MetaAgent: Toward Self-Evolving Agent via Tool Meta-Learning

TL;DR

MetaAgent is a self-evolving agentic system that improves its reasoning and tool use through continual self-reflection, help-seeking, and tool-building, enabling robust knowledge discovery without additional training.

Contribution

It introduces meta tool learning, a data-driven process allowing agents to self-improve and adapt by generating help requests, building tools, and updating knowledge bases without parameter changes.

Findings

Outperforms workflow-based baselines on benchmarks.

Matches or exceeds end-to-end trained agents.

Demonstrates effective self-evolution in knowledge discovery.

Abstract

In this work, we propose MetaAgent, an agentic paradigm inspired by the principle of learning-by-doing, where expertise is developed through hands-on practice and continual self-improvement. MetaAgent starts with a minimal workflow, equipped only with basic reasoning and adaptive help-seeking abilities. When a knowledge gap is encountered, MetaAgent generates natural language help requests, which are routed to the most suitable external tool by a dedicated tool router. As MetaAgent solves tasks, it continually conducts self-reflection and answer verification, distilling actionable experience into concise texts that are dynamically incorporated into future task contexts. Besides, MetaAgent autonomously builds in-house tools and a persistent knowledge base by organizing its tool-use history, further enhancing its ability to retrieve and integrate relevant information We term this continual, data-driven process as \textit{meta tool learning}, through which MetaAgent incrementally refines its reasoning and tool-use strategies, without changing model parameters or requiring further post-training. Evaluated on challenging knowledge discovery benchmarks, including GAIA, WebWalkerQA, and BrowseCamp, MetaAgent consistently outperforms workflow-based baselines and matches or exceeds end-to-end trained agents, demonstrating the promise of self-evolving agentic systems for robust, general-purpose knowledge discovery. We provide our source codes in https://github.com/qhjqhj00/MetaAgent.