零博士：无需训练数据的自我进化搜索代理

Dr. Zero: Self-Evolving Search Agents without Training Data

January 11, 2026

作者: Zhenrui Yue, Kartikeya Upasani, Xianjun Yang, Suyu Ge, Shaoliang Nie, Yuning Mao, Zhe Liu, Dong Wang

cs.AI

摘要

随着高质量数据日益稀缺，无数据自进化已成为一种前景广阔的研究范式。该方法使大语言模型能够自主生成并解决复杂问题，从而提升其推理能力。然而在多轮搜索智能体中，由于问题多样性受限以及多步推理与工具调用需消耗大量算力，无数据自进化面临挑战。本研究提出Dr. Zero框架，使搜索智能体在无需训练数据的情况下实现高效自进化。我们设计了自进化反馈循环机制：提议者生成多样化问题来训练基于同源基础模型的求解器，随着求解器能力提升，会激励提议者生成难度递增且可解的任务，从而形成双向精进的自动化课程。为提升训练效率，我们提出跳步分组相对策略优化（HRPO），通过聚类结构相似问题构建组级基线，有效降低评估单个查询难度与可解性时的采样开销。HRPO在不影响性能稳定性的前提下，显著减少了求解器训练的算力需求。大量实验表明，无数据训练的Dr. Zero在性能上媲美甚至超越全监督搜索智能体，证实复杂推理与搜索能力可仅通过自进化机制涌现。

English

As high-quality data becomes increasingly difficult to obtain, data-free self-evolution has emerged as a promising paradigm. This approach allows large language models (LLMs) to autonomously generate and solve complex problems, thereby improving their reasoning capabilities. However, multi-turn search agents struggle in data-free self-evolution due to the limited question diversity and the substantial compute required for multi-step reasoning and tool using. In this work, we introduce Dr. Zero, a framework enabling search agents to effectively self-evolve without any training data. In particular, we design a self-evolution feedback loop where a proposer generates diverse questions to train a solver initialized from the same base model. As the solver evolves, it incentivizes the proposer to produce increasingly difficult yet solvable tasks, thus establishing an automated curriculum to refine both agents. To enhance training efficiency, we also introduce hop-grouped relative policy optimization (HRPO). This method clusters structurally similar questions to construct group-level baselines, effectively minimizing the sampling overhead in evaluating each query's individual difficulty and solvability. Consequently, HRPO significantly reduces the compute requirements for solver training without compromising performance or stability. Extensive experiment results demonstrate that the data-free Dr. Zero matches or surpasses fully supervised search agents, proving that complex reasoning and search capabilities can emerge solely through self-evolution.