Showing cs.CLShow all
2 papers · 1 filter
cs.CL2026
Share the Symbol, Not the Vector: Training-Free Fact Communication Across Language Models
Xin Li, Mengbing Liu, Hao Jiang +5
Multi-agent systems allow language models to solve tasks collaboratively by sharing complementary information. These systems typically communicate through text, while recent approa…
cs.CL2026
Recall Before You Rank: Similarity-Guided Top- Reuse for Efficient Long-Context Attention
Wenshuai Yao, Wenyong Zhou, Hanyong Shao +5
Top- sparse attention reduces the cost of Softmax and value aggregation by attending to only a small subset of key--value (KV) entries. However, identifying this subset still re…