Original research from the AGNT lab — memory systems, self-improvement, evaluation and machine-verified results.
AI agent memory explained: working, episodic, semantic and procedural memory, the main architectures (MemGPT, Generative Agents, Mem0), why bigger context windows are not memory, and how to design it.
Why Jev, GLiNER, classifiers and reasoning LLMs belong in the same architecture, and how to decide when an AI system should think harder.
How AGNT's evolution system observes every execution, extracts typed insights, and rewrites its own agents, workflows, and skills to compound knowledge over time
Evolving a naive Run-Length Encoder through 10 generations of machine-guided optimization to achieve an 80.9% improvement in combined performance
A comprehensive evaluation framework for AI agent platforms using gold standard datasets, trace-based scoring, and LLM-as-a-Judge evaluators.
A biologically inspired cognitive memory framework modeled after the hippocampal-neocortical system for long-term reasoning and autonomous learning.
A Unified Architecture for Context, Memory, Reasoning, and Recursive Self-Improvement in Autonomous Intelligence Systems
No articles in this category yet.
New agents, workflows and field notes. Sign up for AGNT updates.