GRADS: Graph-Regulated Agentic Data Synthesis with Controllable Difficulty

GRADS is a graph-guided framework for generating synthetic data that explicitly controls difficulty by maintaining a graph of evidence and inference dependencies. It iteratively selects seeds, expands evidence, constructs question–answer pairs, and verifies them, ensuring that each generated task contains only indispensable inference steps. Experiments across security, software engineering, and scientific domains show that GRADS produces verified tasks with distinct difficulty levels, and training models on this data yields significant performance gains, including high solution-termination rates and reduced tool usage.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

• agents
• reinforcement-learning
• fine-tuning
• benchmarks