arXiv:2510. 04399v3 Announce Type: replace Abstract: We develop a learning-theoretic framework for analyzing self-improving agents by decomposing self-modification into five axes.
arXiv:2608. 10157v1 Announce Type: new Abstract: Self-improving agents seek to reduce the human engineering effort behind AI systems by enabling them to evolve and self-improve their performance over time.
arXiv:2607. 13104v1 Announce Type: new Abstract: Self-improving autonomous agents are moving from research prototypes to deployed systems.
arXiv:2509. 03206v2 Announce Type: replace-cross Abstract: Learning from reward functions and imitation learning of demonstrations are the two principal approaches for training autonomous systems that interact with an environment through action and observation.
arXiv:2608. 10332v1 Announce Type: cross Abstract: Differentiable predictive control (DPC), a self-supervised learning approach for approximating explicit model predictive control (MPC) policies, offers significant computational advantages over online optimization-based MPC.
arXiv:2607. 04277v1 Announce Type: cross Abstract: The pursuit of self-evolving AI raises a critical question: when is autonomous self-improvement sustainable rather than degenerative?
arXiv:2606. 00251v1 Announce Type: new Abstract: The ability to recognize one's own limitations and decide whether to solve a problem or delegate is fundamental for reliable intelligent systems.
arXiv:2607. 00871v1 Announce Type: new Abstract: Self-evolving agents violate the assumption behind most learning-theoretic guarantees: the data, evaluator, components, and hypothesis space are produced by the policy being updated.
arXiv:2608. 13040v1 Announce Type: new Abstract: Enabling agents to learn from experience and internalize it into their policy has become a central problem in self-evolving AI.
Reinforcement Learning with Verifiable Rewards (RLVR) has driven recent progress in reasoning-oriented large language models (LLMs) by enabling large-scale optimization. However, its applicability remains largely limited to domains such as mathematics and coding, where correctness can be deterministically verified.
arXiv:2608. 07228v1 Announce Type: new Abstract: When a reinforcement learning agent cannot observe the full state, we usually blame its policies: it cannot see enough to represent a good one.
arXiv:2607. 07663v1 Announce Type: new Abstract: AI systems increasingly participate in their own improvement: revising their outputs, adapting their own harnesses during deployment, training on data they generate, and, increasingly, conducting AI research itself.
arXiv:2606. 28347v1 Announce Type: cross Abstract: Contemporary AI safety spans pre-training interventions, post-training alignment, deployment-time controls, monitoring, and red-teaming.