arXiv AI August 11, 2026 By Alexander Bering

ZenBrain: A Neuroscience-Inspired 7-Layer Memory Architecture for Autonomous AI Systems

arXiv:2604. 23878v3 Announce Type: replace Abstract: ZenBrain is a seven-layer, neuroscience-derived memory architecture for LLM agents that unifies fifteen mechanisms - from Two-Factor synaptic consolidation to a Simulation-Selection sleep loop - under a single MemoryCoordinator: nine foundational algorithms plus six Predictive Memory Architecture components.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv AI.

arXiv AI

Jun 11

Substrate Asymmetry in User-Side Memory: A Diagnostic Framework

arXiv:2606. 11712v1 Announce Type: cross Abstract: User-side memory in LLMs is typically scored as a single "personalization" capability: given a user's history, is the output more user-aware?

By Youwang Deng

llms rag reinforcement-learning fine-tuning safety

arXiv AI

5d ago

$\varepsilon$-MemEvo: Adaptive Cross-Task Memory Transfer for LLM Program Evolution

arXiv:2608. 12522v1 Announce Type: new Abstract: LLM-based program evolution systems such as FunSearch and AlphaEvolve have shown strong ability to discover novel algorithms, but typically optimize each task in isolation, discarding search experience after completion.

By Aofan Liu, Shiyuan Song, Yiyan Qi

llms benchmarks

arXiv Machine Learning

Jun 2

CRMA: A Spectrally-Bounded Backbone for Modular Continual Fine-Tuning of LLMs

arXiv:2606. 00382v1 Announce Type: new Abstract: Sequential fine-tuning of large language models forces a choice: let the shared substrate keep learning and accept catastrophic forgetting, or freeze it after task one and foreclose cross-task refinement.

By Kiran Nayudu, Aswini Nutakki, Sai Vinay Naidu, Ashwin Shanmugasundaram

llms fine-tuning efficiency benchmarks

arXiv AI

5d ago

FluctlightDB: A Memory Model of Data for AI Agents

arXiv:2608. 12365v1 Announce Type: cross Abstract: For fifty years, data systems have answered two questions.

By Ganesh S

llms rag agents benchmarks

arXiv AI

2d ago

MemoryLake on MemoryArena: A Matched Study of Agent Memory Backends

arXiv:2608. 13883v1 Announce Type: new Abstract: Most agent-memory benchmarks test post-hoc recall, whereas MemoryArena evaluates whether memory supports interdependent, multi-session task completion.

By Chaoqun Zhan, Qiang Zhou, Guannan Li, Zhenqiang Huang, Qianjin Wang

llms rag agents benchmarks

arXiv AI

Jul 24

CAMeR: Keyword-Gated Hybrid Activation for Adaptive Memory Retention in LLM Agents

arXiv:2607. 20458v1 Announce Type: cross Abstract: Large language model (LLM) agents operating over extended dialogues accumulate vast amounts of information, yet existing memory systems either retain everything indiscriminately or apply uniform forgetting heuristics that fail to distinguish relevant from irrelevant knowledge.

By Haowen Lai

llms rag agents benchmarks

Related stories

Substrate Asymmetry in User-Side Memory: A Diagnostic Framework

$\varepsilon$-MemEvo: Adaptive Cross-Task Memory Transfer for LLM Program Evolution

CRMA: A Spectrally-Bounded Backbone for Modular Continual Fine-Tuning of LLMs

FluctlightDB: A Memory Model of Data for AI Agents

MemoryLake on MemoryArena: A Matched Study of Agent Memory Backends

CAMeR: Keyword-Gated Hybrid Activation for Adaptive Memory Retention in LLM Agents