让大模型自动进化：能自创工具、持续优化能力。
Towards AGI A Pragmatic Approach Towards Self Evolving Agent
- 分层多智能体架构，支持任务失败后自动生成工具和进化。
- 课程学习快速恢复，强化学习攻克高难任务，遗传算法提升行为多样性。
- 在复杂任务数据集上表现超越原始模型，适合长期自主系统研发。
基于大语言模型（LLM）的智能体在部署后本质上是静态的，缺乏自主扩展能力、生成新工具或进化推理机制的能力。本文提出一种分层自演化多智能体框架，整合基础LLM、操作型SLM智能体、代码生成LLM与教师型LLM，实现持续适应。流程为：智能体先用现有工具和推理尝试任务；若失败，则通过代码生成LLM进行工具合成；持续失败时，触发基于课程学习（CL）、基于奖励的学习（RL）或遗传算法（GA）的演化阶段。在包含层次化任务、工具使用轨迹与难度分级的TaskCraft数据集上评估发现：CL实现快速恢复与强泛化能力，RL在高难度任务中表现最优，GA则带来高行为多样性。所有场景下，演化后的智能体均优于原始版本，证明了其鲁棒、自主、持续进化的智能体演化能力。
原文摘要 · Abstract (English)
Large Language Model (LLM) based agents are powerful yet fundamentally static after deployment, lacking the ability to autonomously expand capabilities, generate new tools, or evolve their reasoning. This work introduces a hierarchical self-evolving multi-agent framework that integrates a Base LLM, an operational SLM agent, a Code-Generation LLM, and a Teacher-LLM to enable continuous adaptation. The workflow begins with the agent attempting a task using reasoning and existing tools; if unsuccessful, it escalates to tool synthesis through the Code-Gen LLM, and when failures persist, it triggers an evolution phase using Curriculum Learning (CL), Reward-Based Learning (RL), or Genetic Algorithm (GA) evolution. Using the TaskCraft dataset rich in hierarchical tasks, tool-use traces, and difficulty scaling we evaluate these paradigms. CL delivers fast recovery and strong generalization, RL excels on high-difficulty tasks, and GA offers high behavioral diversity. Across all settings, evolved agents outperform their originals, demonstrating robust, autonomous, self-improving agentic evolution.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。