跳到正文
HuggingFace Daily Papers(社區熱門論文)·· 2026-10-21AI 評分45

與開放世界共同演進:邁向面向未來預測的遞歸自我改進

Evolving with Open Worlds: Towards Recursive Self-Improvement for Future Forecasting

AI 導讀

DeepEvolve 是一個以未來事件預測為基礎的持續演進智能體系統,透過與動態環境互動,將預測推理過程轉化為能力。在每週更新的 FutureX 排行榜上,它連續三週排名所有系統第一,評分提升最高達 195%。在合成評測中,它於四個基礎 LLM 中均名列前三,較最強基線高最多 10.7 Bradley--Terry points。

正文

Published on Oct 21

Authors:

,

,

,

,

,

,

,

,

,

,

,

,

,

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.

View arXiv page View PDF GitHub Add to collection

Get this paper in your agent:

hf papers read 2610.29784

Don't have the latest CLI?

curl -LsSf https://hf.co/cli/install.sh | bash

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2610.29784 in a model README.md to link it from this page.

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/2610.29784 in a dataset README.md to link it from this page.

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2610.29784 in a Space README.md to link it from this page.

Collections including this paper 0

No Collection including this paper

Add this paper to a collection to link it from this page.

來源:HuggingFace Daily Papers(社區熱門論文) · huggingface.co