Pith. sign in

REVIEW 8 cited by

WeThink: Toward General-purpose Vision-Language Reasoning via Reinforcement Learning

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2506.07905 v1 pith:VLDJTS2K submitted 2025-06-09 cs.CV

Jie Yang , Feipeng Ma , Zitian Wang , Dacheng Yin , Kang Rong , Fengyun Rao , Ruimao Zhang This is my paper
classification cs.CV
keywords reasoningmultimodaldatasetdiversewethinkacrossdatadomains
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Building on the success of text-based reasoning models like DeepSeek-R1, extending these capabilities to multimodal reasoning holds great promise. While recent works have attempted to adapt DeepSeek-R1-style reinforcement learning (RL) training paradigms to multimodal large language models (MLLM), focusing on domain-specific tasks like math and visual perception, a critical question remains: How can we achieve the general-purpose visual-language reasoning through RL? To address this challenge, we make three key efforts: (1) A novel Scalable Multimodal QA Synthesis pipeline that autonomously generates context-aware, reasoning-centric question-answer (QA) pairs directly from the given images. (2) The open-source WeThink dataset containing over 120K multimodal QA pairs with annotated reasoning paths, curated from 18 diverse dataset sources and covering various question domains. (3) A comprehensive exploration of RL on our dataset, incorporating a hybrid reward mechanism that combines rule-based verification with model-based assessment to optimize RL training efficiency across various task domains. Across 14 diverse MLLM benchmarks, we demonstrate that our WeThink dataset significantly enhances performance, from mathematical reasoning to diverse general multimodal tasks. Moreover, we show that our automated data pipeline can continuously increase data diversity to further improve model performance.

Discussion (0). Sign in to comment.

Forward citations

Cited by 8 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Trace: A Taxonomy-Guided Environment for Multidomain Visual Reasoning

    cs.CV 2026-07 conditional novelty 6.0 of 10

    RLVR training on 64,000 procedurally generated Trace instances improves Qwen2.5-VL macro-average on 24 external visual reasoning benchmarks by 3.51 points at 3B and 4.06 points at 7B.

  2. From Seeing to Thinking: Decoupling Perception and Reasoning Improves Post-Training of Vision-Language Models

    cs.CL 2026-05 conditional novelty 6.0 of 10

    Staged post-training that first solidifies visual perception before visual and textual reasoning improves VLM accuracy and shortens reasoning traces on visual math and perception benchmarks.

  3. DR-MMSearchAgent: Deepening Reasoning in Multimodal Search Agents

    cs.CV 2026-04 unverdicted novelty 6.0 of 10

    DR-MMSearchAgent derives batch-wide trajectory advantages and uses differentiated Gaussian rewards to prevent premature collapse in multimodal agents, outperforming MMSearch-R1 by 8.4% on FVQA-test.

  4. $M^3-Verse$: A "Spot the Difference" Challenge for Large Multimodal Models

    cs.CV 2025-12 conditional novelty 6.0 of 10

    A new benchmark tests whether large multimodal models can compare paired 'before and after' videos to detect scene changes, and finds current models perform near random.

  5. The Landscape of Agentic Reinforcement Learning for LLMs: A Survey

    cs.AI 2025-09 accept novelty 6.0 of 10

    Survey that defines agentic RL for LLMs via POMDPs, introduces a taxonomy of planning/tool-use/memory/reasoning capabilities and domains, and compiles open environments from over 500 papers.

  6. VeriEvol: Scaling Multimodal Mathematical Reasoning via Verifiable Evol-Instruct

    cs.AI 2026-06 unverdicted novelty 5.0 of 10

    VeriEvol decouples prompt difficulty evolution from answer reliability verification to scale verified data for visual math reasoning, lifting benchmark accuracy from 35.42 to 54.73 and adding +3.88 in GRPO RL.

  7. MathReal: We Keep It Real! A Real Scene Benchmark for Evaluating Math Reasoning in Multimodal Large Language Models

    cs.CV 2025-08 unverdicted novelty 5.0 of 10

    A new benchmark of 2,000 K-12 math questions photographed in real scenes finds that multimodal LLMs perform significantly worse on authentic handheld images than on clean benchmarks.

  8. Interpretable Open-Vocabulary Referring Object Detection with Reverse Contrast Attention

    cs.CV 2025-07 reject novelty 5.0 of 10

    A training-free attention reweighting method, Reverse Contrast Attention, is claimed to improve referring object detection in 11 of 15 VLMs, but the custom FitAP metric ranks boxes by IoU with ground truth, which make...

Pith tools