The rapid advancement of large language models (LLMs) has significantly enhanced the capabilities of AI-driven agents across various tasks. However, existing agentic systems, whether based on fixed pipeline algorithms or pre-defined meta-learning frameworks, cannot search the whole agent design space due to the restriction of human-designed components, and thus might miss the globally optimal agent design. In this paper, we introduce Gödel Agent, a self-evolving framework inspired by the Gödel machine, enabling agents to recursively improve themselves without relying on predefined routines or fixed optimization algorithms. Gödel Agent leverages LLMs to dynamically modify its own logic and behavior, guided solely by high-level objectives through prompting. Experimental results on mathematical reasoning and complex agent tasks demonstrate that implementation of Gödel Agent can achieve continuous self-improvement, surpassing manually crafted agents in performance, efficiency, and generalizability.
Escher-Loop: Mutual Evolution by Closed-Loop Self-Referential Optimization
Shenzhen X-Institute（深圳X研究所）；Soochow University（苏州大学）；Shenzhen Loop Area Institute（深圳河套学院）；Tsinghua University（清华大学）；National University of Singapore（新加坡国立大学）
The Psychogenic Machine: Simulating AI Psychosis, Delusion Reinforcement and Harm Enablement in Large Language Models
King’s College Hospital（国王学院医院）；Nuraxi AI Dev and Doc: AI for Healthcare（Nuraxi AI 人工智能医疗）；Sage Bionetworks（Sage 生物网络）；University College London（伦敦大学学院）；King’s College London（国王学院伦敦）
