Copertina

Rethinking How to Remember: Beyond Atomic Facts in Lifelong LLM Agent Memory

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Sun, Jingwei, Zhu, Jianing, Yao, Jiangchao, Liu, Tongliang, Han, Bo
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Computation and Language
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

How Do Multilingual Language Models Remember Facts?
di: Fierro, Constanza, et al.
Pubblicazione: (2024)

Belief Memory: Agent Memory Under Partial Observability
di: Liao, Junfeng, et al.
Pubblicazione: (2026)

MemoryCD: Benchmarking Long-Context User Memory of LLM Agents for Lifelong Cross-Domain Personalization
di: Zhang, Weizhi, et al.
Pubblicazione: (2026)

AriadneMem: Threading the Maze of Lifelong Memory for LLM Agents
di: Zhu, Wenhui, et al.
Pubblicazione: (2026)

Remembering More, Risking More: Longitudinal Safety Risks in Memory-Equipped LLM Agents
di: Al-Tawaha, Ahmad, et al.
Pubblicazione: (2026)

How LoRA Remembers? A Parametric Memory Law for LLM Finetuning
di: Xu, Ziwen, et al.
Pubblicazione: (2026)

From Debate to Equilibrium: Belief-Driven Multi-Agent LLM Reasoning via Bayesian Nash Equilibrium
di: Yi, Xie, et al.
Pubblicazione: (2025)

Ella: Embodied Social Agents with Lifelong Memory
di: Zhang, Hongxin, et al.
Pubblicazione: (2025)

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

Rethinking Memory in LLM based Agents: Representations, Operations, and Emerging Topics
di: Du, Yiming, et al.
Pubblicazione: (2025)

WISE: Rethinking the Knowledge Memory for Lifelong Model Editing of Large Language Models
di: Wang, Peng, et al.
Pubblicazione: (2024)

Self-Calibrated Tuning of Vision-Language Models for Out-of-Distribution Detection
di: Yu, Geng, et al.
Pubblicazione: (2024)

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

AgentHijack: Benchmarking Computer Use Agent Robustness to Common Environment Corruptions
di: Sun, Jingwei, et al.
Pubblicazione: (2026)

Long-Form Information Alignment Evaluation Beyond Atomic Facts
di: Zheng, Danna, et al.
Pubblicazione: (2025)

ArcMemo: Abstract Reasoning Composition with Lifelong LLM Memory
di: Ho, Matthew, et al.
Pubblicazione: (2025)

DeepInception: Hypnotize Large Language Model to Be Jailbreaker
di: Li, Xuan, et al.
Pubblicazione: (2023)

Beyond the Context Window: A Cost-Performance Analysis of Fact-Based Memory vs. Long-Context LLMs for Persistent Agents
di: Pollertlam, Natchanon, et al.
Pubblicazione: (2026)

Remember Me, Refine Me: A Dynamic Procedural Memory Framework for Experience-Driven Agent Evolution
di: Cao, Zouying, et al.
Pubblicazione: (2025)

From Passive to Active Reasoning: Can Large Language Models Ask the Right Questions under Incomplete Information?
di: Zhou, Zhanke, et al.
Pubblicazione: (2025)

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

If an LLM Were a Character, Would It Know Its Own Story? Evaluating Lifelong Learning in LLMs
di: Fan, Siqi, et al.
Pubblicazione: (2025)

Do Self-Evolving Agents Forget? Capability Degradation and Preservation in Lifelong LLM Agent Adaptation
di: Yu, Ye, et al.
Pubblicazione: (2026)

Beyond Fact Retrieval: Episodic Memory for RAG with Generative Semantic Workspaces
di: Rajesh, Shreyas, et al.
Pubblicazione: (2025)

Learning What to Remember: Adaptive Probabilistic Memory Retention for Memory-Efficient Language Models
di: Rafiuddin, S M, et al.
Pubblicazione: (2025)

Atomic Fact Decomposition Helps Attributed Question Answering
di: Yan, Zhichao, et al.
Pubblicazione: (2024)

Rethinking Loss Functions for Fact Verification
di: Mukobara, Yuta, et al.
Pubblicazione: (2024)

Do All Autoregressive Transformers Remember Facts the Same Way? A Cross-Architecture Analysis of Recall Mechanisms
di: Choe, Minyeong, et al.
Pubblicazione: (2025)

HeLa-Mem: Hebbian Learning and Associative Memory for LLM Agents
di: Zhu, Jinchang, et al.
Pubblicazione: (2026)

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

Ask Only When Needed: Proactive Retrieval from Memory and Skills for Experience-Driven Lifelong Agents
di: Cai, Yuxuan, et al.
Pubblicazione: (2026)

How Brittle is Agent Safety? Rethinking Agent Risk under Intent Concealment and Task Complexity
di: Ma, Zihan, et al.
Pubblicazione: (2025)

TrendFact: A Benchmark for Explainable Hotspot Perception in Fact-Checking with Natural Language Explanation
di: Zhang, Xiaocheng, et al.
Pubblicazione: (2024)

On the Structural Memory of LLM Agents
di: Zeng, Ruihong, et al.
Pubblicazione: (2024)

Beyond Translation: LLM-Based Data Generation for Multilingual Fact-Checking
di: Chung, Yi-Ling, et al.
Pubblicazione: (2025)

Beyond Heuristics: A Decision-Theoretic Framework for Agent Memory Management
di: Sun, Changzhi, et al.
Pubblicazione: (2025)

Atomic Inference for NLI with Generated Facts as Atoms
di: Stacey, Joe, et al.
Pubblicazione: (2023)

Beyond Known Facts: Generating Unseen Temporal Knowledge to Address Data Contamination in LLM Evaluation
di: Amalvy, Arthur, et al.
Pubblicazione: (2026)

Rethinking Memory Mechanisms of Foundation Agents in the Second Half: A Survey
di: Huang, Wei-Chieh, et al.
Pubblicazione: (2026)

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