Jake Lawrence · AI Systems · AI Systems theme
LLM agents can generate responses but have no persistent model of where they are, what they have done, or what they are trying to accomplish.
Proposes a blackboard architecture with six interoperating modules to give LLM-based agents persistent situational awareness across interaction turns. A pre-registered 72-scenario benchmark (SAGEN-Bench, OSF-registered) confirms the architecture's advantage under live perception while isolating perception, not state architecture, as the binding constraint.
SAGEN's blackboard is itself a classification system: it categorizes agent state into six module types. The position paper argues this is not incidental.
Two missing infrastructure layers. SAGEN builds awareness; LLM-QP builds cost-efficiency. Both are classification systems.
SAGEN addresses the gap between generating and knowing. The Beautiful Unfinished argues that gap is permanent.
This is field data, not commentary: dated, sourced, and versioned. Subscribe and the next release, correction or new thread reaches you when it lands. It is the one list for the whole site, so you will get the rest of the work too. No schedule, easy out.
Back to the release table · See it on the network · Machine-readable catalog
I build the AI tools and automations a team adopts, and the full-stack apps and data pipelines under them, and ship them to production. Tell me the problem in a sentence and I'll give you an honest read on fit within a day.
Work with me →