AgentFrontier: Expanding the Capability Frontier of LLM Agents with ZPD-Guided Data Synthesis
This work addresses the challenge of advancing LLM agent reasoning capabilities, offering a scalable method for data synthesis, though it appears incremental as it builds on existing educational theory and data synthesis techniques.
The authors tackled the problem of training LLM agents on tasks at the frontier of their capabilities by introducing a ZPD-guided data synthesis approach, resulting in the AgentFrontier-30B-A3B model achieving state-of-the-art results on benchmarks like Humanity's Last Exam and surpassing some proprietary agents.
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.