TeleMem: Building Long-Term and Multimodal Memory for Agentic AI
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866909997461405696 |
|---|---|
| author | Chen, Chunliang Guan, Ming Lin, Xiao Li, Jiaxu Lin, Luxi Wang, Qiyi Chen, Xiangyu Luo, Jixiang Sun, Changzhi Zhang, Dell Li, Xuelong |
| author_facet | Chen, Chunliang Guan, Ming Lin, Xiao Li, Jiaxu Lin, Luxi Wang, Qiyi Chen, Xiangyu Luo, Jixiang Sun, Changzhi Zhang, Dell Li, Xuelong |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_06037 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | TeleMem: Building Long-Term and Multimodal Memory for Agentic AI Chen, Chunliang Guan, Ming Lin, Xiao Li, Jiaxu Lin, Luxi Wang, Qiyi Chen, Xiangyu Luo, Jixiang Sun, Changzhi Zhang, Dell Li, Xuelong Computation and Language Artificial Intelligence Computer Vision and Pattern Recognition 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. |
| title | TeleMem: Building Long-Term and Multimodal Memory for Agentic AI |
| topic | Computation and Language Artificial Intelligence Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2601.06037 |