{"ID":2838905,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2511.16043","arxiv_id":"2511.16043","title":"Agent0: Unleashing Self-Evolving Agents from Zero Data via Tool-Integrated Reasoning","abstract":"Large Language Model (LLM) Agents, often trained with Reinforcement Learning (RL), are constrained by a dependency on human-curated data, limiting scalability and tethering AI to human knowledge. Existing self-evolution frameworks offer an alternative but are typically restricted by the model's inherent capabilities and single-round interactions, hindering the development of complex curricula involving tool use or dynamic reasoning. We introduce Agent0, a fully autonomous framework that evolves high-performing agents without external data through multi-step co-evolution and seamless tool integration. Agent0 establishes a symbiotic competition between two agents initialized from the same base LLM: a curriculum agent that proposes increasingly challenging frontier tasks, and an executor agent that learns to solve them. We integrate external tools to enhance the executor's problem-solving capacity; this improvement, in turn, pressures the curriculum agent to construct more complex, tool-aware tasks. Through this iterative process, Agent0 establishes a self-reinforcing cycle that continuously produces high-quality curricula. Empirically, Agent0 substantially boosts reasoning capabilities, improving the Qwen3-8B-Base model by 18% on mathematical reasoning and 24% on general reasoning benchmarks. Code is available at https://github.com/aiming-lab/Agent0.","short_abstract":"Large Language Model (LLM) Agents, often trained with Reinforcement Learning (RL), are constrained by a dependency on human-curated data, limiting scalability and tethering AI to human knowledge. Existing self-evolution frameworks offer an alternative but are typically restricted by the model's inherent capabilities an...","url_abs":"https://arxiv.org/abs/2511.16043","url_pdf":"https://arxiv.org/pdf/2511.16043v1","authors":"[\"Peng Xia\",\"Kaide Zeng\",\"Jiaqi Liu\",\"Can Qin\",\"Fang Wu\",\"Yiyang Zhou\",\"Caiming Xiong\",\"Huaxiu Yao\"]","published":"2025-11-20T05:01:57Z","proceeding":"cs.LG","tasks":"[\"cs.LG\"]","methods":"[\"Reinforcement Learning\",\"Large Language Model\",\"Language Model\"]","has_code":false,"code_links":[{"ID":606816,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_id":2838905,"paper_url":"https://arxiv.org/abs/2511.16043","paper_title":"Agent0: Unleashing Self-Evolving Agents from Zero Data via Tool-Integrated Reasoning","repo_url":"https://github.com/aiming-lab/Agent0","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}