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

Lyucheng Qian; John Yuehan Zhang; Pingyu Wang

cs.AISep 18, 2026

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

Authors: Lyucheng Qian, John Yuehan Zhang, Pingyu Wang

Organizations: Sichuan University · University of California, Berkeley

Abstract

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.

Figures & tables

Figure 1: Illustrative interactive ReID example. From the same Top-4 state at Rank 31, the jacket question moves the target to Rank 38, whereas the retrieval-aware shoe question raises it to Rank 2; question value follows the evidence elicited and its effect on re-ranking.

Figure 2: Question-quality judgments and downstream retrieval gain, measured by the reciprocal-rank difference

\Delta_{\mathrm{RR}}=1/r_{\mathrm{after}}-1/r_{\mathrm{before}}

Figure 3: Illustration of layer-wise visual attention used to compute visual reliance.

Figure 4: Overview of RAVEL’s three-stage training pipeline.

Method	Round 3				Round 5				BRI $\downarrow$
Method	$R@1$	$R@5$	$R@10$	mAP	$R@1$	$R@5$	$R@10$	mAP	BRI $\downarrow$
Initial	37.61	61.74	72.01	28.23	37.61	61.74	72.01	28.23	-
PlugIR ( Lee et al., 2024 )	43.15	67.17	76.78	30.92	47.15	70.83	79.73	33.80	1.012
ChatIR ( Levy et al., 2023 )	45.02	69.24	78.60	33.07	49.06	72.94	81.57	35.85	0.997
GPT-5.6 Luna ( OpenAI, 2026 )	46.37	67.73	77.54	35.43	47.88	69.27	78.19	36.56	1.042
SimRV ( Liang and Albanie, 2023 )	62.91	83.26	89.18	38.65	63.42	84.21	89.34	39.46	0.720

Table 1: Interactive retrieval performance on Interactive-PEDES.

Figure 5: Analysis of learned questioning behavior and retrieval-text quality. (a) Ratio of local WH/open questions over interaction rounds. (b) Mean retrieval gain of different question types. (c) Quality of the final retrieval text, measured by query length, negative-word count, and attribute coverage.

Method	CUHK-PEDES				ICFG-PEDES				RSTPReid
Method	$R@1$	$R@5$	$R@10$	mAP	$R@1$	$R@5$	$R@10$	mAP	$R@1$	$R@5$	$R@10$	mAP
CFine ( Yan et al., 2023 )	69.57	85.93	91.15	-	60.83	76.55	82.42	-	50.55	72.50	81.60	-
RaSa ( Bai et al., 2023 )	76.51	76.51	94.25	69.38	65.28	80.40	85.12	41.29	66.90	86.50	91.35	52.31
APTM ( Yang et al., 2023 )	76.53	90.04	94.15	66.91	68.51	82.99	87.56	41.22	67.50	85.70	91.45	52.56
AUL ( Li et al., 2024b )	77.23	90.43	94.41	-	69.16	83.32	88.37	-	71.65	87.55	92.05	-
RDE ( Qin et al., 2024 )	76.20	90.53	94.20	67.85	67.83	82.50	87.28	40.79	67.40	85.65	90.60	52.01

Table 2: Comparison of text-based ReID retrievers and interactive questioners on three benchmarks.

Table 8

Table 7: Prompt used by the Qwen3-VL question-quality evaluator.

Table 10

Panel of Figure 6 — Figure 6: Attribute shares before and after retrieval-aware training.

Panel of Figure 7 — Figure 7: Qualitative comparison on a case where the target starts at Rank 5.

Panel of Figure 8 — Figure 8: Qualitative comparison on a case where the target starts at Rank 52.

Person Re-Identification

Person re-identification matches the same individual across camera views, times, clothing, and sensing modalities despite changes in appearance.

See all 92 papers

In PRAISE of Attributes: Grounding Retrieval Geometry with Query-Conditioned Subspaces for Person Re-Identification
Oct 20, 2026Rajarshi Bhattacharya, Aryan Shukla, Shakeeb Murtaza +4Person Re-Identification Vision-Language Retrieval
LIVIA, École de technologie supérieure · Genetec Inc.
Thinking Before Matching: A Reinforcement Reasoning Paradigm Towards General Person Re-Identification
Apr 21, 2026Quan Zhang, Jingze Wu, Jialong Wang +3Person Re-Identification
Sun Yat-sen University · Alibaba Cloud Computing
A Generative AI Integrated Multimodal Framework for Low-Latency Multi-Camera Person Re-Identification
Sep 13, 2026Leon Fernando, C Dombawala, P. Hettigoda +3Person Re-Identification Efficient Multimodal Inference
University of Moratuwa · Zone24x7 (Pvt) Ltd · Chulalongkorn University +2

Oct 20, 2026J/K move · Enter open · S save

In PRAISE of Attributes: Grounding Retrieval Geometry with Query-Conditioned Subspaces for Person Re-Identification

Rajarshi Bhattacharya, Aryan Shukla, Shakeeb Murtaza, Christian Desrosiers+3

LIVIA, École de technologie supérieure · Genetec Inc.

Person Re-Identification Vision-Language Retrieval Test-Time Adaptation of VLMs Representation Geometry in VLMs

Open paper AskPDF arXiv

Person re-identification (ReID) ranks an image gallery using either an image query or a textual query. In image-to-image (I2I) ReID, viewpoint, illumination, occlusion, and background changes can make distractors appear more similar than the true match. In text-to-image (T2I) ReID, incomplete or ambiguous descriptions may omit key visual evidence. We study this problem for vision-language model (VLM) based ReID, where attributes such as clothing color and carried objects provide useful fine-grained matching cues. However, directly using attribute-prompt similarities as retrieval scores is unreliable because templated prompts can be biased, correlated, and poorly calibrated. We therefore propose PRompt-guided Attribute-based Inference-time Similarity Enhancement (PRAISE), a query-side test-time adaptation framework for VLM-based ReID. Instead of treating prompts as scores, PRAISE uses a transferable attribute-prompt bank to construct an Attribute-Conditioned Subspace (ACS): a query-dependent low-rank subspace induced by the most compatible attribute prompts. ACS provides a controlled attribute-conditioned geometry for reshaping query--gallery affinities and guiding lightweight inference-time updates without identity or attribute labels. Experiments across multiple I2I- and T2I-ReID benchmarks show that PRAISE consistently improves VLM retrieval backbones and outperforms both generic and ReID-specific TTA baselines.

Abstract

Person Re-Identification

Explore similar work

In PRAISE of Attributes: Grounding Retrieval Geometry with Query-Conditioned Subspaces for Person Re-Identification

Thinking Before Matching: A Reinforcement Reasoning Paradigm Towards General Person Re-Identification

A Generative AI Integrated Multimodal Framework for Low-Latency Multi-Camera Person Re-Identification