Efficient Long-hOrizon (ELO) learning is introduced, an efficient meta-training algorithm that reallocates wasted meta-training compute to longer failure regimes, achieving efficient long-horizon learning, and enforces decoupled progressive expert supervision, providing stable meta-learning signals that additionally improve the generalization of LOs.
Abstract
Learned optimization aims to improve upon hand-designed optimizers (e.g., Adam and Muon) by meta-learning small neural network optimizers over a distribution of tasks. While recent work has greatly advanced the architectural design and inductive biases of learned optimizers (LOs), their meta-training remains biased toward short-unroll learning on particular tasks, resulting in redundant computation and leaving LOs often unable to compete with hand-designed optimizers. We introduce Efficient Long-hOrizon (ELO) learning, an efficient meta-training algorithm that (1) reallocates wasted meta-training compute to longer failure regimes, achieving efficient long-horizon learning, and (2) enforces decoupled progressive expert supervision, providing stable meta-learning signals that additionally improve the generalization of LOs. Our empirical study evaluates ELO for meta-training both element-wise and matrix-based LOs. Across downstream language modeling (GPT-2-124M/350M on FineWeb) and image classification (ViT-B/16, ResNet-50 on ImageNet-1K) tasks, ELO substantially improves the long-unroll performance and out-of-distribution generalization of the base LOs. In particular, ELO-Celo2 consistently outperforms well-tuned AdamW across all evaluated tasks, while remaining competitive with Muon on language modeling. \textit{Notably, all ELO baselines require less than 7 H100 GPU-hours for meta-training.}
ESRL is introduced, an architecture-aware framework that explicitly explores the expert-routing space of MoE models, and preserves high-confidence experts as anchors, and restricts stochastic routing to a plausible candidate pool, thereby retaining reliable computation paths.
Hong-Yi He, Zheng-Wen Lin, Xiao Liu et al.· 0 citations
This work introduces FunL2O, the first unified framework for automating feature design through LLM-driven program evolution for L2O, and establishes LLM-driven feature evolution as a general and effective approach to automating representation design in L2O.
This work introduces Elite-Weighted Supervised Fine-tuning (EW-SFT), which uses reward to guide elite selection of high-scoring molecules, and updates the model by its own pretraining loss on that set, and consistently outperforms the corresponding native optimizers.
Shiyun Wa, Yifei Wang, A. G. Green et al.· 0 citations
A simple modification to supervised fine-tuning, TailSFT, which filters out already fit sequences during training, thereby focusing learning on under-modeled regions, or the tail, of the data distribution, and introduces a lightweight diagnostic for identifying settings where TailSFT is most likely to help.
Sadhika Malladi, Samy Jelassi, Dylan J. Foster et al.· 3 citations
Reinforcement learning with verifiable rewards (RLVR) is rapidly advancing the reasoning capabilities of language models, yet the optimization layer that converts reward feedback into weight-space updates remains poorly understood. Building on our prior analysis (Zhu et al., 2025), we study this missing layer through t...
DIEM is proposed, a principled and fully automated framework that makes data utilization adaptive throughout RFT and consistently outperforms strong static and dynamic baselines.
Haoru Tan, Sitong Wu, Yan-Feng Chen et al.· 0 citations
Related blog posts
MIT News · Artificial Intelligence· news.mit.eduNov 17, 2026
By studying the computational foundations of language learning, Associate Professor Jacob Andreas builds intelligent systems that can communicate effectively with humans.
Microsoft Research Blog· microsoft.comNov 16, 2026
AI coding agents are increasingly help developers fix bugs and build features largely on their own, but every interaction with their models consumes tokens. In each session, an agent sends instructions, tool descriptions, and session history to its model. Most efforts to reduce this cost focus on individual tasks. Yet developers return to the same […] The post TokenEconomizer: Learning from Experience to Make AI Coding Agents More Efficient appeared first on Microsoft Research.
MIT News · Artificial Intelligence· news.mit.eduNov 13, 2026