# Autoregressive Retriever: Improving Query Understanding from Item Feedback for Universal Multimodal Retrieval

arXiv: https://arxiv.org/abs/2610.11666 · HTML: https://mlsanity.com/paper/2610.11666/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 13 of its 43 references that are in the map.
- First posted on arXiv 8 Oct 2026.

## Builds on (most cited first, 13 of 13)

- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [Qwen3-VL-Embedding and Qwen3-VL-Reranker: A Unified Framework for State-of-the-Art Multimodal Retrieval and Ranking](https://mlsanity.com/paper/2601.04720/) (2026)
- [E5-V: Universal Embeddings with Multimodal Large Language Models](https://mlsanity.com/paper/2407.12580/) (2024)
- [Improving Query Representations for Dense Retrieval with Pseudo Relevance Feedback](https://mlsanity.com/paper/2108.13454/) (2021)
- [TRACE: Task-Adaptive Reasoning and Representation Learning for Universal Multimodal Retrieval](https://mlsanity.com/paper/2603.02929/) (2026)
- [LaME: Learning to Think in Latent Space for Multimodal Embedding via Information Bottleneck](https://mlsanity.com/paper/2606.13061/) (2026)
- [ELVA: Exploring Ranking-Driven Universal Multimodal Retrieval](https://mlsanity.com/paper/2606.20280/) (2026)
- [Think When Needed: Adaptive Reasoning-Driven Multimodal Embeddings with a Dual-LoRA Architecture](https://mlsanity.com/paper/2605.14448/) (2026)
- [Bottleneck Tokens for Unified Multimodal Retrieval](https://mlsanity.com/paper/2604.11095/) (2026)
- [GRAPE: Let GRPO Supervise Query Rewriting by Ranking for Retrieval](https://mlsanity.com/paper/2509.23370/) (2025)
- [QueryAgent-R1: Bridging Query Generation and Product Retrieval for E-Commerce Query Recommendation](https://mlsanity.com/paper/2606.05671/) (2026)
- [OneRetrieval: Unifying Multi-Branch E-commerce Retrieval with an Editable Generative Model](https://mlsanity.com/paper/2606.13533/) (2026)
- [ADORE: Iterative Query Expansion with Retrieval-Grounded Relevance Feedback](https://mlsanity.com/paper/2606.13905/) (2026)

## Abstract (arXiv)

Universal multimodal retrieval typically encodes a query once and ranks independently indexed items by embedding similarity. This design supports efficient search, but leaves the query representation unchanged even when retrieved items could help clarify the information need. We introduce the AutoRegressive Retriever (ARR), a multimodal retrieval model that learns both to select informative items and to use their content to refine subsequent retrieval. ARR alternates between retrieving an item and updating the query embedding, then uses the final embedding to rank the collection. Supervised fine-tuning teaches the encoder to use feedback through stepwise contrastive supervision. Reinforcement learning treats feedback items as actions and optimizes their selection using the final reciprocal rank of a relevant item. A query-side adapter enables this optimization against a fixed item index. ARR demonstrates strong retrieval performance on both in-domain and zero-shot benchmarks, outperforming the compared baselines on average. Further analyses show that feedback improves retrieval at inference time and that training with feedback also improves the initial query embedding, before any item is observed.