Hacker News · AI·· 2 h agoAI score71
SID Releases SID-2 Technical Report: Scaling Search with Agent Swarms
SID-2 Technical Report: Scaling Search Swarms
AI summary
SID has released the SID-2 technical report, a retrieval model trained via reinforcement learning that uses agent swarms to search in parallel and share their findings. SID-2 supports a 262k token context window, three reasoning effort levels (low, medium, high), and Metric Steering, letting users choose the retrieval objective among NDCG, F1, and Recall@k.
Source:Hacker News · AI · sid.ai