Reactive Optimizers

← Xingjian Bai Xingjian Bai, Jia-Hao Liang, Jayden Teoh, Vincent SitzmannOctober 2026 TL;DR We put an agent at the heart of the optimizer. It watches the training dynamics, reacts to them, and rewrites the optimizer’s source code as training goes. When no recipe has been tuned for a task, it matches or beats the best recipe one could pick off the shelf, across image and language tasks. Further, we demonstrate that it spontaneously comes up with sophisticated schedules and intricate strategies to prevent loss spikes and escape overfitting. Try it on your own training run with the OPAL package. X post: x.com/SimulatedAnneal/status/2112936831398375800 A static optimizerstep 0 A reactive optimizerstep 0 LightningDiT-XL/1 on ImageNet Today, the recipe used to optimize a deep neural network is typically completely determined before training even begins. A great deal of human ingenuity has gone into priors regarding how training should progress: adaptive step sizes [1], preconditioning [2, 3], orthogonalized updates [4, 5], schedules tied to the training step [6, 7], and learning rates scaled with model size [8]. Automated discovery [9, 10, 11, 12] searches across many runs for better optimizers. Whether hand-crafted or automatically discovered, the optimizer then runs unchanged through the end of training, adapting, if at all, according to rules written in advance. This scope leaves the following questions unanswered: How should an optimizer respond to an unexpected loss spike or stall? What if one module's gradients start to oscillate while the others keep improving smoothly? And when a new type of architecture trains poorly with Adam or Muon, is the architecture worse, or has it not yet met an optimizer suited to it? In this post, we attempt to expand the scope of conventional optimizers and make them reactive to the training itself, leading to an ever-adapting optimizer inside a single training run. This reactive optimizer reasons on the spot and writes the weight update rule for each parameter group. Directly writing optimization code, it has the freedom to implement complicated schedules, respond to training accidents, and customize the optimizer for the single training episode in which it exists. Building on earlier attempts to adapt optimizers during training [12, 13, 14] and to let a model direct its own fine-tuning [15], the reactive optimizer is entirely zero-shot, with nothing learned or retained from repeated runs, and puts the optimizer's entire algorithm up for rewriting. We start with a practical situation, with tasks from image generation and language modeling, in which a reactive optimizer can do much better than static ones. We then turn to the emergent properties of the reactive optimizer, including sophisticated scheduling, suppressing loss spikes, and escaping overfitting. Lastly, we ask what all this costs and how practical it is at scale. We expect the reactive optimizer to grow only stronger with each generation of agents, to be most useful exactly where no recipe exists yet (for a new architecture or a new dataset), and to be one step toward solving the puzzles of deep learning optimization.

Contents 1.

Training without a recipe 2. Updating with spontaneous analysis 3. What is dynamically changing during optimization?

4.

Real-world applicability 5.

Conclusion 1.