Exploratory and Assimilating Reflection: Reflective Recall Cycle for Long-term Memory
2026-07-20 • Artificial Intelligence
Artificial Intelligence
AI summaryⓘ
The authors address a problem where AI agents need to remember information over long conversations but struggle because they can't store everything at once. They developed a method called EAR that helps the AI search for useful memories and then learn from those experiences to get better at finding important information. Their experiments show EAR improves memory retrieval and works well even with little training and noisy data. This approach makes the agents smarter in managing and using their memories during long interactions.
LLM-based autonomous agentsexternal memorycontext windowmemory retrievalsample efficiencyiterative searchexperience replayrerankerlong-term dialoguenoisy feedback
Authors
Ganesh Senrayan, Moyuru Yamada, Ishan Jindal, Kiran Purohit
Abstract
LLM-based autonomous agents require external memory to overcome their statelessness and limited context window for long-term interaction and dynamic knowledge reasoning. However, existing memory retrieval methods often lack adaptability and sample efficiency, and struggle to retrieve the right mixture of memories from heterogeneous stores. We propose Exploratory-Assimilating Reflection (EAR), a framework for high initial retrieval performance and sample-efficient adaptation. EAR combines two mechanisms: Exploratory Reflection, which performs iterative search to bootstrap retrieval and collect useful experiences for each query, and Assimilating Reflection, which replays these experiences from an Experience Buffer to refine a global reranker more efficiently than methods relying only on immediate rewards. Experiments show that EAR improves retrieval by up to 17.9% over the baseline retriever on two long-term dialogue benchmarks. We also show that EAR is highly sample-efficient and robust to noisy feedback.