Wenhang Shi
2 indexed papers
Publications per year
Top categories
Frequent co-authors
Research Timeline
The paper introduces Grounded Agentic Interaction Synthesis (GAIS), a framework that generates high-quality, diverse, and complex agentic training data by anchoring tasks to real-world protocols, significantly improving base model performance.
The paper introduces State-Adaptive Prompt Optimization (SAPO), a novel training strategy that treats prompts as dynamic variables to achieve robust fine-tuning, significantly mitigating catastrophic forgetting and improving generalization in LLMs.
Papers
Scaling Agentic Capabilities via Grounded Interaction Synthesis
Wenhang Shi, Jinhao Dong, Yiren Chen, Zhe Zhao +3 more
The paper introduces Grounded Agentic Interaction Synthesis (GAIS), a framework that generates high-quality, diverse, and complex agentic training data by anchoring tasks to real-world protocols, sign…