Orbit Support Drafter (DPO)

The Drafter agent of a LangGraph multi-agent support system for the fictional shop Orbit Electronics. Base model Qwen/Qwen2.5-0.5B-Instruct, LoRA-fine-tuned and merged. Stage: dpo (sft = supervised on the response simulator; dpo = then aligned with human and critic preferences via Direct Preference Optimisation).

Evaluation (held-out simulated tickets, full multi-agent graph)

Knowledge-base fingerprint: 034b279610ce. Demo model trained on synthetic data; it only knows the toy policies of Orbit Electronics.

Preferences: {'synthetic': 24, 'critic': 14, 'gold': 2} (β=0.1, epochs=2).