Classifier-Guided Tactical Generation
Classifier-Guided Tactical Generation
Auto-generated stub. Edit this file to add more details.
A framework that uses classifier guidance to steer multi-agent movement generation toward specific tactical objectives at inference time.
Why It Matters
This represents a powerful paradigm for steering generative models in multi-agent environments using heterogeneous constraints like natural language or rules.
Evidence
TacticGen enables adaptable tactic generation tailored to diverse inference-time objectives through classifier guidance mechanism
Related Papers
Metadata & Links
- created_at
- 2026-04-23T05:49:14Z