Weaviate adds test-time compute scaling to Search Mode, boosting retrieval performance significantly
dl_weekly · x · 2026-08-16
Weaviate has introduced test-time compute scaling to its Query Agent's Search Mode with medium, high, and ultrahigh effort tiers, allowing users to trade latency for accuracy at inference. By investing more compute in query decomposition and reranking, the ultrahigh effort setting lifted nDCG@10 to 57.5 on the BRIGHT Biology benchmark, compared to 13.0 with standard Hybrid Search. This feature allows developers to choose the appropriate level of computational effort per request, balancing speed and cost against the need for precise answers. The update is available in weaviate-agents 1.8.0 and agents-typescript-client 1.7.0.
More from Infra
- First AA-AgentPerf results: NVIDIA Vera Rubin NVL72 delivers up to 5.7x throughput per MW vs GB300 — ArtificialAnlys · 2026-10-16
- Vera Rubin NVL72 first benchmarks: up to 5.7x throughput per MW vs GB300 — ArtificialAnlys · 2026-10-16
- NVIDIA Vera Rubin NVL72 hits up to 5.7x GB300 throughput per MW on agent benchmark — ArtificialAnlys · 2026-10-16
- 14 open-source LLM observability tools to know in 2026, from Langfuse to Laminar — TheTuringPost · 2026-10-16
- Local AI is a routing problem, not a privacy feature: where each task should run — bigdata · 2026-10-16
- Moving agent work from GPUs to CPUs for durable, predictable actions — cramforce · 2026-10-16