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
- Move data centers to the moon? Let AI ruin an uninhabited planet — DevToD4 · 2026-08-16
- Nvidia reportedly in talks to invest up to $3B in SoftBank's SB Energy for OpenAI data center — Polymarket · 2026-08-16
- Exploring agent behavior when equipped with an owned knowledge library — dfinke · 2026-08-16
- Vietjet Invests Additional $9.5M in Starlink, Accelerating In-Flight Internet Deployment — XFreeze · 2026-08-16
- llama.cpp integrates Dots3 Note model, scoring 78.4 on SWE-bench Verified — victormustar · 2026-08-16
- New Book: Algorithms for Modern Hardware Open-Sourced on GitHub — thehiphopswami · 2026-08-16