# What Should We Ask Next? Retrieval-Aware Question Learning for Interactive ReID

arXiv: https://arxiv.org/abs/2609.21924 · HTML: https://mlsanity.com/paper/2609.21924/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 27 of its 32 references that are in the map.
- First posted on arXiv 18 Sep 2026.

## Builds on (most cited first, 27 of 27)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [Qwen2.5 Technical Report](https://mlsanity.com/paper/2412.15115/) (2024)
- [QLoRA: Efficient Finetuning of Quantized LLMs](https://mlsanity.com/paper/2305.14314/) (2023)
- [Qwen3-VL Technical Report](https://mlsanity.com/paper/2511.21631/) (2025)
- [LLaVA-OneVision: Easy Visual Task Transfer](https://mlsanity.com/paper/2408.03326/) (2024)
- [Person Search with Natural Language Description](https://mlsanity.com/paper/1702.05729/) (2017)
- [Cross-Modal Implicit Relation Reasoning and Aligning for Text-to-Image Person Retrieval](https://mlsanity.com/paper/2303.12501/) (2023)
- [Semantically Self-Aligned Network for Text-to-Image Part-aware Person Re-identification](https://mlsanity.com/paper/2107.12666/) (2021)
- [DSSL: Deep Surroundings-person Separation Learning for Text-based Person Retrieval](https://mlsanity.com/paper/2109.05534/) (2021)
- [Dialog-based Interactive Image Retrieval](https://mlsanity.com/paper/1805.00145/) (2018)
- [CLIP-Driven Fine-grained Text-Image Person Re-identification](https://mlsanity.com/paper/2210.10276/) (2022)
- [Vision-OPD: Learning to See Fine Details for Multimodal LLMs via On-Policy Self-Distillation](https://mlsanity.com/paper/2605.18740/) (2026)
- [Towards Unified Text-based Person Retrieval: A Large-scale Multi-Attribute and Language Search Benchmark](https://mlsanity.com/paper/2306.02898/) (2023)
- [Noisy-Correspondence Learning for Text-to-Image Person Re-identification](https://mlsanity.com/paper/2308.09911/) (2023)
- [RaSa: Relation and Sensitivity Aware Representation Learning for Text-based Person Search](https://mlsanity.com/paper/2305.13653/) (2023)
- [Zooming without Zooming: Region-to-Image Distillation for Fine-Grained Multimodal Perception](https://mlsanity.com/paper/2602.11858/) (2026)
- [Chatting Makes Perfect: Chat-based Image Retrieval](https://mlsanity.com/paper/2305.20062/) (2023)
- [Interactive Text-to-Image Retrieval with Large Language Models: A Plug-and-Play Approach](https://mlsanity.com/paper/2406.03411/) (2024)
- [Learning to Retrieve Videos by Asking Questions](https://mlsanity.com/paper/2205.05739/) (2022)
- [Simple Baselines for Interactive Video Retrieval with Questions and Answers](https://mlsanity.com/paper/2308.10402/) (2023)
- [WhittleSearch: Interactive Image Search with Relative Attribute Feedback](https://mlsanity.com/paper/1505.04141/) (2015)
- [LLaVA-ReID: Selective Multi-image Questioner for Interactive Person Re-Identification](https://mlsanity.com/paper/2504.10174/) (2025)
- [Human-centered Interactive Learning via MLLMs for Text-to-Image Person Re-identification](https://mlsanity.com/paper/2506.11036/) (2025)
- [Deeper Thought, Weaker Aim: Understanding and Mitigating Perceptual Impairment during Reasoning in Multimodal Large Language Models](https://mlsanity.com/paper/2603.14184/) (2026)
- [Harnessing Weak Pair Uncertainty for Text-based Person Search](https://mlsanity.com/paper/2604.08877/) (2026)
- [Uncertainty-Aware Pedestrian Attribute Recognition via Evidential Deep Learning](https://mlsanity.com/paper/2604.26873/) (2026)

## Abstract (arXiv)

Interactive retrieval with partial evidence constitutes a sequential information-acquisition problem: an agent must choose questions that acquire useful evidence for the next retrieval update. Existing systems train this decision by imitating an offline ordering of candidate QA pairs. However, a question's value depends on the response it elicits and its downstream effect on retrieval. We establish that candidate discriminativeness and perceived usefulness provide weak supervision for this objective, then introduce RAVEL, a retrieval-aware online reinforcement learning framework for interactive person re-identification. RAVEL initializes from supervised question generation, observes the current Top-4 candidates directly, and optimizes the question policy with rank feedback from the full question-answer-retrieval loop. Experiments on Interactive-PEDES show that RAVEL delivers progressively stronger retrieval performance across five interaction rounds. Further analysis shows that RAVEL allocates more of its interaction budget to localized open-ended prompts targeting specific attributes.