arXiv 2609.32259 · cs.AI · 2026-09-26
Prefill-Free Cross-Family KV Cache Transfer for Heterogeneous Multi-Agent LLMs
Vincent-Daniel Yun, Woosang Lim, Haneul Yoo, Sungjoo Yoo, Murali Annavaram, Sai Praneeth Karimireddy
University of Southern California
在最新榜 #182 本站收录于 2026-10-21
一句话要点
HeteroFold 让不同家族的大模型之间直接传递 KV 缓存，多智能体协作时免去重复预填充。
HeteroFold transfers KV caches across different model families, avoiding repeated prefill in heterogeneous multi-agent systems.
阅读 arXiv 原文 PDF Hugging Face 讨论 代码仓库 项目页
主题与学科
同主题：高效训练与推理
- The Teacher Is a Direction, Not a Destination: Extrapolating RL-Induced Representation Residuals in On-Policy Distillation ▲511
- Scaling Properties of Same-Family On-Policy Distillation ▲327
- Beyond Domain-Routed Supervision: Cross-Teacher Guarding for Multi-Teacher On-Policy Distillation ▲251
- On-Policy or Off-Policy Learning? A Systematic Study of Distillation Dynamics ▲205
- Beyond Teacher Assignment: Domain-Normalized Multi-Teacher On-Policy Distillation ▲181
数据说明
元数据来自 arXiv API（已核实）；点赞来自 Hugging Face 每日论文；引用来自 Semantic Scholar。最近刷新 2026-10-22。
要点由本站根据摘要自写，不转载摘要原文，请阅读原文。