paper-with-me

Papers

Memory Sharing for Large Language Model based Agents

2024-04-15 · Hang Gao, Yongfeng Zhang

The adaptation of Large Language Model (LLM)-based agents to execute tasks via natural language prompts represents a significant advancement, notably eliminating the need for explicit retraining or fine tuning, but are constrained by the comprehensiveness and diversity of the provided examples, leading to outputs that often diverge significantly from expected results, especially when it comes to the open-ended questions. This paper introduces the Memory Sharing, a framework which integrates the real-time memory filter, storage and retrieval to enhance the In-Context Learning process. This framework allows for the sharing of memories among multiple agents, whereby the interactions and shared memories between different agents effectively enhance the diversity of the memories. The collective self-enhancement through interactive learning among multiple agents facilitates the evolution from individual intelligence to collective intelligence. Besides, the dynamically growing memory pool is utilized not only to improve the quality of responses but also to train and enhance the retriever. We evaluated our framework across three distinct domains involving specialized tasks of agents. The experimental results demonstrate that the MS framework significantly improves the agents' performance in addressing open-ended questions.

📄 PDF Abstract BibTeX arXiv:2404.09982

Code (1)

ghupppp/memorysharingllm 공식 구현 pytorch

Tasks

Common Sense ReasoningDiversityIn-Context LearningLanguage ModelingLanguage ModellingLarge Language ModelmodelRetrieval

Similar Papers 제목 키워드 기반

Unifying Dynamic Tool Creation and Cross-Task Experience Sharing through Cognitive Memory Architecture

2025-12-12 · Jiarun Liu, Shiyue Xu, Yang Li, Shangkun Liu 외 arxiv

Large Language Model agents face fundamental challenges in adapting to novel tasks due to limitations in tool availability and experience reuse. Existing approaches either rely on predefined tools with limited coverage o…

Semantic SimilarityCode Generation

LRAgent: Efficient KV Cache Sharing for Multi-LoRA LLM Agents

2026-02-01 · Hyesung Jeon, Hyeongju Ha, Jae-Joon Kim arxiv

Role specialization in multi-LLM agent systems is often realized via multi-LoRA, where agents share a pretrained backbone and differ only by lightweight adapters. Despite sharing base model weights, each agent independen…

Social Hippocampus Memory Learning

2026-03-26 · Liping Yi, Zhiming Zhao, Qinghua Hu arxiv

Social learning highlights that learning agents improve not in isolation, but through interaction and structured knowledge exchange with others. When introduced into machine learning, this principle gives rise to social …

Federated Learning

Collaborative Memory: Multi-User Memory Sharing in LLM Agents with Dynamic Access Control

2025-05-23 · Alireza Rezazadeh, Zichao Li, Ange Lou, Yuying Zhao 외

Complex tasks are increasingly delegated to ensembles of specialized LLM-based agents that reason, communicate, and coordinate actions-both among themselves and through interactions with external tools, APIs, and databas…

Transfer Learning

Safe and Robust Experience Sharing for Deterministic Policy Gradient Algorithms

2022-07-27 · Baturay Saglam, Dogan C. Cicek, Furkan B. Mutlu, Suleyman S. Kozat

Learning in high dimensional continuous tasks is challenging, mainly when the experience replay memory is very limited. We introduce a simple yet effective experience sharing mechanism for deterministic policies in conti…

continuous-controlContinuous ControlDeep Reinforcement LearningOpenAI Gym+1