works on
multi-hop QA 1reinforcement learning 1self-distillation 1verifiable environment 1web search agents 1

From the 1 of 2 linked papers with an AI index.

collaborators
Showing cs.AIShow all

1 paper · 1 filter

cs.AI2026

Rethinking Heterogeneous LLM Merging: A Weighted Model Averaging Perspective

Jiahe Fan, Yinghao Hou, Si Chen +3

Can large language models with substantially different parameter spaces be merged by direct weighted averaging, without training or semantic alignment? Existing heterogeneous fusio…