ADR-002: V4 Instruct-Only GRPO — revises dual-model plan based on model repo audit 50e0e4d verified rtferraz commited on 13 days ago
Add comprehensive investigation report — performance audit, unexplored alternatives, literature-backed recommendations 4312bfd verified rtferraz commited on 14 days ago
Add session checkpoint: v3 launch decision with full context bead5cb verified rtferraz commited on 15 days ago
Add v3 thinking control patch - task-aware system prompts + think efficiency reward 0f39df7 verified rtferraz commited on 15 days ago
docs: add ADR-001 next steps with detailed execution plans b47b36b verified rtferraz commited on 15 days ago