@inproceedings{man-etal-2026-reasoning,
    title = "Reasoning with Memory: Adaptive Information Management for Retrieval-Augmented Generation",
    author = "Man, Hieu  and
      Tal, Ro-ee  and
      Kumar, Abhishek  and
      Cho, Jaejin  and
      Hsu, Benjamin",
    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.1834/",
    pages = "36825--36841",
    ISBN = "979-8-89176-395-1",
    abstract = "Multi-hop reasoning remains a fundamental challenge for Retrieval-Augmented Generation (RAG) systems. Recent approaches{---}from adaptive retrieval to agentic pipelines{---}struggle to maintain coherent intermediate reasoning states as chains grow longer. We introduce State-Aware RAG, a framework that addresses this limitation through an explicit working memory that serves as a dynamic cognitive workspace for reasoning. Our modular architecture features a lightweight, trainable extractor that learns to actively filter, consolidate, and update this working memory via a novel Path-Outcome Dual Reward paradigm, which balances local coherence with global strategy. The retriever and generator remain frozen, enabling plug-and-play flexibility. Experiments on eight QA benchmarks demonstrate state-of-the-art results, on average achieving +8.6{\%} over the best memory-augmented baseline and +9.3{\%} over the best RL-enhanced baseline. Our architecture generalizes seamlessly to stronger generators and retrievers without retraining, establishing dynamic memory management as a critical yet underexplored dimension for advancing RAG systems."
}