cd /news/ai-search/sid-ai-releases-sid-2-agentic-search… · home › topics › ai-search › article
[ARTICLE · art-171634] src=marktechpost.com ↗ pub= topic=ai-search verified=true sentiment=↑ positive

SID AI Releases SID-2 Agentic Search Model With 0.720 NDCG Swarm Mode

SID AI released SID-2, an agentic search model trained with reinforcement learning, according to MarkTechPost. A single SID-2 agent reaches 0.585 NDCG in 3.11 seconds, while a 12-agent SID-2 Swarm scores 0.720 NDCG on SID's benchmark, above GPT-6 Astra. The release positions a multi-agent search configuration as outperforming a leading general model on SID's own evaluation.

recommendation

When search quality matters more than latency, fan out to a multi-agent swarm: SID-2's 12-agent configuration gained about 0.135 NDCG over its single agent on SID's benchmark.

more in playbook: Designing agent systems
by read1 min views8 publishedNov 18, 2026

SID AI released SID-2, an agentic search model trained with reinforcement learning. A single agent reaches 0.585 NDCG in 3.11 seconds, and a 12-agent SID-2 Swarm scores 0.720 NDCG, above GPT-6 Astra on SID’s benchmark.

The post SID AI Releases SID-2 Agentic Search Model With 0.720 NDCG Swarm Mode appeared first on MarkTechPost.

── more in #ai-search 4 stories · sorted by recency
── more on @sid ai 3 stories trending now
sponsored brought to you by zahid.host 4,200+ EU-deployed projects
reading about agents? ship yours in a single git push.

Run your AI side-project on zahid.host

EU-based hosting, git-push deploys, automatic HTTPS, no cold starts. Free tier with a custom domain — perfect for shipping the agent you just read about.

$git push zahid main
→ Live at https://your-agent.zahid.host ✓
Get free account → Pricing
from €0/mo · no card required
LIVE [news/sid-ai-releases-sid-…] indexed:0 read:1min 2026-11-18 · —