# Agent0: Unleashing Self-Evolving Agents from Zero Data via Tool-Integrated Reasoning

Source: [Agent0: Unleashing Self-Evolving Agents from Zero Data via Tool-Integrated Reasoning](<https://www.sota2.com/research/paper/691ff234d6b0dd334292e82b>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-11-24T06:00:00.789Z

Authors: Peng Xia, Kaide Zeng, Jiaqi Liu, Can Qin, Fang Wu, Yiyang Zhou, Caiming Xiong, Huaxiu Yao

Published: 2025-11-20T05:01:57.000Z

## 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.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Code Generation on Code Benchmarks LCBv6 & MBPP+](<https://www.sota2.com/research/sota/code-generation-on-code-benchmarks-lcbv6-and-mbpp-plus.md>): Code Generation; Code Benchmarks LCBv6 & MBPP+; LCBv6 Score: 32.

- [Mathematical Reasoning on AIME 2024, AIME 2025, and OlympiadBench](<https://www.sota2.com/research/sota/mathematical-reasoning-on-aime-2024-aime-2025-and-olympiadbench.md>): Mathematical Reasoning; Math Benchmarks AIME 2024 AIME 2025 OlympiadBench; AIME 2024 Score: 13.1.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2511.16043>)

[PDF](<https://arxiv.org/pdf/2511.16043.pdf>)

[Implementation](<https://github.com/aiming-lab/Agent0>)