QwQ and Qwen models have been extensively post-trained to excel at single-step tasks, causing degradation in long multi-turn interactions.

{
  "doc": "nguyen-2025-sfr-deepresearch.md",
  "context": "Proposed explanation for why single-turn reformulation improves performance: models' training distribution is concentrated on single-turn reasoning.",
  "norm_label": "QwQ and Qwen models have been extensively post-trained to excel at single-step tasks, causing degradation in long multi-turn interactions.",
  "graphify_id": "hypothesis_qwen_single_turn_optimization",
  "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": "hypothesis",
  "source_location": "§4.2.1",
  "graphify_file_type": "hypothesis"
}