Cover Image

Beyond Heuristics: A Decision-Theoretic Framework for Agent Memory Management

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Sun, Changzhi, Chen, Xiangyu, Luo, Jixiang, Zhang, Dell, Li, Xuelong
Format:	Preprint
Published:	2025
Subjects:	Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

TeleMem: Building Long-Term and Multimodal Memory for Agentic AI
by: Chen, Chunliang, et al.
Published: (2025)

Logic-Regularized Verifier Elicits Reasoning from LLMs
by: Wang, Xinyu, et al.
Published: (2026)

Infinite Video Understanding
by: Zhang, Dell, et al.
Published: (2025)

SmartFreeEdit: Mask-Free Spatial-Aware Image Editing with Complex Instruction Understanding
by: Sun, Qianqian, et al.
Published: (2025)

ClinicalAgents: Multi-Agent Orchestration for Clinical Decision Making with Dual-Memory
by: Ge, Zhuohan, et al.
Published: (2026)

Beyond Retrieval-Ranking: A Multi-Agent Cognitive Decision Framework for E-Commerce Search
by: Zhai, Zhouwei, et al.
Published: (2025)

Case-Based Decision-Theoretic Decoding with Quality Memories
by: Deguchi, Hiroyuki, et al.
Published: (2025)

Locomo-Plus: Beyond-Factual Cognitive Memory Evaluation Framework for LLM Agents
by: Li, Yifei, et al.
Published: (2026)

UMEM: Unified Memory Extraction and Management Framework for Generalizable Memory
by: Ye, Yongshi, et al.
Published: (2026)

Dynamic Affective Memory Management for Personalized LLM Agents
by: Lu, Junfeng, et al.
Published: (2025)

Rethinking How to Remember: Beyond Atomic Facts in Lifelong LLM Agent Memory
by: Sun, Jingwei, et al.
Published: (2026)

Beyond Static Summarization: Proactive Memory Extraction for LLM Agents
by: Yang, Chengyuan, et al.
Published: (2026)

RISK: A Framework for GUI Agents in E-commerce Risk Management
by: Chen, Renqi, et al.
Published: (2025)

HiAgent: Hierarchical Working Memory Management for Solving Long-Horizon Agent Tasks with Large Language Model
by: Hu, Mengkang, et al.
Published: (2024)

Beyond Local vs. External: A Game-Theoretic Framework for Trustworthy Knowledge Acquisition
by: Yao, Rujing, et al.
Published: (2026)

Multi-Agent Debate with Memory Masking
by: Tian, Hongduan, et al.
Published: (2026)

MemPrivacy: Privacy-Preserving Personalized Memory Management for Edge-Cloud Agents
by: Chen, Yining, et al.
Published: (2026)

A Framework for Inference Inspired by Human Memory Mechanisms
by: Zeng, Xiangyu, et al.
Published: (2023)

Beyond Shallow Heuristics: Leveraging Human Intuition for Curriculum Learning
by: Toborek, Vanessa, et al.
Published: (2025)

SentenceVAE: Enable Next-sentence Prediction for Large Language Models with Faster Speed, Higher Accuracy and Longer Context
by: An, Hongjun, et al.
Published: (2024)

Generation with Dynamic Vocabulary
by: Liu, Yanting, et al.
Published: (2024)

MemEmo: Evaluating Emotion in Memory Systems of Agents
by: Liu, Peng, et al.
Published: (2026)

TeleEgo: Benchmarking Egocentric AI Assistants in the Wild
by: Yan, Jiaqi, et al.
Published: (2025)

Agentic Memory: Learning Unified Long-Term and Short-Term Memory Management for Large Language Model Agents
by: Yu, Yi, et al.
Published: (2026)

Beyond RAG for Agent Memory: Retrieval by Decoupling and Aggregation
by: Hu, Zhanghao, et al.
Published: (2026)

EvoGens: A Population-Based Heuristic Search Framework for Scientific Idea Generation
by: Li, Xu, et al.
Published: (2026)

CAST: Character-and-Scene Episodic Memory for Agents
by: Ma, Kexin, et al.
Published: (2026)

ANALOGYKB: Unlocking Analogical Reasoning of Language Models with A Million-scale Knowledge Base
by: Yuan, Siyu, et al.
Published: (2023)

Gestura: A LVLM-Powered System Bridging Motion and Semantics for Real-Time Free-Form Gesture Understanding
by: Li, Zhuoming, et al.
Published: (2025)

Knowledge Access Beats Model Size: Memory Augmented Routing for Persistent AI Agents
by: Liu, Xunzhuo, et al.
Published: (2026)

FinResearchBench: A Logic Tree based Agent-as-a-Judge Evaluation Framework for Financial Research Agents
by: Sun, Rui, et al.
Published: (2025)

SWE-AGILE: A Software Agent Framework for Efficiently Managing Dynamic Reasoning Context
by: Lian, Shuquan, et al.
Published: (2026)

MemFactory: Unified Inference & Training Framework for Agent Memory
by: Guo, Ziliang, et al.
Published: (2026)

Enhancing Conversational Agents via Task-Oriented Adversarial Memory Adaptation
by: Deng, Yimin, et al.
Published: (2026)

From Single to Multi-Granularity: Toward Long-Term Memory Association and Selection of Conversational Agents
by: Xu, Derong, et al.
Published: (2025)

Towards Lifelong Dialogue Agents via Timeline-based Memory Management
by: Ong, Kai Tzu-iunn, et al.
Published: (2024)

Stabilizing LLM Supervised Fine-Tuning via Explicit Distributional Control
by: Wang, Xinyu, et al.
Published: (2026)

SurveyForge: On the Outline Heuristics, Memory-Driven Generation, and Multi-dimensional Evaluation for Automated Survey Writing
by: Yan, Xiangchao, et al.
Published: (2025)

STRIDE: A Tool-Assisted LLM Agent Framework for Strategic and Interactive Decision-Making
by: Li, Chuanhao, et al.
Published: (2024)

Beyond Memorization: A Rigorous Evaluation Framework for Medical Knowledge Editing
by: Chen, Shigeng, et al.
Published: (2025)