← Search

Cassandra Hui-Ming Tan

2 accepted papers

2026

ARTEM: Enhancing Large Language Model Agents with Spatial-Temporal Episodic Memory

AAAI 2026technical

Current large language models (LLMs) exhibit significant deficiencies in episodic memory tasks including encoding, storing, and retrieving specific information from temporally dependent events over a long period of time. Recent approaches to handle memory tasks in LLMs, such as in-context learning,

Cited by 0SourcePDFScholar
2026

Value-Driven Memory-Augmented Generation for Agentic LLMs: Towards Structured and Adaptive Knowledge Utilization

AAAI 2026technical

Large Language Models (LLMs) have demonstrated remarkable capabilities in reasoning, yet their efficacy is constrained by a fundamental memory limitation: a static context window that resets with each interaction. This prevents them from accumulating experience and adapting to dynamic, long-term tas

Cited by 0SourcePDFScholar