Copertina

MEMAUDIT: An Exact Package-Oracle Evaluation Protocol for Budgeted Long-Term LLM Memory Writing

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Bhargava, Nishant, Barrento, Rodrigo Sobral
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Artificial Intelligence
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Evaluating Very Long-Term Conversational Memory of LLM Agents
di: Maharana, Adyasha, et al.
Pubblicazione: (2024)

HiMem: Hierarchical Long-Term Memory for LLM Long-Horizon Agents
di: Zhang, Ningning, et al.
Pubblicazione: (2026)

Position: Episodic Memory is the Missing Piece for Long-Term LLM Agents
di: Pink, Mathis, et al.
Pubblicazione: (2025)

Preference-Aware Memory Update for Long-Term LLM Agents
di: Sun, Haoran, et al.
Pubblicazione: (2025)

Dynamic Long Short-Term Memory Based Memory Storage For Long Horizon LLM Interaction
di: Lou, Yuyang, et al.
Pubblicazione: (2025)

A Heterogeneous Temporal Memory Governance Framework for Long-Term LLM Persona Consistency
di: Yang, Zhao, et al.
Pubblicazione: (2026)

Hierarchical Memory for High-Efficiency Long-Term Reasoning in LLM Agents
di: Sun, Haoran, et al.
Pubblicazione: (2025)

Multi-Layered Memory Architectures for LLM Agents: An Experimental Evaluation of Long-Term Context Retention
di: Tiwari, Sunil, et al.
Pubblicazione: (2026)

EngramaBench: Evaluating Long-Term Conversational Memory with Structured Graph Retrieval
di: Acuna, Julian
Pubblicazione: (2026)

CloneMem: Benchmarking Long-Term Memory for AI Clones
di: Hu, Sen, et al.
Pubblicazione: (2026)

StoryBench: A Dynamic Benchmark for Evaluating Long-Term Memory with Multi Turns
di: Wan, Luanbo, et al.
Pubblicazione: (2025)

HyperMem: Hypergraph Memory for Long-Term Conversations
di: Yue, Juwei, et al.
Pubblicazione: (2026)

MemGround: Long-Term Memory Evaluation Kit for Large Language Models in Gamified Scenarios
di: Ding, Yihang, et al.
Pubblicazione: (2026)

xLSTM: Extended Long Short-Term Memory
di: Beck, Maximilian, et al.
Pubblicazione: (2024)

Long Term Memory: The Foundation of AI Self-Evolution
di: Jiang, Xun, et al.
Pubblicazione: (2024)

MEMTRACK: Evaluating Long-Term Memory and State Tracking in Multi-Platform Dynamic Agent Environments
di: Deshpande, Darshan, et al.
Pubblicazione: (2025)

Foundations of Global Consistency Checking with Noisy LLM Oracles
di: He, Paul, et al.
Pubblicazione: (2026)

ContextBudget: Budget-Aware Context Management for Long-Horizon Search Agents
di: Wu, Yong, et al.
Pubblicazione: (2026)

Automatic Legal Writing Evaluation of LLMs
di: Pires, Ramon, et al.
Pubblicazione: (2025)

Short-Term-to-Long-Term Memory Transfer for Knowledge Graphs under Partial Observability
di: Kim, Taewoon, et al.
Pubblicazione: (2026)

Is Agent Memory a Database? Rethinking Data Foundations for Long-Term AI Agent Memory
di: Orogat, Abdelghny, et al.
Pubblicazione: (2026)

M2A: Multimodal Memory Agent with Dual-Layer Hybrid Memory for Long-Term Personalized Interactions
di: Feng, Junyu, et al.
Pubblicazione: (2026)

StreamBP: Memory-Efficient Exact Backpropagation for Long Sequence Training of LLMs
di: Luo, Qijun, et al.
Pubblicazione: (2025)

Self-Improvement Imitation with Biologically Guided Search for Protein Design Under Oracle Budgets
di: Khanna, Ashima, et al.
Pubblicazione: (2026)

Solving Truly Massive Budgeted Monotonic POMDPs with Oracle-Guided Meta-Reinforcement Learning
di: Vora, Manav, et al.
Pubblicazione: (2024)

Controllable Memory Usage: Balancing Anchoring and Innovation in Long-Term Human-Agent Interaction
di: Tian, Muzhao, et al.
Pubblicazione: (2026)

MultiSessionCollab: Learning User Preferences with Memory to Improve Long-Term Collaboration
di: Mehri, Shuhaib, et al.
Pubblicazione: (2026)

Mesh Memory Protocol: Semantic Infrastructure for Multi-Agent LLM Systems
di: Xu, Hongwei
Pubblicazione: (2026)

Synthesizing Procedural Memory: Challenges and Architectures in Automated Workflow Generation
di: Gaurav, Nishant, et al.
Pubblicazione: (2025)

CarMem: Enhancing Long-Term Memory in LLM Voice Assistants through Category-Bounding
di: Kirmayr, Johannes, et al.
Pubblicazione: (2025)

CAIM: Development and Evaluation of a Cognitive AI Memory Framework for Long-Term Interaction with Intelligent Agents
di: Westhäußer, Rebecca, et al.
Pubblicazione: (2025)

KARMA: Augmenting Embodied AI Agents with Long-and-short Term Memory Systems
di: Wang, Zixuan, et al.
Pubblicazione: (2024)

MemRouter: Memory-as-Embedding Routing for Long-Term Conversational Agents
di: Hu, Tianyu, et al.
Pubblicazione: (2026)

MGRetrieval: Memory-Guided Reflective Retrieval for Long-Term Dialogue Agents
di: Wang, Tan, et al.
Pubblicazione: (2026)

BudgetThinker: Empowering Budget-aware LLM Reasoning with Control Tokens
di: Wen, Hao, et al.
Pubblicazione: (2025)

Mem2ActBench: A Benchmark for Evaluating Long-Term Memory Utilization in Task-Oriented Autonomous Agents
di: Shen, Yiting, et al.
Pubblicazione: (2026)

Does Memory Need Graphs? A Unified Framework and Empirical Analysis for Long-Term Dialog Memory
di: Hu, Sen, et al.
Pubblicazione: (2026)

MemoryRewardBench: Benchmarking Reward Models for Long-Term Memory Management in Large Language Models
di: Tang, Zecheng, et al.
Pubblicazione: (2026)

HIMM: Human-Inspired Long-Term Memory Modeling for Embodied Exploration and Question Answering
di: Li, Ji, et al.
Pubblicazione: (2026)

Mem-Gallery: Benchmarking Multimodal Long-Term Conversational Memory for MLLM Agents
di: Bei, Yuanchen, et al.
Pubblicazione: (2026)