{"ID":2887757,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2508.00271","arxiv_id":"2508.00271","title":"MetaAgent: Toward Self-Evolving Agent via Tool Meta-Learning","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.","short_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 knowledg...","url_abs":"https://arxiv.org/abs/2508.00271","url_pdf":"https://arxiv.org/pdf/2508.00271v2","authors":"[\"Hongjin Qian\",\"Zheng Liu\"]","published":"2025-08-01T02:30:32Z","proceeding":"cs.AI","tasks":"[\"cs.AI\",\"cs.CL\",\"cs.IR\"]","methods":"[\"Generative Adversarial Network\"]","has_code":false,"code_links":[{"ID":611464,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_id":2887757,"paper_url":"https://arxiv.org/abs/2508.00271","paper_title":"MetaAgent: Toward Self-Evolving Agent via Tool Meta-Learning","repo_url":"https://github.com/qhjqhj00/MetaAgent","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}