Related papers: Position: Episodic Memory is the Missing Piece for Long-Term LLM Agents

Position: Episodic Memory is the Missing Piece for Long-Term LLM Agents

URL: http://arxiv.org/abs/2502.06975v1
Date: Mon, 10 Feb 2025 19:14:51 GMT
Title: Position: Episodic Memory is the Missing Piece for Long-Term LLM Agents
Authors: Mathis Pink, Qinyuan Wu, Vy Ai Vo, Javier Turek, Jianing Mu, Alexander Huth, Mariya Toneva,
Abstract summary: We present an episodic memory framework for Large Language Models (LLMs) agents, centered around five key properties of episodic memory. This position paper argues that now is the right time for an explicit, integrated focus on episodic memory to catalyze the development of long-term agents.
Score: 43.94686139164999
License:
Abstract: As Large Language Models (LLMs) evolve from text-completion tools into fully fledged agents operating in dynamic environments, they must address the challenge of continually learning and retaining long-term knowledge. Many biological systems solve these challenges with episodic memory, which supports single-shot learning of instance-specific contexts. Inspired by this, we present an episodic memory framework for LLM agents, centered around five key properties of episodic memory that underlie adaptive and context-sensitive behavior. With various research efforts already partially covering these properties, this position paper argues that now is the right time for an explicit, integrated focus on episodic memory to catalyze the development of long-term agents. To this end, we outline a roadmap that unites several research directions under the goal to support all five properties of episodic memory for more efficient long-term LLM agents.

Related papers

Episodic Memories Generation and Evaluation Benchmark for Large Language Models [7.660368798066376]
We argue that integrating episodic memory capabilities into Large Language Models is essential for advancing AI towards human-like cognition. We develop a structured approach to represent episodic events, encapsulating temporal and spatial contexts, involved entities, and detailed descriptions. We synthesize a unique episodic memory benchmark, free from contamination, and release open source code and datasets to assess LLM performance.
arXiv Detail & Related papers (2025-01-21T02:16:13Z)
On the Structural Memory of LLM Agents [20.529239764968654]
Memory plays a pivotal role in enabling large language model(LLM)-based agents to engage in complex and long-term interactions. This paper investigates how memory structures and memory retrieval methods affect the performance of LLM-based agents.
arXiv Detail & Related papers (2024-12-17T04:30:00Z)
InternLM-XComposer2.5-OmniLive: A Comprehensive Multimodal System for Long-term Streaming Video and Audio Interactions [104.90258030688256]
This project introduces disentangled streaming perception, reasoning, and memory mechanisms, enabling real-time interaction with streaming video and audio input. This project simulates human-like cognition, enabling multimodal large language models to provide continuous and adaptive service over time.
arXiv Detail & Related papers (2024-12-12T18:58:30Z)
LongMemEval: Benchmarking Chat Assistants on Long-Term Interactive Memory [68.97819665784442]
This paper introduces LongMemEval, a benchmark designed to evaluate five core long-term memory abilities of chat assistants. LongMemEval presents a significant challenge to existing long-term memory systems. We present a unified framework that breaks down the long-term memory design into four design choices.
arXiv Detail & Related papers (2024-10-14T17:59:44Z)
HERMES: temporal-coHERent long-forM understanding with Episodes and Semantics [32.117677036812836]
HERMES is a model that simulates episodic memory accumulation to capture action sequences. Episodic COmpressor efficiently aggregates crucial representations from micro to semi-macro levels. Semantic ReTRiever dramatically reduces feature dimensionality while preserving relevant macro-level information.
arXiv Detail & Related papers (2024-08-30T17:52:55Z)
Hello Again! LLM-powered Personalized Agent for Long-term Dialogue [63.65128176360345]
We introduce a model-agnostic framework, the Long-term Dialogue Agent (LD-Agent) It incorporates three independently tunable modules dedicated to event perception, persona extraction, and response generation. The effectiveness, generality, and cross-domain capabilities of LD-Agent are empirically demonstrated.
arXiv Detail & Related papers (2024-06-09T21:58:32Z)
A Survey on the Memory Mechanism of Large Language Model based Agents [66.4963345269611]
Large language model (LLM) based agents have recently attracted much attention from the research and industry communities. LLM-based agents are featured in their self-evolving capability, which is the basis for solving real-world problems. The key component to support agent-environment interactions is the memory of the agents.
arXiv Detail & Related papers (2024-04-21T01:49:46Z)
Evaluating Very Long-Term Conversational Memory of LLM Agents [95.84027826745609]
We introduce a machine-human pipeline to generate high-quality, very long-term dialogues. We equip each agent with the capability of sharing and reacting to images. The generated conversations are verified and edited by human annotators for long-range consistency.
arXiv Detail & Related papers (2024-02-27T18:42:31Z)
Empowering Working Memory for Large Language Model Agents [9.83467478231344]
This paper explores the potential of applying cognitive psychology's working memory frameworks to large language models (LLMs) An innovative model is proposed incorporating a centralized Working Memory Hub and Episodic Buffer access to retain memories across episodes. This architecture aims to provide greater continuity for nuanced contextual reasoning during intricate tasks and collaborative scenarios.
arXiv Detail & Related papers (2023-12-22T05:59:00Z)

This list is automatically generated from the titles and abstracts of the papers in this site.