Large language models (LLMs) like GPTs, trained on vast datasets, have demonstrated impressive capabilities in language understanding, reasoning, and planning, achieving human-level performance in various tasks. Most studies focus on enhancing these models by training on ever-larger datasets to build more powerful foundation models. While training stronger models is important, enabling models to evolve during inference is equally crucial, a process we refer to as AI self-evolution. Unlike large-scale training, self-evolution may rely on limited data or interactions. Inspired by the columnar organization of the human cerebral cortex, we hypothesize that AI models could develop cognitive abilities and build internal representations through iterative interactions with their environment. To achieve this, models need long-term memory (LTM) to store and manage processed interaction data. LTM supports self-evolution by representing diverse experiences across environments and agents. In this report, we explore AI self-evolution and its potential to enhance models during inference. We examine LTM's role in lifelong learning, allowing models to evolve based on accumulated interactions. We outline the structure of LTM and the systems needed for effective data retention and representation. We also classify approaches for building personalized models with LTM data and show how these models achieve self-evolution through interaction. Using LTM, our multi-agent framework OMNE achieved first place on the GAIA benchmark, demonstrating LTM's potential for AI self-evolution. Finally, we present a roadmap for future research, emphasizing the importance of LTM for advancing AI technology and its practical applications.

翻译：基于海量数据训练的GPT等大型语言模型（LLM）在语言理解、推理与规划方面展现出卓越能力，已在多项任务中达到人类水平。当前研究多集中于通过更大规模数据训练来构建更强大的基础模型。尽管训练更强大的模型至关重要，但让模型在推理过程中实现自主进化同样关键，这一过程我们称之为人工智能自我进化。与大规模训练不同，自我进化可能仅依赖有限的数据或交互。受人类大脑皮层柱状结构的启发，我们提出假设：人工智能模型可通过与环境的迭代交互发展认知能力并构建内部表征。为实现这一目标，模型需要长期记忆（LTM）来存储和管理已处理的交互数据。LTM通过表征跨环境与智能体的多样化经验来支持自我进化。本报告探讨了人工智能自我进化及其在推理阶段增强模型的潜力。我们研究了LTM在终身学习中的作用，使模型能够基于累积交互实现进化。我们概述了LTM的结构及实现高效数据保持与表征所需的系统架构。同时，我们对利用LTM数据构建个性化模型的方法进行分类，并展示这些模型如何通过交互实现自我进化。基于LTM构建的多智能体框架OMNE在GAIA基准测试中荣获首位，证明了LTM推动人工智能自我进化的潜力。最后，我们提出了未来研究的路线图，强调LTM对推进人工智能技术及其实际应用的重要性。