AgentFrontier: Expanding the Capability Frontier of LLM Agents with ZPD-Guided Data Synthesis

TL;DR

This paper introduces a ZPD-guided data synthesis method for training large language model agents, enabling them to master complex tasks and achieve state-of-the-art performance on challenging benchmarks.

Contribution

It presents the AgentFrontier Engine for automated, ZPD-aligned data synthesis and introduces the ZPD Exam benchmark for evaluating frontier capabilities.

Findings

Achieved state-of-the-art results on Humanity's Last Exam.

Synthesized high-quality, multidisciplinary data within the LLM's ZPD.

Surpassed some proprietary agents on complex reasoning benchmarks.

Abstract

Training large language model agents on tasks at the frontier of their capabilities is key to unlocking advanced reasoning. We introduce a data synthesis approach inspired by the educational theory of the Zone of Proximal Development (ZPD), which defines this frontier as tasks an LLM cannot solve alone but can master with guidance. To operationalize this, we present the AgentFrontier Engine, an automated pipeline that synthesizes high-quality, multidisciplinary data situated precisely within the LLM's ZPD. This engine supports both continued pre-training with knowledge-intensive data and targeted post-training on complex reasoning tasks. From the same framework, we derive the ZPD Exam, a dynamic and automated benchmark designed to evaluate agent capabilities on these frontier tasks. We train AgentFrontier-30B-A3B model on our synthesized data, which achieves state-of-the-art results on demanding benchmarks like Humanity's Last Exam, even surpassing some leading proprietary agents. Our work demonstrates that a ZPD-guided approach to data synthesis offers a scalable and effective path toward building more capable LLM agents.