Weaviate Adds Configurable Effort Parameter to Scale Test-Time Compute in Search Mode
CShorten30 · x · 2026-08-25
Weaviate introduced a configurable effort parameter in its Query Agent's Search Mode, scaling test-time compute during query writing and reranking to balance accuracy against latency. On the BRIGHT Biology benchmark, the ultrahigh setting boosts nDCG@10 to 57.5, compared to 13.0 with Hybrid Search alone. The feature is available in weaviate-agents (Python/TS) versions 1.8.0 and 1.7.0.
More from coding & agent
- VecturaKit: Swift-based on-device vector database with MLX acceleration — rudrank · 2026-08-25
- Building a Multi-Agent Personal Assistant Workflow with Claude — michael_k18 · 2026-08-25
- Browser Use CLI reportedly boosts Hermes agent performance 10x — intellectronica · 2026-08-25
- SUCCESSOR Ω: Neural-Symbolic System Generates and Evolves Executable World Programs — Ghost_Pilot_MD · 2026-08-25
- AI Fact-Checker Audit: 1 in 18 Citations Were Fabricated — jonathancheckwise · 2026-08-25
- Guide: Running Hermes Agent on a Raspberry Pi — LeviTurk · 2026-08-25