Test-Time Compute for Dense Retrieval: Agentic Program Generation with Frozen Embedding Models 事件

Test-Time Compute for Dense Retrieval: Agentic Program Generation with Frozen Embedding Models arXiv:2605.11374v3 Announce Type: replace-cross Abstract: Test-time compute is widely believed to benefit only large reasoning models. We show it also helps small embedding models. Since modern embedding models are distilled from LLM backbones, a frozen encoder should benefit from extra inference compute without retraining. An agentic program-search loop explores 144 candidate programs over a frozen e