Image de couverture de livre

CogMem: A Cognitive Memory Architecture for Sustained Multi-Turn Reasoning in Large Language Models

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Zhang, Yiran, Hu, Jincheng, Dras, Mark, Naseem, Usman
Format:	Preprint
Publié:	2025
Sujets:	Computation and Language
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Beyond the Black Box: Demystifying Multi-Turn LLM Reasoning with VISTA
par: Zhang, Yiran, et autres
Publié: (2025)

AlignCultura: Towards Culturally Aligned Large Language Models?
par: Kashyap, Gautam Siddharth, et autres
Publié: (2026)

TurnBench-MS: A Benchmark for Evaluating Multi-Turn, Multi-Step Reasoning in Large Language Models
par: Zhang, Yiran, et autres
Publié: (2025)

Seeing the Threat: Vulnerabilities in Vision-Language Models to Adversarial Attack
par: Ren, Juan, et autres
Publié: (2025)

Framing Political Bias in Multilingual LLMs Across Pakistani Languages
par: Nadeem, Afrozah, et autres
Publié: (2025)

Over-Refusal and Representation Subspaces: A Mechanistic Analysis of Task-Conditioned Refusal in Aligned LLMs
par: Maskey, Utsav, et autres
Publié: (2026)

SHIELD: Classifier-Guided Prompting for Robust and Safer LVLMs
par: Ren, Juan, et autres
Publié: (2025)

Should LLM Safety Be More Than Refusing Harmful Instructions?
par: Maskey, Utsav, et autres
Publié: (2025)

Steering Over-refusals Towards Safety in Retrieval Augmented Generation
par: Maskey, Utsav, et autres
Publié: (2025)

When the Model Said 'No Comment', We Knew Helpfulness Was Dead, Honesty Was Alive, and Safety Was Terrified
par: Kashyap, Gautam Siddharth, et autres
Publié: (2026)

Steering Towards Fairness: Mitigating Political Bias in LLMs
par: Nadeem, Afrozah, et autres
Publié: (2025)

Fairness Evaluation and Inference Level Mitigation in LLMs
par: Nadeem, Afrozah, et autres
Publié: (2025)

We Think, Therefore We Align LLMs to Helpful, Harmless and Honest Before They Go Wrong
par: Kashyap, Gautam Siddharth, et autres
Publié: (2025)

Too Helpful, Too Harmless, Too Honest or Just Right?
par: Kashyap, Gautam Siddharth, et autres
Publié: (2025)

SafeConstellations: Mitigating Over-Refusals in LLMs Through Task-Aware Representation Steering
par: Maskey, Utsav, et autres
Publié: (2025)

MemCog: From Memory-as-Tool to Memory-as-Cognition in Conversational Agents
par: Li, Zihan, et autres
Publié: (2026)

VITAL: A New Dataset for Benchmarking Pluralistic Alignment in Healthcare
par: Shetty, Anudeex, et autres
Publié: (2025)

Mechanistic Interpretability for Large Language Model Alignment: Progress, Challenges, and Future Directions
par: Naseem, Usman
Publié: (2026)

VaxGuard: A Multi-Generator, Multi-Type, and Multi-Role Dataset for Detecting LLM-Generated Vaccine Misinformation
par: Ahmad, Syed Talal, et autres
Publié: (2025)

Agentic Moderation: Multi-Agent Design for Safer Vision-Language Models
par: Ren, Juan, et autres
Publié: (2025)

CogAtom: From Cognitive Atoms to Olympiad-level Mathematical Reasoning in Large Language Models
par: Chen, Zhuofan, et autres
Publié: (2025)

CogLM: Tracking Cognitive Development of Large Language Models
par: Wang, Xinglin, et autres
Publié: (2024)

Benchmarking Large Language Models for Cryptanalysis and Side-Channel Vulnerabilities
par: Maskey, Utsav, et autres
Publié: (2025)

A Survey on Progress in LLM Alignment from the Perspective of Reward Design
par: Ji, Miaomiao, et autres
Publié: (2025)

Reversal of Thought: Enhancing Large Language Models with Preference-Guided Reverse Reasoning Warm-up
par: Yuan, Jiahao, et autres
Publié: (2024)

EvolMem: A Cognitive-Driven Benchmark for Multi-Session Dialogue Memory
par: Shen, Ye, et autres
Publié: (2026)

PersoBench: Benchmarking Personalized Response Generation in Large Language Models
par: Afzoon, Saleh, et autres
Publié: (2024)

XGUARD: A Graded Benchmark for Evaluating Safety Failures of Large Language Models on Extremist Content
par: Abishethvarman, Vadivel, et autres
Publié: (2025)

TokMem: One-Token Procedural Memory for Large Language Models
par: Wu, Zijun, et autres
Publié: (2025)

DUAL-Bench: Measuring Over-Refusal and Robustness in Vision-Language Models
par: Ren, Kaixuan, et autres
Publié: (2025)

CogRAG+: Cognitive-Level Guided Diagnosis and Remediation of Memory and Reasoning Deficiencies in Professional Exam QA
par: Wang, Xudong, et autres
Publié: (2026)

CogGPT: Unleashing the Power of Cognitive Dynamics on Large Language Models
par: Lv, Yaojia, et autres
Publié: (2024)

From Generation to Detection: A Multimodal Multi-Task Dataset for Benchmarking Health Misinformation
par: Zhang, Zhihao, et autres
Publié: (2025)

MulCogBench: A Multi-modal Cognitive Benchmark Dataset for Evaluating Chinese and English Computational Language Models
par: Zhang, Yunhao, et autres
Publié: (2024)

LLM-MemCluster: Empowering Large Language Models with Dynamic Memory for Text Clustering
par: Zhu, Yuanjie, et autres
Publié: (2025)

G-MemLLM: Gated Latent Memory Augmentation for Long-Context Reasoning in Large Language Models
par: Xu, Xun
Publié: (2026)

Web-CogReasoner: Towards Knowledge-Induced Cognitive Reasoning for Web Agents
par: Guo, Yuhan, et autres
Publié: (2025)

Do Personality Traits Interfere? Geometric Limitations of Steering in Large Language Models
par: Bhandari, Pranav, et autres
Publié: (2026)

MemOS: An Operating System for Memory-Augmented Generation (MAG) in Large Language Models
par: Li, Zhiyu, et autres
Publié: (2025)

Myanmar XNLI: Building a Dataset and Exploring Low-resource Approaches to Natural Language Inference with Myanmar
par: Htet, Aung Kyaw, et autres
Publié: (2025)