@inproceedings{hu-etal-2026-querylink,
    title = "{Q}uery{L}ink: Leveraging Query-Memory Alignment for Long-Term Reasoning in {LLM} Agents",
    author = "Hu, Xuxian  and
      Teng, Zhu  and
      Zhang, Wei  and
      He, Ming  and
      Fan, Jianping",
    editor = "Liakata, Maria  and
      Moreira, Viviane P.  and
      Zhang, Jiajun  and
      Jurgens, David",
    booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {ACL} 2026",
    month = jul,
    year = "2026",
    address = "San Diego, California, United States",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl/2026.findings-acl.765/",
    pages = "15608--15621",
    ISBN = "979-8-89176-395-1",
    abstract = "Retrieval-Augmented Generation (RAG) systems are widely used to mitigate the stateless nature of Large Language Models (LLMs) in long-term and personalized interactions by incorporating external memory. However, existing approaches often prioritize memory organization, such as knowledge graphs, while overlooking a critical semantic gap between implicit, intent-driven queries and explicit, narrative-based memories. To bridge this gap, we propose QueryLink, a novel framework that leverages Query-Memory Alignment to project both queries and memories into a shared semantic space. It significantly boosts recall by facilitating multi-grained retrieval of semantically relevant information. To further enhance memory retrieval, we leverage Coherent Memory Chunking, a mechanism that processes memories in multi-turn dialogue units, preserving semantic integrity, rather than relying on fixed-size segments. Extensive experiments on the LoCoMo and LongMemEval benchmark demonstrate that QueryLink significantly outperforms SOTA methods, achieving at least a 7{\%} improvement in reasoning accuracy (measured by LLM). Additionally, QueryLink can be integrated as a plug-and-play component to boost existing vector-based systems like A-MEM, leading to improvements of over 6{\%} in both F1 and B1 scores.The code is available at https://github.com/Dontplay0112/querylink."
}