Epi: Towards a Persistent, Self-Improving Agent for Autonomous Research
Yue Huang, Zhangchen Xu, Paul Liang, Nouha Dziri, Huan Sun, Jianfeng Gao, Xiangliang Zhang, Alex Pentland and colleagues present Épi, a research agent that keeps investigations going across model sessions through persistent history, hierarchical memory, branching and independent review, with a fixed verifier scoring outputs.
Ask this paper
Record count. Épi produced 120 record-setting results: 20 numerical bound records across 12 families and 100 construction records across eight families.
Examples. These include an interval for the n-queens constant about 84 times narrower and a rigorous interval for the quartic Feigenbaum attractor dimension more than 3.6 million times narrower. Exact dual certificates show the Cohn-Elkies LP bound cannot be sharp in dimensions 10 and 11.
Proof result. It 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.
Épi-turbo. A lightweight configuration for solver coding scores 5.4% higher than Codex on 30 FrontierOR tasks at 64% of its model cost, with the same model and reasoning effort.
Abstract
We present \'{E}pi, an autonomous research agent that sustains investigations across model sessions and evolves its methods through accumulated experience. \'{E}pi 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. \'{E}pi 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, \'{E}pi 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 \'{E}pi-turbo, a lightweight configuration that develops executable solvers for tasks including vehicle routing, scheduling and production planning. On 30 FrontierOR tasks, \'{E}pi-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. \'{E}pi is designed to support human understanding by connecting computational results to explicit methods and mathematical arguments that researchers can examine and build upon.