The papers

Most central to this idea first, not most recent.

• Chinese Techcs.AIcode

  C3M preserves multimodal evidence across sessions within fixed memory budgets

  Huzhou Normal University, Alibaba Group · Sept 2026

• Chinese Techcs.CV

  Streaming video memory works better when internalized as evolving latent tokens

  Nanjing University of Science and Technology, Ant Group · Sept 2026

• Independentcs.AI

  Memory consolidation outperforms retention under tight budgets, but retention wins when budgets are loose.

  July 2026

• Big Techcs.AI

  Memory as state management instead of semantic retrieval improves long-horizon agents

  University of Science and Technology of China, Microsoft · June 2026

• Industrycs.AIcode

  Memory lets traffic-simulation agents build reusable skills without retraining

  Jilin University · Sept 2026

• Industrycs.AI

  Self-configured memory views improve retrieval across long conversations

  National University of Defense Technology · Sept 2026

• Big Techcs.AI

  Memory guidelines help language-model agents succeed consistently across repeated runs

  IBM Software Innovation Lab, IBM Research · Sept 2026

• Big Techcs.AI

  Post-training can replace prompt-time schema injection for enterprise coding agents

  Amazon Advertising Foundations, Amazon Web Services Agentic AI · June 2026

• Industrycs.AI

  Kernel-managed memory personalizes multiple AI agents with shorter prompts

  Rutgers University · Sept 2026

• Independentcs.AI

  Smarter merging and packing improve LLM memory under tight budgets

  Sept 2026

• Top Universitycs.AI

  First systematic characterization of agent memory systems across long-horizon tasks

  Stanford University, Independent Researcher · June 2026