PulseAugur
LIVE 04:15:59
research · [7 sources] ·
0
research

AdaMem: Adaptive User-Centric Memory for Long-Horizon Dialogue Agents

By PulseAugur Editorial · Summary by None from 7 sources

Multiple research papers released on arXiv propose novel frameworks for enhancing the memory capabilities of Large Language Model (LLM) agents. These approaches aim to overcome limitations in handling long-term conversations and personalized interactions. Innovations include adaptive graph intelligence for memory organization and retrieval, structured anchoring of conversational data, and embedding-based routing for efficient memory management. The proposed systems, such as MemORAI, GRAVITY, MemRouter, TiMem, and AdaMem, demonstrate state-of-the-art performance on benchmarks like LoCoMo and LongMemEval, improving coherence, personalization, and reasoning. AI

Summary written by None from 7 sources. How we write summaries →

IMPACT These advancements in LLM memory management could lead to more coherent and personalized conversational agents capable of sustained, long-horizon interactions.

RANK_REASON Multiple academic papers published on arXiv introducing new frameworks for LLM memory management.

Read on arXiv cs.CL →

COVERAGE [7]

  1. arXiv cs.CL TIER_1 · Hung Pham Van, Nguyen Manh Hieu, Khang Pham Tran Tuan, Nam Le Hai, Linh Ngo Van, Nguyen Thi Ngoc Diep, Trung Le ·

    MemORAI: Memory Organization and Retrieval via Adaptive Graph Intelligence for LLM Conversational Agents

    arXiv:2605.01386v1 Announce Type: new Abstract: Large Language Models (LLMs) lack persistent memory for long-term personalized conversations. Existing graph-based memory systems suffer from information dilution, absent provenance tracking, and uniform retrieval that ignores query…

  2. arXiv cs.CL TIER_1 · Yushi Sun, Bowen Cao, Dong Fang, Lingfeng Su, Wai Lam ·

    GRAVITY: Architecture-Agnostic Structured Anchoring for Long-Horizon Conversational Memory

    arXiv:2605.01688v1 Announce Type: new Abstract: Long-horizon conversational agents rely on memory systems with increasingly sophisticated retrieval mechanisms. However, retrieved fragments are typically fed to the language model as unstructured text, lacking the relational, tempo…

  3. arXiv cs.CL TIER_1 · Tianyu Hu, Weikai Lin, Weizhi Zhang, Jing Ma, Song Wang ·

    MemRouter: Memory-as-Embedding Routing for Long-Term Conversational Agents

    arXiv:2605.00356v1 Announce Type: new Abstract: Long-term conversational agents must decide which turns to store in external memory, yet recent systems rely on autoregressive LLM generation at every turn to make that decision. We present MemRouter, a write-side memory router that…

  4. arXiv cs.AI TIER_1 · Kai Li, Xuanqing Yu, Ziyi Ni, Yi Zeng, Yao Xu, Zheqing Zhang, Xin Li, Jitao Sang, Xiaogang Duan, Xuelei Wang, Chengbao Liu, Jie Tan ·

    TiMem: Temporal-Hierarchical Memory Consolidation for Long-Horizon Conversational Agents

    arXiv:2601.02845v2 Announce Type: replace-cross Abstract: Long-horizon conversational agents have to manage ever-growing interaction histories that quickly exceed the finite context windows of large language models (LLMs). Existing memory frameworks provide limited support for te…

  5. arXiv cs.CL TIER_1 · Yi Yu, Liuyi Yao, Yuexiang Xie, Qingquan Tan, Jiaqi Feng, Yaliang Li, Libing Wu ·

    Agentic Memory: Learning Unified Long-Term and Short-Term Memory Management for Large Language Model Agents

    arXiv:2601.01885v2 Announce Type: replace Abstract: Large language model (LLM) agents face fundamental limitations in long-horizon reasoning due to finite context windows, making effective memory management critical. Existing methods typically handle long-term memory (LTM) and sh…

  6. arXiv cs.CL TIER_1 · Song Wang ·

    MemRouter: Memory-as-Embedding Routing for Long-Term Conversational Agents

    Long-term conversational agents must decide which turns to store in external memory, yet recent systems rely on autoregressive LLM generation at every turn to make that decision. We present MemRouter, a write-side memory router that decouples memory admission from the downstream …

  7. arXiv cs.CL TIER_1 · Shannan Yan, Jingchen Ni, Leqi Zheng, Jiajun Zhang, Peixi Wu, Dacheng Yin, Jing Lyu, Chun Yuan, Fengyun Rao ·

    AdaMem: Adaptive User-Centric Memory for Long-Horizon Dialogue Agents

    arXiv:2603.16496v2 Announce Type: replace Abstract: Large language model (LLM) agents increasingly rely on external memory to support long-horizon interaction, personalized assistance, and multi-step reasoning. However, existing memory systems still face three core challenges: th…

RELATED ENTITIES

RELATED TOPICS