20B搜索器外置状态打平前沿

重点关注

• Harness-1: Reinforcement Learning for Search Agents with State-Externalizing Harnesses score 9
  入选 HF Daily Papers；HF 热度: 41 upvotes (+4)；有代码实现
• TVIR: Building Deep Research Agents Towards Text--Visual Interleaved Report Generation score 9
  入选 HF Daily Papers；HF 热度: 13 upvotes (+3)；有代码实现；关键词(1): reasoning
• Masking Stale Observations Helps Search Agents -- Until It Doesn't: A Regime Map and Its Mechanism score 10
  入选 HF Daily Papers；HF 热度: 60 upvotes (+4)；有代码实现；关键词(1): agentic
• FineVerify: Scaling Test-Time Compute with Fine-Grained Self-Verification for Agentic Search score 8
  入选 HF Daily Papers；HF 热度: 8 upvotes (+2)；有代码实现；关键词(2): scaling, agentic
• MindZero: Learning Online Mental Reasoning With Zero Annotations score 7
  入选 HF Daily Papers；HF 热度: 4 upvotes (+1)；有代码实现；关键词(2): real-time, reasoning