SpeakerMem-R1：面向多人对话的双轨记忆框架
SpeakerMem-R1: Speaker-Centered Dual-Track Memory for Multi-Party Dialogue
多人对话里模型总记不清谁说了什么，这篇给出双轨记忆方案，在 EverMemBench 榜单拿了最好成绩，做记忆系统的可以看看。
论文提出 SpeakerMem-R1，用双轨记忆分别存储带说话人标签的逐字消息和按人物、群组组织的派生状态。模型通过 SpeakerLevenshtein 和说话人条件 GRPO 训练 Writer-R1，降低归属与更新错误。在 GroupMemBench、SocialMemBench、EverMemBench 上二值准确率分别为 47.9%、69.2%、61.9%，其中 EverMemBench 以 62.33% 为公开榜单最好成绩。消融实验显示逐字与结构化两条轨道、人物级与群组级视图互相补充。
SpeakerMem-R1: Speaker-Centered Dual-Track Memory for Multi-Party Dialogue
Long-term conversational memory in multi-party settings requires more than retrieving relevant content from long-term conversations: it must distinguish who said what, whom each statement concerns, how individuals perceive one another, what information is shared by the group, and how states change over time. Recent studies on multi-party dialogue benchmarks show that existing general-purpose LLM memory systems tend to lose person and group relations or struggle to integrate clues distributed across members, groups, and time. Together, these issues reveal two core bottlenecks: message attribution and relational understanding in multi-party dialogue, and state reconstruction from interleaved histories. To address both, we propose $\textbf{SpeakerMem-R1}$: its dual-track memory stores speaker-labeled verbatim messages and derived states organized into person-level and group-level views, then combines evidence from both tracks by entity, event, and time at query time. To reduce attribution and update errors during structured memory construction while enabling local deployment, we train Writer-R1 with SpeakerLevenshtein and speaker-conditioned GRPO. On GroupMemBench, SocialMemBench, and EverMemBench, SpeakerMem-R1 achieves binary accuracies of 47.9%, 69.2%, and 61.9%, respectively. On the publicly reported EverMemBench leaderboard from EverMind-AI, we achieves 62.33%, the best reported result among the latest state-of-the-art frameworks. It also achieves 70.85% on all 1,986 LoCoMo questions, which we use as a two-person long-term conversation boundary test. In a controlled evaluation of 305 questions, RL raises the SFT Writer's mean accuracy from 57.38% to 68.20%. We report both binary accuracy and token-F1, and ablations show that the verbatim and structured tracks, as well as person-level and group-level views, are complementary under the standardized evaluation interface.
