arXiv 2610.24944 · cs.CL · 2026-10-18
Epi: Towards a Persistent, Self-Improving Agent for Autonomous Research
Yue Huang, Zhangchen Xu, Xiaonan Luo, Zheyuan Liu, Lichi Li, Yiping Wang, Peiyang Song, Eric Gabriel Ramos 等 19 人
BakeLab
在最新榜 #327 本站收录于 2026-10-25
一句话要点
Épi 是能跨会话持续工作、靠经验自我改进的自主科研 agent，结合持久研究记录、分层记忆、分支探索和独立评审，产出 120 项数学纪录，如 n 皇后常数区间收窄约 84 倍。
Épi is a persistent, self-improving research agent with research history, hierarchical memory, branching and independent review; it produced 120 record-setting math results, e.g. an ~84x narrower interval for the n-queens constant.
阅读 arXiv 原文 PDF Hugging Face 讨论 代码仓库 项目页
主题与学科
同主题：智能体
- Raven: The Harness of Harnesses for Composable Agentic Intelligence ▲748
- False Frontiers: Diagnosing and Mitigating Co-Cheating in Self-Evolving Search Agents ▲642
- Omni-IO Skills: Harnessing Your Agent Omni-Native ▲485
- BizAgentBench: Unveiling Hidden Challenges in Deploying Long-Horizon Agents for Real-World Business ▲388
- Player-1: Learning to Play from Synthetic Experience ▲347
同主题：AI for Science
- Scaling Parameter-Efficient Fine-Tuning for Brain Encoding 2026-10-19 · ▲247
- Into the Unknown: Benchmarking AI agents on open scientific research problems 2026-10-13 · ▲144
- EvoDuet: Bilevel Co-Evolution of Web Searching and Task Solving for Scientific Discovery 2026-09-30 · ▲112
- Predictive Credit: Measuring What Scientific Explanations Add to Experimental Forecasts 2026-09-29 · ▲103
- X-Ragent: Tool-Augmented Reinforcement Learning for Evidence-Grounded Chest X-Ray Reasoning 2026-10-12 · ▲79
数据说明
元数据来自 arXiv API（已核实）；点赞来自 Hugging Face 每日论文；引用来自 Semantic Scholar。最近刷新 2026-10-26。
要点由本站根据摘要自写，不转载摘要原文，请阅读原文。