# Test-Time Optimization of Query Embeddings with Ranking Aware Reward Maximization

arXiv: https://arxiv.org/abs/2608.12569 · HTML: https://mlsanity.com/paper/2608.12569/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 12 Aug 2026.

## Built on by (most cited first, 2 of 2)

- [CORE: Improving Compositional Reasoning in MLLM Embedding via Reranker Distillation](https://mlsanity.com/paper/2609.04083/) (2026)
- [Historical-Feature Residual Adaptation for Sequential Screening](https://mlsanity.com/paper/2610.19315/) (2026)

## Abstract (arXiv)

Dense retrievers rank documents using vector similarity between a frozen encoder and a precomputed index. While test-time ranking rewards from a reranker or LLM judge can improve results, existing methods discard this signal after a single query. Updating the retriever's weights makes rewards reusable, but this requires parameter access, which is unavailable for closed-source models, and is computationally prohibitive. We propose TTT-Embed (Test-Time Tuning of Embeddings), a framework that distills ranking rewards into a lightweight, learned vector within the output embedding space of a frozen model. This vector is optimized purely from scalar ranking scores assigned to the retriever's own candidate documents, requiring no access to model weights, ground-truth labels, or modifications to index. A single scope parameter controls rewards reuse (global, task, or query), enabling a principled trade-off between reusability and specificity under a fixed reward computation budget. We demonstrate that as the available reward budget scales, the optimal sharing scope shifts dynamically from global-wise to task-wise and finally to query-wise. Evaluated across five embedding models and 15 MTEB retrieval tasks, TTT-Embed improves test-time retrieval by up to +8.36 nDCG@10. Crucially, the learned states generalize effectively to unseen queries (up to +8.57 nDCG@10) and unseen tasks (up to +4.71 nDCG@10). Furthermore, TTT-Embed successfully resolves catastrophic forgetting: by leaving base weights entirely frozen, it recovers degraded general capabilities (up to +8.00 nDCG@10, even surpassing the original base model) while preserving in-domain specialization. These results establish ranking rewards as a reusable test-time state, enabling budget-efficient adaptation for any embedding model, including closed-source APIs.