Human-Like Lifelong Memory: A Neuroscience-Grounded Architecture for Infinite Interaction

Diego C. Lerma-Torres

Keywords: LLM memory, long-term memory for large language models, agentic AI memory, bio-inspired cognitive architecture, beyond RAG, knowledge graph memory, hallucination reduction, System 1 System 2 cognition, neuroscience-inspired AI, context window limitations, persistent memory, cognitive behavioral therapy AI, memory-augmented language models, lifelong learning agents

TL;DR: We propose a neuroscience-grounded memory architecture for LLMs with emotional valence vectors, System 1/2 routing via a thalamic gateway, and curiosity-driven gist formation that enables lifelong interaction with decreasing cost over time.

Abstract:

Large language models lack persistent, structured memory for long-term interaction and context-sensitive retrieval. Expanding context windows does not solve this: recent evidence shows that **context length alone degrades reasoning by up to 85%**—even with perfect retrieval. We propose a bio-inspired memory framework grounded in complementary learning systems theory, cognitive behavioral therapy's belief hierarchy, dual-process cognition, and fuzzy-trace theory, organized around **three principles**:

1. **Memory has valence, not just content**—pre-computed emotional-associative summaries (*valence vectors*) organized in an emergent belief hierarchy inspired by Beck's cognitive model enable instant orientation before deliberation;
2. **Retrieval defaults to System 1 with System 2 escalation**—automatic spreading activation and passive priming as default, with deliberate retrieval only when needed, and *graded epistemic states* that address hallucination structurally; and
3. **Encoding is active, present, and feedback-dependent**—a *thalamic gateway* tags and routes information between stores, while the executive forms gists through curiosity-driven investigation, not passive exposure.

**Seven functional properties** specify what any implementation must satisfy. Over time, the system converges toward System 1 processing—the computational analog of clinical expertise—producing interactions that become **cheaper, not more expensive**, with experience.

Submission Number: 74