cs.LGNov 17, 2026

JEPA as a Transferable Optimizer: Learning and Understanding Black-Box Optimization from Reward-Agnostic Pretraining

Authors: Mayukh Debnath, Manan Roy Choudhury

Organizations: Robotics and Autonomous Systems (AI), Arizona State University, Tempe, USA · Department of Artificial Intelligence, Arizona State University, Tempe, USA

Abstract

Black-box optimization evaluates candidates through simulations, rollouts, or experiments, often without gradients. Learned optimizers are usually judged by whether they outperform existing methods. We ask a complementary question: what information does a learned optimizer use from its search history? We introduce JEPA-PS (JEPA Policy Search), based on a Joint-Embedding Predictive Architecture. It is pretrained on random rollouts using parameter vectors and scalar returns. Its latent-prediction objective predicts the next point in an optimization trajectory rather than its reward or gradient, allowing us to examine what was tried and how well it performed. At test time, JEPA-PS reads a short evaluation history and proposes a candidate in one forward pass, without task descriptions, reward shaping, or test-time gradients. We evaluate it on 15 control environments against 12 optimizers, including evolutionary methods, Bayesian optimization, CMA-ES, and an LLM optimizer. JEPA-PS is competitive with tuned classical baselines and outperforms the LLM optimizer by more than 2x on Swimmer at 71x lower per-step cost. It also transfers zero-shot to environments excluded from pretraining. Null-model comparisons and decoder-training ablations indicate that its latent representation carries information beyond simple history statistics; every trained decoder variant performs worse than the default frozen representation. Our main finding is that the history JEPA-PS uses depends on the task. On smooth landscapes it uses the full trajectory, whereas on rugged landscapes the best-seen point carries nearly all the signal. This memory requirement has a weak positive correlation with fitness-distance correlation (FDC; r=0.112, n=7), while an independent reward-ordering sensitivity probe does not corroborate the relationship (r=-0.024, n=7). Code: https://github.com/mdebnath22/jepa-props.

Figures & tables

Appendix figures & tables32 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

Sep 8, 2026

Code-to-Harness: Distilling Black-Box Optimizers from Self-Play

Can an agent learn a numerical search strategy through executable practice and then transfer that strategy as text? We study low-budget black-box optimization, where unaided language models remain well below strong classical optimizers. During development, an agent repeatedly writes and evaluates optimizer programs. It then distills the resulting program and practice record once into a 197-word primary Harness A, which is frozen before evaluation. Harness A reduces Gemini Flash regret by 48% in an independent N=30N=30 study (p<.001p<.001), enters the GP-BO performance range on the practice family, and lowers mean regret on all three held-out BBOB landscapes. The same text improves every tested Gemini executor and transfers to Claude Sonnet, reducing regret by 43% and 49% (p≤.005p\leq.005). An independent end-to-end replication produces Harness B, a different program and text at the same performance tier. The same framework also attains the lowest regret on a sealed YouTube reward-tuning production benchmark. Executable practice is thus a viable way to discover a search policy, and language a portable medium for deploying it.
Oct 23, 2026

RSI-Opt: Recursive Self-Improvement Optimizer Agents For Model Training

Conventional neural-network training typically follows a predefined optimization recipe, motivating a LLM agent that monitors training dynamics and adjusts optimizer settings as training progresses, but a fixed agent policy does not accumulate experience across runs. We introduce RSI-Opt, a plug-and-play Recursive Self-Improvement Optimizer Agents which evolves the knowledge that guides this process: a prompt, a playbook of procedures, a library of tested optimizer code, and a decision cadence. A meta-agent rewrites this policy using evidence from earlier runs, and an archive retains evaluated policies for further evolution. Across 5 generations on three training tasks, the meta-agents develop reusable procedures and code and conduct their own CPU proxy experiments. RSI-Opt substantially improves optimizer-agent performance, with representative raw-space summary zz-scores increasing from +10.48+10.48 to +14.33+14.33 on the evolution suite with Opus 5.5 and from −0.36-0.36 to +3.11+3.11 on held-out tasks with GPT-5.5 through cross-model policy transfer. On the Burgers PDE, it reduces mean relative L2L_2 error by approximately 2.7-fold with Opus 5.5 and 8.8-fold with GPT-6.1 over the fixed-prompt agent baseline, although PDE transfer varies across LLMs and tasks. Controlled comparisons show that the evolved policy combines reusable optimization knowledge with adaptation to each task: initial decisions capture most observed gains on seen tasks, while continued adaptation improves outcomes on unseen tasks. These findings demonstrate how procedures and executable tools accumulated across training runs can improve optimizer-agent performance and support transfer to scientific machine learning.
May 22, 2026

An Open-Source Training Dataset for Foundation Models for Hyperparameter Optimization

Most hyperparameter optimization methods require extensive tuning of their own hyperparameters, often limiting their ability to generalize across different benchmark families. Foundation models for hyperparameter optimization that learn optimization principles from a large collection of optimization trajectories offer a promising alternative, with the potential to outperform manually designed methods across diverse problem classes. However, prior work as either relied on non-public datasets or on purely synthetic data, limiting reproducibility and generalization to real-world problems. As a result, progress in this area has been constrained by the lack of large-scale, real-world, publicly available pre-training data. We introduce BBO-Pile, the first open-source dataset comprising over 500K optimization trajectories evaluated across 3,095 different hyperparameter optimization tasks and global optimization problems for different optimizers, which represents by far the largest public dataset for this task. Using this dataset, we train a family of foundation models at multiple scales, ranging from 2M to 80M parameters and from 200M to 2B training tokens, and study their scaling behavior with respect to compute. Our results demonstrate that large-scale pre-training is a viable and effective approach to imitate hyperparameter optimization methods, paving the way for future research in this direction.