arXiv Computer Vision September 11, 2026 By Dongyang Chen, Chaoyang Wang, Dezhao Su, Xi Xiao, Zeyu Zhang, Jing Xiong, Qing Li, Yuzhang Shang, Shichao Kan

V-Retrver: Evidence-Driven Agentic Reasoning for Universal Multimodal Retrieval

Read the original on arXiv Computer Vision →

V‑Retrver is an evidence‑driven retrieval framework that treats universal multimodal retrieval as an agentic reasoning process grounded in visual inspection. It allows multimodal large language models to selectively acquire visual evidence through external tools, alternating between hypothesis generation and targeted visual verification. The approach is trained with a curriculum that blends supervised activation, rejection‑based refinement, and reinforcement learning, achieving an average 23.0% improvement in retrieval accuracy across multiple benchmarks.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computer Vision.

arXiv AI

Aug 17

VISOR: Agentic Visual Retrieval-Augmented Generation via Iterative Search and Over-horizon Reasoning

arXiv:2604. 09508v2 Announce Type: replace-cross Abstract: Visual Retrieval-Augmented Generation (VRAG) empowers Vision-Language Models to retrieve and reason over visually rich documents.

By Yucheng Shen, Jiulong Wu, Jizhou Huang, Dawei Yin, Lingyong Yan, Min Cao

llms rag agents reinforcement-learning efficiency multimodal benchmarks

arXiv AI

Jun 30

ReasonRec: A Reasoning-Augmented Multimodal Agent for Unified Recommendation

arXiv:2606. 28357v1 Announce Type: cross Abstract: Recent advances in multimodal recommenders excel at feature fusion but remain opaque and inefficient decision-makers, lacking explicit reasoning and self-awareness of uncertainty.

By Yihua Zhang, Mingfu Liang, Jiyan Yang, Rong Jin, Wen-Yen Chen, Yiping Han, Huayu Li, Buyun Zhang, Liang Luo, Frank Shyu, Luke Simon, Sijia Liu, Tianlong Chen, Xi Liu

agents fine-tuning efficiency multimodal benchmarks

arXiv Computer Vision

Sep 30

ARK: A Dual-Axis Multimodal Retrieval Benchmark along Reasoning and Knowledge

arXiv:2602.09839v2 Announce Type: replace Abstract: Existing multimodal retrieval benchmarks largely emphasize semantic matching on daily-life images and offer limited diagnostics of professional kno...

By Yijie Lin, Guofeng Ding, Haochen Zhou, Haobin Li, Mouxing Yang, Xi Peng

agents multimodal benchmarks

arXiv Machine Learning

Jul 2

VisReason: A Large-Scale Dataset for Visual Chain-of-Thought Reasoning

arXiv:2511. 17731v2 Announce Type: replace-cross Abstract: Chain-of-Thought (CoT) prompting has proven remarkably effective for eliciting complex reasoning in large language models (LLMs).

By Lingxiao Li, Yifan Wang, Xinyan Gao, Chen Tang, Xiangyu Yue, Chenyu You

llms fine-tuning multimodal benchmarks safety

arXiv Computer Vision

Oct 21

Look Before You Reason: Implicit Visual Thinking for Efficient Multimodal Reasoning

arXiv:2610.27341v1 Announce Type: new Abstract: Vision-language models (VLMs) have advanced rapidly in multimodal reasoning, yet they remain limited on tasks requiring fine-grained understanding of s...

By Zerui Chen, Changrui Chen, Fei Ni, Jiankang Deng

llms reinforcement-learning multimodal benchmarks

arXiv AI

Oct 9

SLVR: Structured Latent Visual Reasoning via Human-like Reasoning Flows

SLVR (Structured Latent Visual Reasoning) is a training framework that blends explicit chain-of-thought with latent reasoning for multimodal large language models. It organizes reasoning into typed latent stages—planning, grounding, evidence selection, and integration—each supervised by corresponding signals such as plans, bounding boxes, visual evidence, and final rationales. Built on Qwen2.5‑VL‑7B, SLVR consistently improves performance on multimodal reasoning benchmarks, achieving significant gains on MMVP, BLINK Relation, V*, MathVista, and ChartQA.

By Albert Gao, Bing Xue, Andrea Zanette

llms multimodal benchmarks

One email a morning, machine-written

Related stories

VISOR: Agentic Visual Retrieval-Augmented Generation via Iterative Search and Over-horizon Reasoning

ReasonRec: A Reasoning-Augmented Multimodal Agent for Unified Recommendation

ARK: A Dual-Axis Multimodal Retrieval Benchmark along Reasoning and Knowledge

VisReason: A Large-Scale Dataset for Visual Chain-of-Thought Reasoning

Look Before You Reason: Implicit Visual Thinking for Efficient Multimodal Reasoning

SLVR: Structured Latent Visual Reasoning via Human-like Reasoning Flows