Agentevolver: Towards Efficient Self-evolving Agent System

Abstract

Autonomous agents powered by large language models (LLMs) have the potential to significantly enhance human productivity by reasoning, using tools, and executing complex tasks in diverse environments. However, current approaches to developing such agents remain costly and inefficient, as they typically require manually constructed task datasets and reinforcement learning (RL) pipelines with extensive random exploration. These limitations lead to prohibitively high data-construction costs, low exploration efficiency, and poor sample utilization. To address these challenges, we present AgentEvolver, a self-evolving agent system that leverages the semantic understanding and reasoning capabilities of LLMs to drive autonomous agent learning. AgentEvolver introduces three synergistic mechanisms: (i) self-questioning, which enables curiosity-driven task generation in novel environments, reducing dependence on handcrafted datasets; (ii) self-navigating, which improves exploration efficiency th

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyzhai2025agentevolver

Related papers

• Agent-pro: Learning To Evolve Via Policy-level Reflection And Optimization (2024)9.59
• Comas: Co-evolving Multi-agent Systems Via Interaction Rewards (2025)0.00
• Towards Agentic Self-learning Llms In Search Environment (2025)0.00
• Proagent: Building Proactive Cooperative Agents With Large Language Models (2023)12.74
• Discovering Multiagent Learning Algorithms With Large Language Models (2026)2.05
• Training Agents With Weakly Supervised Feedback From Large Language Models (2024)0.00
• From Laws To Motivation: Guiding Exploration Through Law-based Reasoning And Rewards (2024)0.00
• Llm-explorer: A Plug-in Reinforcement Learning Policy Exploration Enhancement Driven By Large Language Models (2025)0.00