aiqbench analysis
Agent0 introduces a novel self-evolution framework that eliminates the need for human-curated data by pitting a curriculum agent against an executor agent in a symbiotic competition. This approach successfully enhances tool integration and dynamic reasoning capabilities, demonstrating significant performance gains on mathematical and general benchmarks without external training sets. The method represents a critical step toward scalable, autonomous AI development that breaks dependency on static datasets.
Agent0: Unleashing Self-Evolving Agents from Zero Data via Tool-Integrated Reasoning
arXiv:2511.16043v2 Announce Type: replace 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.
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 this https URL.
Machine Learning (cs.LG)
arXiv:2511.16043 [cs.LG]
(or arXiv:2511.16043v2 [cs.LG] for this version)
https://doi.org/10.48550/arXiv.2511.16043 Focus to learn more arXiv-issued DOI via DataCite
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Full text under the publisher's open licence · 268 words
Related coverage
Microsoft’s AI chief says superintelligence is near, but won’t take your job
The Verge · Jun 8, 2026
RoboFoundry: System-as-Policy Evolution for Self-Learning Embodied Agents
arXiv · Sep 29, 2026
Dr. Zero: Self-Evolving Search Agents without Training Data
arXiv · Jul 23, 2026
Presentation: Exploding GPUs
InfoQ · Oct 16, 2026