README: tighten Drescher description — cite Made-Up Minds, clarify design goal vs running system

Co-authored-by: Cursor <cursoragent@cursor.com>

Author: SimHacker

README.md

@@ -175,7 +175,7 @@ Full details: [MOOLLM: A Microworld Operating System for LLM Orchestration](http
 
 **Speed of Light vs Carrier Pigeon:** Most AI agent systems coordinate *between* LLM calls -- 500ms+ per hop, precision degrades each hop, every turn re-tokenizes the full context. MOOLLM skills run *during* one LLM call -- multiple agents iterating dozens of times inside a single generation, instant latency, perfect precision. AI tutors can debate a zoning decision, explore alternatives, and reach a recommendation in one call rather than a slow chain of API round-trips. Full writeup: [Speed of Light vs Carrier Pigeon](https://github.com/SimHacker/moollm/blob/main/designs/SPEED-OF-LIGHT-VS-CARRIER-PIGEON.md).
 
-**Schema Mechanism + LLMs:** Gary Drescher's [schema mechanism](https://github.com/SimHacker/moollm/tree/main/skills/schema-mechanism) discovers causal structure (context + action = result) while the LLM supplies meanings, explanations, and generalization. Applied to Micropolis: an agent can learn that "placing industrial zones near residential zones causes pollution complaints" not as a hardcoded rule but as a discovered schema grounded in actual simulation behavior. See: [MOOLLM Eval/Incarnate Framework](https://github.com/SimHacker/moollm/blob/main/designs/MOOLLM-EVAL-INCARNATE-FRAMEWORK.md).
+**Schema Mechanism + LLMs:** Gary Drescher's [schema mechanism](https://github.com/SimHacker/moollm/tree/main/skills/schema-mechanism) (*Made-Up Minds*, 1991) is a computational model for discovering causal relationships: a schema is a Context + Action -> Result triple that an agent learns through experience. MOOLLM pairs this with LLM semantic understanding — the schema mechanism discovers structure, the LLM grounds the symbols with meaning and can explain the discovered relationships in natural language. The design goal for Micropolis: an agent discovers that placing industrial zones near residential zones causes pollution complaints, not as a hardcoded rule but as a schema learned from observing the running simulation. See: [MOOLLM Eval/Incarnate Framework](https://github.com/SimHacker/moollm/blob/main/designs/MOOLLM-EVAL-INCARNATE-FRAMEWORK.md).
 
 **Experiment Skill:** The [experiment](https://github.com/SimHacker/moollm/tree/main/skills/experiment) skill brings systematic evaluation to Micropolis. Define an experiment (e.g., "compare tax strategies"), run multiple simulations using speed-of-light, evaluate outcomes against rubrics, iterate with variations, and analyze patterns across runs. The experiment framework was proven with 5 tournament rounds, 20+ games, and 116+ turns in the Fluxx Championship -- the same SIMULATE/EVALUATE/ITERATE/ANALYZE cycle applies to city planning strategies. Inherits from: [simulation](https://github.com/SimHacker/moollm/tree/main/skills/simulation), [evaluator](https://github.com/SimHacker/moollm/tree/main/skills/evaluator), [rubric](https://github.com/SimHacker/moollm/tree/main/skills/rubric), [speed-of-light](https://github.com/SimHacker/moollm/tree/main/skills/speed-of-light).