agent. We derive the exact error between negative entropy and the expected prediction reward. This insight provides theoretical motivation for several fields using prediction rewards.
  arXiv  Detail & Related papers  (2020-05-11T08:13:49Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.