dataset
active
dataset:gpt-oss-20b

gpt-oss-20b

Reasoning-optimized base model used for training SFR-DR-20B, the paper's best-performing variant.

Neighborhood — ranked by edge-count

Frameworks (1)

framework
  • SFR-DeepResearch
    mentions
    The paper's core contribution: an RL-based framework for training autonomous single-agent LLMs to perform deep research with web search, browsing, and code execution.