T-Search Open-Sourced: Small Model Boosts Retrieval

T-Search is an open-weight agentic retriever designed for complex questions requiring multiple rounds of search.

Built on the Qwen3.6-35B-A3B model and fine-tuned on adversarially filtered synthetic data, it achieves a Recall@10 of 56.0 in single-rollout tests across seven English and Russian benchmarks, a 14.4-point improvement over its base model. Three fused rollouts reach 61.3.

The architecture leaves answer generation to downstream models, allowing backend or generator swaps without retraining. The team also released three new benchmarks, including TRuST, the first native-Russian hard-search benchmark.