mlsanityData to 7 Oct 2026

Simulating Human Memory with Language Models

arXiv 2605.25680 ↗First posted 25 May 2026cs.CL cs.AIcited by 2

Not on the map. Why?

Abstract (arXiv)

Language models are increasingly being deployed as user simulators, but their memory is far more reliable than that of real users. To measure this gap, we run a series of classic memory experiments from psychology on both humans and language models. Across tasks, we find that out-of-the-box language models exhibit better memory than humans, even when prompted to imitate human behavior. We then show that better prompting strategies and the use of a compactor can cause language models to forget content in a more human-like way. Using these methods, we show preliminary evidence that language models with human-like memory constraints can function as more effective user simulators in a downstream education task. Finally, we release human reference data and benchmarks to support future work on simulating human memory with language models.

Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 58 of its 85 references that are in the map. First posted on arXiv 25 May 2026.

Builds on

58 of 85 references.

References · 58

  1. 2024The Llama 3 Herd of Modelscited by 14,192
  2. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,355
  3. 2025Qwen3 Technical Reportcited by 8,195
  4. 2021RoFormer: Enhanced Transformer with Rotary Position Embeddingcited by 4,581
  5. 2023Generative Agents: Interactive Simulacra of Human Behaviorcited by 3,500
  6. 2023Lost in the Middle: How Language Models Use Long Contextscited by 3,383
  7. 2019Transformer-XL: Attentive Language Models Beyond a Fixed-Length Contextcited by 1,830
  8. 2022Rethinking the Role of Demonstrations: What Makes In-Context Learning Work?cited by 1,413
  9. 2021What Makes Good In-Context Examples for GPT-3?cited by 1,184
  10. 2025A-MEM: Agentic Memory for LLM Agentscited by 1,000
  11. 2024Evaluating Very Long-Term Conversational Memory of LLM Agentscited by 800
  12. 2023Extending Context Window of Large Language Models via Positional Interpolationcited by 721
38 more
  1. 2024LongMemEval: Benchmarking Chat Assistants on Long-Term Interactive Memorycited by 656
  2. 2023YaRN: Efficient Context Window Extension of Large Language Modelscited by 584
  3. 2025τ2-Bench: Evaluating Conversational Agents in a Dual-Control Environmentcited by 558
  4. 2023Cognitive Architectures for Language Agentscited by 422
  5. 2024Scaling Synthetic Data Creation with 1,000,000,000 Personascited by 397
  6. 2025Zep: A Temporal Knowledge Graph Architecture for Agent Memorycited by 372
  7. 2025Evaluating Memory in LLM Agents via Incremental Multi-Turn Interactionscited by 236
  8. 2023S3: Social-network Simulation System with Large Language Model-Empowered Agentscited by 228
  9. 2022Recurrent Memory Transformercited by 197
  10. 2025AgentSociety: Large-Scale Simulation of LLM-Driven Generative Agents Advances Understanding of Human Behaviors and Societycited by 180
  11. 2023Do LLMs exhibit human-like response biases? A case study in survey designcited by 176
  12. 2024A Human-Inspired Reading Agent with Gist Memory of Very Long Contextscited by 140
  13. 2023User Behavior Simulation with Large Language Model based Agentscited by 136
  14. 2024OASIS: Open Agent Social Interaction Simulations with One Million Agentscited by 127
  15. 2021How much do language models copy from their training data? Evaluating linguistic novelty in text generation using RAVENcited by 124
  16. 2025Verbalized Sampling: How to Mitigate Mode Collapse and Unlock LLM Diversitycited by 100
  17. 2024MEMORYLLM: Towards Self-Updatable Large Language Modelscited by 89
  18. 2026Conditional Memory via Scalable Lookup: A New Axis of Sparsity for Large Language Modelscited by 78
  19. 2024Human-inspired Episodic Memory for Infinite Context LLMscited by 62
  20. 2025Hierarchical Memory for High-Efficiency Long-Term Reasoning in LLM Agentscited by 60
  21. 2025M+: Extending MemoryLLM with Scalable Long-Term Memorycited by 51
  22. 2025SimBench: Benchmarking the Ability of Large Language Models to Simulate Human Behaviorscited by 48
  23. 2026Mind the Sim2Real Gap in User Simulation for Agentic Taskscited by 44
  24. 2025Training Proactive and Personalized LLM Agentscited by 42
  25. 2025LLM-based Human Simulations Have Not Yet Been Reliablecited by 30
  26. 2023Decision-Oriented Dialogue for Human-AI Collaborationcited by 29
  27. 2025Can LLM Agents Simulate Multi-Turn Human Behavior? Evidence from Real Online Customer Behavior Datacited by 27
  28. 2024A Controlled Study on Long Context Extension and Generalization in LLMscited by 26
  29. 2025MOSAIC: Modeling Social AI for Content Dissemination and Regulation in Multi-Agent Simulationscited by 26
  30. 2023In-context Learning Generalizes, But Not Always Robustly: The Case of Syntaxcited by 22
  31. 2024Self-Updatable Large Language Models by Integrating Context into Model Parameterscited by 21
  32. 2023A Systematic Comparison of Syllogistic Reasoning in Humans and Language Modelscited by 20
  33. 2024Linear Recency Bias During Training Improves Transformers' Fit to Reading Timescited by 14
  34. 2026The Need for a Socially-Grounded Persona Framework for User Simulationcited by 14
  35. 2025Can LLM-Simulated Practice and Feedback Upskill Human Counselors? A Randomized Study with 90+ Novice Counselorscited by 13
  36. 2025MEMTRACK: Evaluating Long-Term Memory and State Tracking in Multi-Platform Dynamic Agent Environmentscited by 13
  37. 2023Humans and language models diverge when predicting repeating textcited by 12
  38. 2025The Automated but Risky Game: Modeling and Benchmarking Agent-to-Agent Negotiations and Transactions in Consumer Marketscited by 12

50 most cited of 58 All 58 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 2.

2 papers.

  1. 2026Belief Cascades Drive Persuasion in LLM Agent Networkscited by 0
  2. 2026CogGym: Towards Large-Scale Comparative Evaluation of Human and Machine Cognitioncited by 0