Driving · 2026-11-03
Spacetime Emergence in the Memory of a Learning Agent
Philip A. LeMaitre, T. Rick Perche
AI-assisted summary based on the paper. Consult the linked source for methods and limitations. Benchmark numbers appear after editor verification.
TL;DR
The authors train a model-based reinforcement-learning agent on a quantum information task involving two Unruh–DeWitt qubits coupled to a massless scalar field in Minkowski spacetime. The only reward is the quantum mutual information between the detectors, with no metric/causal structure provided. The agent’s internal planner develops null/lightcone structure, enabling reconstruction of the Minkowski causal structure with high accuracy from its memory.
Why it matters
The paper argues that spacetime causal structure can emerge inside an agent’s learned memory using only operational quantum rewards. By reconstructing components of the Minkowski metric from the agent’s learned predictive representation, it connects operational quantum experience, active agent behavior, and recoverable spacetime geometry.
Method
- Construct an RL environment where detector 2’s spacetime smearing center is varied on a grid; the reward is quantum mutual information between two UDW qubits coupled to a real massless scalar field in (3+1)-dimensional Minkowski spacetime.
- Train a model-based RL agent with a learned internal predictive model (encoder/decoder, transition/reward models, and planning rule) using only the reward signal, with no prior spacetime metric or causal-structure information.
- After training, apply a mask to the learned planner representation to minimally identify lightcone-like branches and fit a quadratic form to extract metric tensor components (up to conformal freedom).
Abstract (from arXiv)
We show that the causal structure of spacetime can emerge within the memory of a learning agent performing a quantum information task. We train a model-based reinforcement-learning agent to maximize the quantum mutual information between localized quantum probes interacting with a quantum field in Minkowski spacetime, without directly providing it with information regarding the spacetime metric or causal structure. In learning to accomplish this task, the reinforcement-learning agent constructs an internal predictive model whose planner develops the characteristic null structure of spacetime, allowing us to reconstruct the causal structure of the Minkowski metric with high accuracy. Within this task, spacetime geometry is obtained from an agent's successful predictions and actions, providing a first step toward showing that spacetime concepts emerge from operational quantum experience.
Related papers
- Reinforcement Learning with Complex (valued) Memories
- Axiomatic World Modeling for Physics Reasoning
- A Bayesian Mirror Architecture for Emergent Consciousness: Circular Hierarchies, Self-Manifolds, and Hybrid Event-Self Binding
- Quantum-JEPA: Quantum Born Priors for Latent-Action JEPA World Models
- Learning to Plan from Random Exploration
Publication record
Bibliographic evidence describes where and when a record appeared. It does not validate scientific claims.
First public release: 2026-11-02 · Indexed by Pub-AI: 2026-11-03 UTC
Spacetime Emergence in the Memory of a Learning Agent
Preprint posted: 2026-11-02 · Original record ↗
- arxiv
- 2611.03596
Explicit source versions (1)
- v1 · 2026-11-02
- Preprint available
Source date: 2026-11-02 · First detected: 2026-11-03 UTC · Historical baseline
Source evidence (1)
- Official evidence ↗ · atom:published (official metadata)
Abstract · arxiv
We show that the causal structure of spacetime can emerge within the memory of a learning agent performing a quantum information task. We train a model-based reinforcement-learning agent to maximize the quantum mutual information between localized quantum probes interacting with a quantum field in Minkowski spacetime, without directly providing it with information regarding the spacetime metric or causal structure. In learning to accomplish this task, the reinforcement-learning agent constructs an internal predictive model whose planner develops the characteristic null structure of spacetime, allowing us to reconstruct the causal structure of the Minkowski metric with high accuracy. Within this task, spacetime geometry is obtained from an agent's successful predictions and actions, providing a first step toward showing that spacetime concepts emerge from operational quantum experience.
