What Does a System Modify When It Modifies Itself?

arXiv:2603.27611 · cs.AI, q-bio.NC · Submitted 2026-03-29 · Read on arXiv

cs.AI, q-bio.NC

Submitted: 2026-03-29

Updated: 2026-09-03

Comments: 19 pages, 1 figure, 3 tables. Version 2 is a substantially rewritten and condensed journal-submission version. Version 1 (35 pages), which remains publicly available, contains the original longer formulation of the framework

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Core — 22× in this paper · explained in 2 episodes
• Metacognition — 14× in this paper · explained in 5 episodes
• Accuracy — 9× in this paper · explained in 1 episode
• Introspection — 8× in this paper · explained in 2 episodes
• Adaptation — 6× in this paper · explained in 1 episode
• Reinforcement Learning — 6× in this paper · explained in 4 episodes
• Meta-learning — 4× in this paper · explained in 2 episodes
• Active Inference — 3× in this paper · explained in 1 episode
• Reward Function — 3× in this paper · explained in 2 episodes
• Abstraction — 2× in this paper · explained in 1 episode
• Attention Schema Theory — 2× in this paper
• Fidelity — 2× in this paper · explained in 2 episodes
• Generative Model — 2× in this paper · explained in 2 episodes
• In-Context Learning — 2× in this paper · explained in 4 episodes
• World Model — 2× in this paper · explained in 7 episodes
• Alternation — 1× in this paper · explained in 1 episode
• Fine-Tuning — 1× in this paper · explained in 5 episodes
• Generative Models — 1× in this paper · explained in 2 episodes
• Interpretability — 1× in this paper · explained in 15 episodes
• Latent Representation — 1× in this paper · explained in 2 episodes
• Latent Representations — 1× in this paper · explained in 3 episodes
• Linear probe — 1× in this paper · explained in 2 episodes
• Longitudinal Data — 1× in this paper · explained in 2 episodes
• Loss Function — 1× in this paper · explained in 2 episodes
• Methodological Rigor — 1× in this paper · explained in 2 episodes
• Modularity — 1× in this paper · explained in 9 episodes
• Reward Shaping — 1× in this paper · explained in 2 episodes
• Verification — 1× in this paper · explained in 2 episodes

Sources

• Concrete Problems in AI Safety
• RL$^2$: Fast Reinforcement Learning via Slow Reinforcement Learning
• World Models
• Learning to reinforcement learn
• Darwin Godel Machine: Open-Ended Evolution of Self-Improving Agents

Related papers

• MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
• Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
• The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
• MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
• Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems
• VSAL: A Vision Solver with Adaptive Layouts for Graph Property Detection