Newest papers

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

Zhipeng Chen, Yongli 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 · 2026 · arXiv (Cornell University)

DOI: 10.48550/arxiv.2610.29784 · cited by 0 works (OpenAlex) · open-access PDF

Korean

대부분의 현대적인 에이전트 인공 지능 (AI) 시스템은 고정된 매개 변수로 공개되며 외부 업데이트를 통해 개선되며, 이상적인 시스템은 자신의 경험에서 개선을 계속할 것이며, 우리는 복구적 자기 향상 (RSI) 교육을 호출 할 수있는 능력입니다. 그럼에도 불구하고 RSI를 연구하는 것은 지속적으로 변화하고 객관적으로 검증 할 수있는 환경을 내부화하고 외부화함으로써 지속적으로 변화하는 환경을 필요로합니다. 외부 업데이트를 통해 기본적인 도전을 제공하는 라이브 환경은 검증 할 수있는 작업을 합성합니다. 여기에서 우리는 EvoForesight를 소개합니다. 지속 가능한 진화 에이전트 시스템은 미래의 이벤트 예측을 기반으로하며, 에이전트는 역동적으로 진화하는 환경과 지속적으로 상호 작용

Machine translation (Meta M2M100); the English original follows.

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 EvoForesight, 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.

Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese

Topics: Computer science, Artificial intelligence, Machine learning, Baseline (sea), Event (particle physics), Verifiable secret sharing

Sources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange