How can reasoning-optimized models preserve their reasoning ability while gaining agentic capabilities?

{
  "doc": "nguyen-2025-sfr-deepresearch.md",
  "context": "Core research question motivating the paper's focus on continual RL training of reasoning models rather than base/instruction-tuned models.",
  "norm_label": "How can reasoning-optimized models preserve their reasoning ability while gaining agentic capabilities?",
  "graphify_id": "question_how_to_preserve_reasoning_agentic",
  "source_file": "nguyen-2025-sfr-deepresearch.md",
  "imported_from": "/Users/antonborzov/Documents/Research.nosync/papers/extract_typed_out/nguyen-2025-sfr-deepresearch/graph.json",
  "extracted_type": "question",
  "source_location": "§2.2",
  "graphify_file_type": "question"
}