Papers by Shenglong Yao

Copied to clipboard

Challenge:	Existing methods for supervised fine-tuning (SFT) are suboptimal to preserve task-specific capabilities on RL-trained agentic models.
Approach:	They propose a distribution-aware merging framework specifically designed for RL-trained agentic models that disentangles shared and task-specific unique parameter updates while selectively preserving and rescaling unique ones.
Outcome:	Experiments across multiple agent domains and model architectures show that the proposed framework surpasses baselines and unlocks synergistic potential among agents.