@inproceedings{chen-etal-2026-dynamic,
    title = "Dynamic Long Context Reasoning over Compressed Memory via End-to-End Reinforcement Learning",
    author = "Chen, Zhuoen  and
      Li, Dongfang  and
      Zhang, Meishan  and
      Hu, Baotian  and
      Zhang, Min",
    editor = "Liakata, Maria  and
      Moreira, Viviane P.  and
      Zhang, Jiajun  and
      Jurgens, David",
    booktitle = "Proceedings of the 64th Annual Meeting of the {A}ssociation for {C}omputational {L}inguistics (Volume 1: Long Papers)",
    month = jul,
    year = "2026",
    address = "San Diego, California, United States",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl/2026.acl-long.365/",
    pages = "8064--8083",
    ISBN = "979-8-89176-390-6",
    abstract = "Large Language Models (LLMs) face severe challenges in long-context processing, including quadratic computational costs, information forgetting, and the context fragmentation inherent in Retrieval-Augmented Generation (RAG). We introduce LycheeMemory, a cognitively inspired framework that enables efficient long-context inference via chunk-wise compression and selective memory recall, rather than processing all raw tokens. LycheeMemory segments the input into chunks and encodes each into compressed KV-cache style representations using a Compressor. A Gate then dynamically selects relevant memory blocks, which a Reasoner iteratively processes with an evolving working memory to solve downstream tasks. The Compressor and Reasoner are jointly optimized via end-to-end reinforcement learning, while the Gate is trained separately as a classifier. Experimental results demonstrate that LycheeMemory achieves competitive accuracy (up to 82{\%} in ablation variants) on multi-hop reasoning benchmarks (e.g., RULER-HQA), successfully extrapolates context length from 7K to 1.75M, and provides a favorable accuracy{--}efficiency trade-off against strong long-context baselines. Notably, compared to MemAgent, LycheeMemory achieves an average 2{\texttimes} reduction in peak GPU memory usage and a 6{\texttimes} speedup during inference."
}