TeleMem: 构建面向代理AI的长期和多模态记忆
TeleMem: Building Long-Term and Multimodal Memory for Agentic AI
AI总结：
TeleMem通过统一的长期和多模态记忆系统，提升代理AI在长对话和多模态任务中的表现，实现更高的准确率、更低的令牌使用和更快的操作速度。
摘要：
大型语言模型（LLMs）在许多NLP任务中表现出色，但因在长对话历史中注意力有限而难以维持长期交互。检索增强生成（RAG）缓解了这一问题，但缺乏可靠的机制来更新或完善存储的记忆，导致基于模式的幻觉、低效的写入操作以及对多模态推理的最小支持。为了解决这些挑战，我们提出了TeleMem，一个统一的长期和多模态记忆系统，通过叙述动态提取保持连贯的用户资料，确保只保留基于对话的信息。TeleMem进一步引入了结构化的写作流程，将、检索、聚类和整合记忆条目，显著提高了存储效率，减少了令牌使用，并加速了记忆操作。此外，结合ReAct风格推理的多模态记忆模块使系统具备闭环的观察、思考和行动过程，能够准确理解长期内复杂视频内容。实验结果表明，TeleMem在ZH-4O长期角色扮演游戏基准测试中，比最先进的Mem0基线提高了19%的准确率，减少了43%的令牌使用，并实现了2.1倍的速度提升。
英文摘要：
Large language models (LLMs) excel at many NLP tasks but struggle to sustain long-term interactions due to limited attention over extended dialogue histories. Retrieval-augmented generation (RAG) mitigates this issue but lacks reliable mechanisms for updating or refining stored memories, leading to schema-driven hallucinations, inefficient write operations, and minimal support for multimodal reasoning.To address these challenges, we propose TeleMem, a unified long-term and multimodal memory system that maintains coherent user profiles through narrative dynamic extraction, ensuring that only dialogue-grounded information is preserved. TeleMem further introduces a structured writing pipeline that batches, retrieves, clusters, and consolidates memory entries, substantially improving storage efficiency, reducing token usage, and accelerating memory operations. Additionally, a multimodal memory module combined with ReAct-style reasoning equips the system with a closed-loop observe, think, and act process that enables accurate understanding of complex video content in long-term contexts. Experimental results show that TeleMem surpasses the state-of-the-art Mem0 baseline with 19% higher accuracy, 43% fewer tokens, and a 2.1x speedup on the ZH-4O long-term role-play gaming benchmark.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
