SID AI released SID-2, an agentic search model trained with reinforcement learning. A single SID-2 agent returns results with a 0.585 NDCG score in about 3.1 seconds. When 12 agents work together as a swarm, the score rises to 0.720 NDCG, which SID AI says is higher than GPT‑6 Astra on its own benchmark.
Why it matters
Higher NDCG scores could give developers more accurate search results when they use SID‑2 in multi‑agent applications.