Useful Memories Become Faulty When Continuously Updated by LLMs

arXiv:2605.12978 · cs.AI · Submitted 2026-05-13 · Read on arXiv

cs.AI

Submitted: 2026-05-13

Updated: 2026-08-29

Terminology

• Abstraction — 67× in this paper · explained in 1 episode
• Generalization — 14× in this paper · explained in 13 episodes
• Accuracy — 10× in this paper · explained in 1 episode
• Benchmark — 9× in this paper · explained in 2 episodes
• Failure Modes — 9× in this paper · explained in 3 episodes
• Trace — 9× in this paper · explained in 2 episodes
• Ablation — 8× in this paper · explained in 1 episode
• Agent Workflow Memory — 5× in this paper
• Agent Memory — 4× in this paper · explained in 1 episode
• Distillation — 4× in this paper · explained in 2 episodes
• Adaptation — 3× in this paper · explained in 1 episode
• In-Context Learning — 3× in this paper · explained in 4 episodes
• Analyzer — 2× in this paper · explained in 1 episode
• LLM judge — 2× in this paper · explained in 2 episodes
• Metacognition — 2× in this paper · explained in 5 episodes
• Reinforcement Learning — 2× in this paper · explained in 4 episodes
• Task Goal Completion — 2× in this paper
• Verification — 2× in this paper · explained in 2 episodes
• Action Space — 1× in this paper · explained in 1 episode
• Affordance — 1× in this paper · explained in 1 episode
• Benchmarking — 1× in this paper · explained in 3 episodes
• Catastrophic Forgetting — 1× in this paper · explained in 5 episodes
• Chain-of-Thought Prompting — 1× in this paper · explained in 2 episodes
• Continual Learning — 1× in this paper · explained in 2 episodes
• Fine-Tuning — 1× in this paper · explained in 5 episodes
• Scaffolding — 1× in this paper · explained in 3 episodes
• Self-Evolving Agents — 1× in this paper · explained in 2 episodes
• Transferability — 1× in this paper · explained in 4 episodes
• World Model — 1× in this paper · explained in 7 episodes

Sources

• Mem0: Building Production-Ready AI Agents with Scalable Long-Term Memory
• Mind2Web: Towards a Generalist Agent for the Web
• PEARL: Self-Evolving Assistant for Time Management with Reinforcement Learning
• ARC-GEN: A Mimetic Procedural Benchmark Generator for the Abstraction and Reasoning Corpus
• The ConceptARC Benchmark: Evaluating Understanding and Generalization in the ARC Domain
• AppWorld: A Controllable World of Apps and People for Benchmarking Interactive Coding Agents
• WebShop: Towards Scalable Real-World Web Interaction with Grounded Language Agents

Related papers

• MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
• Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
• The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
• MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
• Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems
• VSAL: A Vision Solver with Adaptive Layouts for Graph Property Detection