arXiv 2609.26780 · cs.CL · 2026-09-22
SpeakerMem-R1: Speaker-Centered Dual-Track Memory for Multi-Party Dialogue
Haobo Zheng, Tan Tang, Yan Chen, Weijie Wang, Yingcai Wu
Zhejiang University
在最新榜 #79 2026-W39 第 9 名 本站收录于 2026-10-21
一句话要点
SpeakerMem-R1 以说话人为中心构建双轨记忆，解决多人对话中“谁说了什么”的记忆难题。
SpeakerMem-R1 builds speaker-centred dual-track memory for multi-party dialogue, tracking who said what about whom.
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：智能体
- Raven: The Harness of Harnesses for Composable Agentic Intelligence ▲748
- False Frontiers: Diagnosing and Mitigating Co-Cheating in Self-Evolving Search Agents ▲642
- BizAgentBench: Unveiling Hidden Challenges in Deploying Long-Horizon Agents for Real-World Business ▲492
- Omni-IO Skills: Harnessing Your Agent Omni-Native ▲485
- Player-1: Learning to Play from Synthetic Experience ▲347
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 2026-10-23。
要点由本站根据摘要自写，不转载摘要原文，请阅读原文。