Know What You Don't Know: Agentic Data Synthesis by Evolving Generation Space for Closed-Loop Learning

查看原文 / View Original 编辑 / Edit

Computer Science > Artificial Intelligence arXiv:2610.12593 (cs) [Submitted on 8 Oct 2026] Title:Know What You Don’t Know: Agentic Data Synthesis by Evolving Generation Space for Closed-Loop Learning Authors:Wei Yang, Qing Ping, Youzhi Luo, Yawei Wang, Abhishek Kumar, Panpan Xu, Jun Huan

计算机科学 > 人工智能 arXiv:2610.12593 (cs) [提交于 2026 年 10 月 8 日] 标题：了解你的未知：通过演化生成空间进行闭环学习的代理数据合成作者：Wei Yang, Qing Ping, Youzhi Luo, Yawei Wang, Abhishek Kumar, Panpan Xu, Jun Huan

Abstract: The continued improvement of large language models increasingly depends on synthetic experience, yet effective data synthesis for interactive agents requires not only executable and verifiable trajectories, but also interactions that provide learning value for the current task agent. Existing methods increasingly incorporate environment feedback, data validation, or learner failures, but still face a feedback-to-decision gap: observed weaknesses do not directly specify how future synthesis should change, or whether they can be represented by the current synthesis space.

摘要：大型语言模型的持续改进日益依赖于合成经验，然而，针对交互式代理的有效数据合成不仅需要可执行且可验证的轨迹，还需要能够为当前任务代理提供学习价值的交互。现有方法越来越多地结合了环境反馈、数据验证或学习者失败案例，但仍面临从反馈到决策的鸿沟：观察到的弱点并不能直接说明未来的合成应如何改变，或者它们是否能被当前的合成空间所表示。

To address this gap, we propose EvoSyn, a learning-feedback-driven multi-agent framework that organizes synthesis around a revisable state specifying what interaction factors can be deliberately generated and where synthesis effort should be allocated. A role-specialized multi-agent system translates learner feedback into synthesis revisions, while a Designer allocates synthesis directions and a Planner grounds them into executable experience.

为了解决这一鸿沟，我们提出了 EvoSyn，这是一个由学习反馈驱动的多代理框架。该框架围绕一个可修订的状态来组织合成，该状态明确了哪些交互因素可以被刻意生成，以及合成工作应分配到何处。一个角色专业化的多代理系统将学习者的反馈转化为合成修订，同时由“设计者”（Designer）分配合成方向，并由“规划者”（Planner）将其落实为可执行的经验。

This process enables within-space adaptation toward weak or under-covered regions and synthesis-space expansion that promotes newly discovered factors into explicit generation controls. Experiments on $\tau^2$-Bench and CAR-Bench show that EvoSyn improves average task success by 13.3 points over the strongest synthesis baseline, while producing higher-quality and structurally broader synthetic experience and discovering controllable factors missed without learner feedback.

这一过程实现了在空间内针对薄弱或覆盖不足区域的适应，以及合成空间的扩展，从而将新发现的因素提升为明确的生成控制项。在 $\tau^2$-Bench 和 CAR-Bench 上的实验表明，EvoSyn 将平均任务成功率比最强的合成基准提高了 13.3 个百分点，同时产生了更高质量和结构更广泛的合成经验，并发现了在没有学习者反馈时会被遗漏的可控因素。