@inproceedings{yang-etal-2026-agentic,
    title = "Agentic Episodic Control",
    author = "Yang, Xidong  and
      Li, Wenhao  and
      Sheng, Junjie  and
      Hua, Yun  and
      Chen, Haosheng  and
      Shen, Chuyun  and
      Wang, Xiangfeng",
    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.654/",
    pages = "13355--13370",
    ISBN = "979-8-89176-395-1",
    abstract = "Reinforcement learning (RL) remains fundamentally limited by poor data efficiency and weak generalization. Prior episodic RL methods attempt to alleviate this via external memory modules, yet they suffer from two key limitations: a representation bottleneck caused by shallow encoders, and a retrieval dilemma where episodic memory is accessed indiscriminately.To address these challenges, we propose Agentic Episodic Control (AEC), a novel architecture that integrates large language models (LLMs) into episodic RL.AEC uses an LLM-based semantic augmenter to generate semantic representations from raw observations, and a critical state recognizer to selectively retrieve valuable experiences.This transforms memory usage from passive similarity matching into strategic, context-aware recall.Across five BabyAI-Text environments, AEC achieves 2{--}6{\texttimes} higher data efficiency than baselines and is the only method to solve complex tasks like UnlockLocal with over 90{\%} success.It further demonstrates strong cross-task and cross-environment generalization, maintaining performance even under distribution shifts.AEC shows that combining LLM-derived priors with reinforcement learning yields more sample-efficient and adaptable agents. Code is available at https://github.com/Xidong-Yang/Agentic{\_}Episodic{\_}Control."
}