The World Is Bigger! A Computationally-Embedded Perspective on the Big World Hypothesis

• URL: http://arxiv.org/abs/2512.23419v1
• Date: Mon, 29 Dec 2025 12:31:46 GMT
• Title: The World Is Bigger! A Computationally-Embedded Perspective on the Big World Hypothesis
• Authors: Alex Lewandowski, Adtiya A. Ramesh, Edan Meyer, Dale Schuurmans, Marlos C. Machado,
• Abstract summary: We describe a problem setting in which an agent, regardless of its capacity, is constrained by being embedded in the environment.<n>We propose an objective for this setting, which we call interactivity, that measures an agent's ability to continually adapt its behaviour by learning new predictions.<n>Our results show that deep nonlinear networks struggle to sustain interactivity, whereas deep linear networks sustain higher interactivity as capacity increases.
• Score: 40.015199580592174
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Continual learning is often motivated by the idea, known as the big world hypothesis, that "the world is bigger" than the agent. Recent problem formulations capture this idea by explicitly constraining an agent relative to the environment. These constraints lead to solutions in which the agent continually adapts to best use its limited capacity, rather than converging to a fixed solution. However, explicit constraints can be ad hoc, difficult to incorporate, and may limit the effectiveness of scaling up the agent's capacity. In this paper, we characterize a problem setting in which an agent, regardless of its capacity, is constrained by being embedded in the environment. In particular, we introduce a computationally-embedded perspective that represents an embedded agent as an automaton simulated within a universal (formal) computer. Such an automaton is always constrained; we prove that it is equivalent to an agent that interacts with a partially observable Markov decision process over a countably infinite state-space. We propose an objective for this setting, which we call interactivity, that measures an agent's ability to continually adapt its behaviour by learning new predictions. We then develop a model-based reinforcement learning algorithm for interactivity-seeking, and use it to construct a synthetic problem to evaluate continual learning capability. Our results show that deep nonlinear networks struggle to sustain interactivity, whereas deep linear networks sustain higher interactivity as capacity increases.

Related papers

• Agent-Dice: Disentangling Knowledge Updates via Geometric Consensus for Agent Continual Learning [41.461840578204956]
  Large Language Model (LLM)-based agents learn new tasks without catastrophic forgetting.<n>Agent-Dice is a parameter fusion framework based on directional consensus evaluation.<n>Experiments on GUI agents and tool-use agent domains demonstrate that Agent-Dice exhibits outstanding continual learning performance.
  arXiv  Detail & Related papers  (2026-01-07T06:43:50Z)
• 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)
• Agent0: Unleashing Self-Evolving Agents from Zero Data via Tool-Integrated Reasoning [84.70211451226835]
  Large Language Model (LLM) Agents are constrained by a dependency on human-curated data.<n>We introduce Agent0, a fully autonomous framework that evolves high-performing agents without external data.<n>Agent0 substantially boosts reasoning capabilities, improving the Qwen3-8B-Base model by 18% on mathematical reasoning and 24% on general reasoning benchmarks.
  arXiv  Detail & Related papers  (2025-11-20T05:01:57Z)
• Adaptive and Resource-efficient Agentic AI Systems for Mobile and Embedded Devices: A Survey [11.537225726120495]
  Foundation models have reshaped AI by unifying fragmented architectures into scalable backbones with multimodal reasoning and contextual adaptation.<n>With FMs as their cognitive core, agents transcend rule-based behaviors to achieve autonomy, generalization, and self-reflection.<n>This survey provides the first systematic characterization of adaptive, resource-efficient agentic AI systems.
  arXiv  Detail & Related papers  (2025-09-30T02:37:52Z)
• Computational Irreducibility as the Foundation of Agency: A Formal Model Connecting Undecidability to Autonomous Behavior in Complex Systems [0.0]
  we establish precise mathematical connections, proving that for any truly autonomous system, questions about its future behavior are fundamentally undecidable.<n>The findings have significant implications for artificial intelligence, biological modeling, and philosophical concepts like free will.
  arXiv  Detail & Related papers  (2025-05-05T21:24:50Z)
• Principal-Agent Reinforcement Learning: Orchestrating AI Agents with Contracts [20.8288955218712]
  We propose a framework where a principal guides an agent in a Markov Decision Process (MDP) using a series of contracts. We present and analyze a meta-algorithm that iteratively optimize the policies of the principal and agent. We then scale our algorithm with deep Q-learning and analyze its convergence in the presence of approximation error.
  arXiv  Detail & Related papers  (2024-07-25T14:28:58Z)
• Scaling Large Language Model-based Multi-Agent Collaboration [72.8998796426346]
  Recent breakthroughs in large language model-driven autonomous agents have revealed that multi-agent collaboration often surpasses each individual through collective reasoning.<n>This study explores whether the continuous addition of collaborative agents can yield similar benefits.
  arXiv  Detail & Related papers  (2024-06-11T11:02:04Z)
• Sim-to-Real Causal Transfer: A Metric Learning Approach to Causally-Aware Interaction Representations [58.96953392466609]
  We take an in-depth look at the causal awareness of modern representations of agent interactions.<n>We show that recent representations are already partially resilient to perturbations of non-causal agents.<n>We introduce a metric learning approach that regularizes latent representations with causal annotations.
  arXiv  Detail & Related papers  (2023-12-07T18:57:03Z)
• Neural Amortized Inference for Nested Multi-agent Reasoning [54.39127942041582]
  We propose a novel approach to bridge the gap between human-like inference capabilities and computational limitations. We evaluate our method in two challenging multi-agent interaction domains.
  arXiv  Detail & Related papers  (2023-08-21T22:40:36Z)
• Ubiquitous Distributed Deep Reinforcement Learning at the Edge: Analyzing Byzantine Agents in Discrete Action Spaces [0.06554326244334865]
  This paper discusses some of the challenges in multi-agent distributed deep reinforcement learning that can occur in the presence of byzantine or malfunctioning agents. We show how wrong discrete actions can significantly affect the collaborative learning effort. Experiments are carried out in a simulation environment using the Atari testbed for the discrete action spaces, and advantage actor-critic (A2C) for the distributed multi-agent training.
  arXiv  Detail & Related papers  (2020-08-18T11:25:39Z)

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.