Saved in:
Bibliographic Details
Main Authors: Alhajir, Alfath Daryl, Dodgson, Jennifer, Lim, Joseph, Phi, Truong Ma, Peh, Julian, Pattirane, Akira Rafhael Janson, Poovaragan, Lokesh
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2504.04711
Tags: Add Tag
No Tags, Be the first to tag this record!
Table of Contents:
  • Current large language models (LLMs) are constrained by human-derived training data and limited by a single level of abstraction that impedes definitive truth judgments. This paper introduces a novel framework in which AI models autonomously generate and validate new knowledge through direct interaction with their environment. Central to this approach is an unbounded, ungamable numeric reward - such as annexed disk space or follower count - that guides learning without requiring human benchmarks. AI agents iteratively generate strategies and executable code to maximize this metric, with successful outcomes forming the basis for self-retraining and incremental generalisation. To mitigate model collapse and the warm start problem, the framework emphasizes empirical validation over textual similarity and supports fine-tuning via GRPO. The system architecture employs modular agents for environment analysis, strategy generation, and code synthesis, enabling scalable experimentation. This work outlines a pathway toward self-improving AI systems capable of advancing beyond human-imposed constraints toward autonomous general intelligence.