AgentFrontier: Expanding the Capability Frontier of LLM Agents with ZPD-Guided Data Synthesis
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917048235327488 |
|---|---|
| author | Chen, Xuanzhong Qiao, Zile Chen, Guoxin Su, Liangcai Zhang, Zhen Wang, Xinyu Xie, Pengjun Huang, Fei Zhou, Jingren Jiang, Yong |
| author_facet | Chen, Xuanzhong Qiao, Zile Chen, Guoxin Su, Liangcai Zhang, Zhen Wang, Xinyu Xie, Pengjun Huang, Fei Zhou, Jingren Jiang, Yong |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_24695 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | AgentFrontier: Expanding the Capability Frontier of LLM Agents with ZPD-Guided Data Synthesis Chen, Xuanzhong Qiao, Zile Chen, Guoxin Su, Liangcai Zhang, Zhen Wang, Xinyu Xie, Pengjun Huang, Fei Zhou, Jingren Jiang, Yong Computation and Language 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. |
| title | AgentFrontier: Expanding the Capability Frontier of LLM Agents with ZPD-Guided Data Synthesis |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2510.24695 |