通用智能体：通过上下文信息密度最大化实现令牌高效的自演进大语言模型代理（V1.0版）

摘要

长视野大型语言模型（LLM）智能体的根本局限在于上下文容量。随着交互时长增加，工具描述、检索记忆和原始环境反馈会不断累积，进而挤占决策所需的关键信息。与此同时，任务中获得的有效经验往往在多次执行中流失。我们认为，长视野性能并非取决于上下文长度，而在于有限上下文预算内能保留多少与决策相关的信息。本文提出通用智能体（GA）——一个围绕核心原则（上下文信息密度最大化）构建的通用自进化LLM智能体系统。GA通过四个紧密关联的组件实现这一目标：保持接口简洁的最小化原子工具集、默认仅展示高层摘要的分层按需记忆机制、将已验证任务轨迹转化为可复用标准操作流程与可执行代码的自进化模块，以及在长时执行中维持信息密度的上下文截断压缩层。在任务完成度、工具使用效率、记忆有效性、自进化能力和网页浏览等维度，GA在显著减少令牌消耗和交互次数的前提下持续领先主流智能体系统，并能随时间不断进化。项目地址：https://github.com/lsdefine/GenericAgent

English

Long-horizon large language model (LLM) agents are fundamentally limited by context. As interactions become longer, tool descriptions, retrieved memories, and raw environmental feedback accumulate and push out the information needed for decision-making. At the same time, useful experience gained from tasks is often lost across episodes. We argue that long-horizon performance is determined not by context length, but by how much decision-relevant information is maintained within a finite context budget. We present GenericAgent (GA), a general-purpose, self-evolving LLM agent system built around a single principle: context information density maximization. GA implements this through four closely connected components: a minimal atomic tool set that keeps the interface simple, a hierarchical on-demand memory that only shows a small high-level view by default, a self-evolution mechanism that turns verified past trajectories into reusable SOPs and executable code, and a context truncation and compression layer that maintains information density during long executions. Across task completion, tool use efficiency, memory effectiveness, self-evolution, and web browsing, GA consistently outperforms leading agent systems while using significantly fewer tokens and interactions, and it continues to evolve over time. Project: https://github.com/lsdefine/GenericAgent

通用智能体：通过上下文信息密度最大化实现令牌高效的自演进大语言模型代理（V1.0版）

GenericAgent: A Token-Efficient Self-Evolving LLM Agent via Contextual Information Density Maximization (V1.0)

摘要

Support