Image de couverture de livre

Honest Lying: Understanding Memory Confabulation in Reflexive Agents

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Dixit, Prakhar, Kamal, Sadia, Oates, Tim
Format:	Preprint
Publié:	2026
Sujets:	Machine Learning Artificial Intelligence
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

SBI-RAG: Enhancing Math Word Problem Solving for Students through Schema-Based Instruction and Retrieval-Augmented Generation
par: Dixit, Prakhar, et autres
Publié: (2024)

MedGrad E-CLIP: Enhancing Trust and Transparency in AI-Driven Skin Lesion Diagnosis
par: Kamal, Sadia, et autres
Publié: (2025)

Towards Scalable SOAP Note Generation: A Weakly Supervised Multimodal Framework
par: Kamal, Sadia, et autres
Publié: (2025)

Skin-SOAP: A Weakly Supervised Framework for Generating Structured SOAP Notes
par: Kamal, Sadia, et autres
Publié: (2025)

Hierarchical Learning for Maze Navigation: Emergence of Mental Representations via Second-Order Learning
par: Manir, Shalima Binta, et autres
Publié: (2025)

Enhancing Biologically Inspired Hierarchical Temporal Memory with Hardware-Accelerated Reflex Memory
par: Bera, Pavia, et autres
Publié: (2025)

TEN-GUARD: Tensor Decomposition for Backdoor Attack Detection in Deep Neural Networks
par: Hossain, Khondoker Murad, et autres
Publié: (2024)

Confabulation dynamics in a reservoir computer: Filling in the gaps with untrained attractors
par: O'Hagan, Jack, et autres
Publié: (2025)

Predictable Confabulations: Factual Recall by LLMs Scales with Model Size and Topic Frequency
par: Smith, Matthew L., et autres
Publié: (2026)

Generating Expressive and Customizable Evals for Timeseries Data Analysis Agents with AgentFuel
par: Maddi, Aadyaa, et autres
Publié: (2026)

Bootstrapped Mixed Rewards for RL Post-Training: Injecting Canonical Action Order
par: Gupta, Prakhar, et autres
Publié: (2025)

Autotelic Reinforcement Learning: Exploring Intrinsic Motivations for Skill Acquisition in Open-Ended Environments
par: Srivastava, Prakhar, et autres
Publié: (2025)

Deep Recurrent Learning Through Long Short Term Memory and TOPSIS
par: Kamal, Rossi
Publié: (2022)

Honesty to Subterfuge: In-Context Reinforcement Learning Can Make Honest Models Reward Hack
par: McKee-Reid, Leo, et autres
Publié: (2024)

WildfireVLM: AI-powered Analysis for Early Wildfire Detection and Risk Assessment Using Satellite Imagery
par: Ayanzadeh, Aydin, et autres
Publié: (2026)

Rethinking Hallucinations: Correctness, Consistency, and Prompt Multiplicity
par: Ganesh, Prakhar, et autres
Publié: (2026)

Systemizing Multiplicity: The Curious Case of Arbitrariness in Machine Learning
par: Ganesh, Prakhar, et autres
Publié: (2025)

A Walsh Hadamard Derived Linear Vector Symbolic Architecture
par: Alam, Mohammad Mahmudul, et autres
Publié: (2024)

H3Fusion: Helpful, Harmless, Honest Fusion of Aligned LLMs
par: Tekin, Selim Furkan, et autres
Publié: (2024)

Holographic Global Convolutional Networks for Long-Range Prediction Tasks in Malware Detection
par: Alam, Mohammad Mahmudul, et autres
Publié: (2024)

EigenLoRAx: Recycling Adapters to Find Principal Subspaces for Resource-Efficient Adaptation and Inference
par: Kaushik, Prakhar, et autres
Publié: (2025)

Understanding Transformer from the Perspective of Associative Memory
par: Zhong, Shu, et autres
Publié: (2025)

Predictive Modeling of Homeless Service Assignment: A Representation Learning Approach
par: Rahman, Khandker Sadia, et autres
Publié: (2024)

Better World Models Can Lead to Better Post-Training Performance
par: Gupta, Prakhar, et autres
Publié: (2025)

Pivoting Retail Supply Chain with Deep Generative Techniques: Taxonomy, Survey and Insights
par: Wang, Yuan, et autres
Publié: (2024)

Reflex: Reinforcement Learning with Reflection Symmetry Exploitation in State-Based Continuous Control
par: Zhen, Shuai, et autres
Publié: (2026)

Empirical and Experimental Insights into Data Mining Techniques for Crime Prediction: A Comprehensive Survey
par: Taha, Kamal
Publié: (2024)

Observational and Experimental Insights into Machine Learning-Based Defect Classification in Wafers
par: Taha, Kamal
Publié: (2023)

Enhancing Temporal Understanding in LLMs for Semi-structured Tables
par: Deng, Irwin, et autres
Publié: (2024)

The Memory Perturbation Equation: Understanding Model's Sensitivity to Data
par: Nickl, Peter, et autres
Publié: (2023)

Self-Mined Hardness for Safety Fine-Tuning
par: Gupta, Prakhar, et autres
Publié: (2026)

Modular Memory is the Key to Continual Learning Agents
par: Dorovatas, Vaggelis, et autres
Publié: (2026)

State Contamination in Memory-Augmented LLM Agents
par: Wang, Yian, et autres
Publié: (2026)

Scalable Neighborhood-Based Multi-Agent Actor-Critic
par: Goppelsroeder, Tim, et autres
Publié: (2026)

Higher-Order Action Regularization in Deep Reinforcement Learning: From Continuous Control to Building Energy Management
par: Ahmed, Faizan, et autres
Publié: (2026)

Hybrid Self-evolving Structured Memory for GUI Agents
par: Zhu, Sibo, et autres
Publié: (2026)

The Trap of Trajectory: Towards Understanding and Mitigating Spurious Correlations in Agentic Memory
par: Tang, Luoxi, et autres
Publié: (2026)

Understanding Agent Scaling in LLM-Based Multi-Agent Systems via Diversity
par: Yang, Yingxuan, et autres
Publié: (2026)

Beyond Sliding Windows: Learning to Manage Memory in Non-Markovian Environments
par: Tasse, Geraud Nangue, et autres
Publié: (2025)

Choosing How to Remember: Adaptive Memory Structures for LLM Agents
par: Lu, Mingfei, et autres
Publié: (2026)