arXiv cs.CL· Zhipeng Chen, Yunsen Liang, Yanxi Chen, Hongkang Zhao, Lingyun Feng, Ruiyang Ren, Guoxin Chen, Jia Deng, Feng Chang, Chuan Hao, Ran Tao, Jian Yang, Ji-Rong Wen, Bryan Dai, Wayne Xin Zhao·· 13 小时前AI 评分49
DeepEvolve：面向未来预测的递归自我改进智能体系统
Evolving with Open Worlds: Towards Recursive Self-Improvement for Future Forecasting
AI 导读
DeepEvolve 是一个基于未来事件预测的可持续进化智能体系统，通过动态演化环境合成可验证任务，并用递归进化引擎将预测推理轨迹转化为能力。在每周更新的 FutureX 排行榜上，其自我改进的预测器连续三周排名第一，评分提升最高达 195%；在合成评测中于四个基础 LLM 上均进入前三，最高超过最强基线 10.7 个 Bradley-Terry 分。
正文 · 原文
Authors:Zhipeng Chen, Yunsen Liang, Yanxi Chen, Hongkang Zhao, Lingyun Feng, Ruiyang Ren, Guoxin Chen, Jia Deng, Feng Chang, Chuan Hao, Ran Tao, Jian Yang, Ji-Rong Wen, Bryan Dai, Wayne Xin Zhao
Abstract:Most contemporary artificial intelligence (AI) systems are released with frozen parameters and improve through external updates, whereas an ideal system would keep improving from its own experience, a capacity we call recursive self-improvement (RSI). Yet studying RSI requires an environment that is continuously changing, objectively verifiable, and naturally grounded, posing a fundamental challenge for agent evolution. Here we introduce DeepEvolve, a sustainable evolution agent system grounded in future event prediction, in which agents continuously interact with a dynamically evolving environment and improve by internalizing and externalizing the experience gained through these interactions. A living environment synthesizes verifiable tasks, and a recursive-evolution engine turns the reasoning trajectory behind each prediction back into capability: decoupling search from prediction adapts parameter-level evolution to the contamination-prone live environment, while distilling reusable skills lets the agent evolve from the limited live trajectories such an environment affords. On the external FutureX leaderboard, which evaluates predictions against real-world outcomes and is updated weekly, our self-improved forecaster ranked first across all systems over three consecutive weeks, achieving up to a 195% improvement in rating. On our synthesized evaluation, it ranked among the top three across four base LLMs, outperforming the strongest baseline by up to 10.7 Bradley--Terry points. More broadly, these results suggest that a system built for self-improvement is best understood as an agent that co-evolves with a genuinely living, open-ended environment, pointing to a shift in AI from training static models on fixed data toward cultivating agents that grow stronger from their own experience, with such an open world as the indispensable basis of that growth.
| Comments: | 47 pages, 13 figures. Working in progress |
| Subjects: | Computation and Language (cs.CL) |
| Cite as: | arXiv:2610.29784 [cs.CL] |
| (or arXiv:2610.29784v1 [cs.CL] for this version) | |
| https://doi.org/10.48550/arXiv.2610.29784 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Zhipeng Chen [view email]
[v1]
Wed, 21 Oct 2026 14:09:57 UTC (5,116 KB)
来源：arXiv cs.CL · arxiv.org