| title | Epi: Towards a Persistent, Self-Improving Agent for Autonomous Research |
|---|---|
| authors | Yue Huang, Zhangchen Xu, Xiaonan Luo, Zheyuan Liu, Lichi Li, Yiping Wang, Peiyang Song, Eric Gabriel Ramos, Enze Xie, Olexandr Isayev, Paul Liang, Nouha Dziri, Huan Sun, Jianfeng Gao, Ying Liu, Misha Sra, Xiangliang Zhang, Alex Pentland, Zichen Chen |
| date | 2026-10-18 |
| venue | arXiv (preprint, not peer reviewed) |
| id | arXiv:2610.24944 |
| affiliation | BakeLab |
| upvotes | 23 (Hugging Face Daily Papers, 2026-11-01) |
| links | abs pdf hf code |
| abstract | We present Épi, an autonomous research agent that sustains investigations across model sessions and evolves its methods through accumulated experience. Épi combines persistent research history, hierarchical memory, branching and independent review to maintain research continuity, learn from experiments, and explore and revisit alternative approaches. Its experiments run across session boundaries, and a fixed verifier evaluates their outputs. Épi produced 120 record-setting results, comprising 20 numerical bound records across 12 families and 100 construction records across eight families. These include an approximately 84-fold narrower interval for the n-queens constant and a more than 3.6-million-fold narrower rigorous interval for the quartic Feigenbaum attractor dimension. Exact dual certificates establish that the Cohn-Elkies linear-programming bound cannot be sharp in dimensions 10 and 11. Beyond numerical improvements, Épi gives a computer-assisted proof of Tuza's conjecture for split graphs with an eight-vertex clique part and at most three triangle-active neighborhood types, with arbitrary multiplicities. We extend this research process to algorithmic coding with Épi-turbo, a lightweight configuration that develops executable solvers for tasks including vehicle routing, scheduling and production planning. On 30 FrontierOR tasks, Épi-turbo achieves a 5.4% higher total benchmark score than Codex at 64% of its model cost, using the same underlying model and reasoning effort. Épi is designed to support human understanding by connecting computational results to explicit methods and mathematical arguments that researchers can examine and build upon. |
cite
@misc{huang2026epi,
title={Epi: Towards a Persistent, Self-Improving Agent for Autonomous Research},
author={Yue Huang and Zhangchen Xu and Xiaonan Luo and Zheyuan Liu and Lichi Li and Yiping Wang and Peiyang Song and Eric Gabriel Ramos and Enze Xie and Olexandr Isayev and Paul Liang and Nouha Dziri and Huan Sun and Jianfeng Gao and Ying Liu and Misha Sra and Xiangliang Zhang and Alex Pentland and Zichen Chen},
year={2026},
eprint={2610.24944},
archivePrefix={arXiv},
url={https://arxiv.org/abs/2610.24944}
}