Pith. sign in

REVIEW 7 cited by

OThink-MR1: Stimulating multimodal generalized reasoning capabilities via dynamic 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 2503.16081 v2 pith:4UXBUXTT submitted 2025-03-20 cs.LG cs.IR

Zhiyuan Liu , Yuting Zhang , Feng Liu , Changwang Zhang , Ying Sun , Jun Wang This is my paper
classification cs.LGcs.IR
keywords capabilitiesmultimodalgeneralizedgrpo-dreasoninglearningmllmothink-mr1
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Multimodal Large Language Models (MLLMs) have gained significant traction for their ability to process diverse input data types and generate coherent, contextually relevant outputs across various applications. While supervised fine-tuning (SFT) has been the predominant approach to enhance MLLM capabilities in task-specific optimization, it often falls short in fostering crucial generalized reasoning abilities. Although reinforcement learning (RL) holds great promise in overcoming these limitations, it encounters two significant challenges: (1) its generalized capacities in multimodal tasks remain largely unexplored, and (2) its training constraints, including the constant Kullback-Leibler divergence or the clamp strategy, often result in suboptimal bottlenecks. To address these challenges, we propose OThink-MR1, an advanced MLLM equipped with profound comprehension and reasoning capabilities across multimodal tasks. Specifically, we introduce Group Relative Policy Optimization with a dynamic Kullback-Leibler strategy (GRPO-D), which markedly enhances reinforcement learning (RL) performance. For Qwen2-VL-2B-Instruct, GRPO-D achieves a relative improvement of more than 5.72% over SFT and more than 13.59% over GRPO in same-task evaluation on two adapted datasets. Furthermore, GRPO-D demonstrates remarkable cross-task generalization capabilities, with an average relative improvement of more than 61.63% over SFT in cross-task evaluation. These results highlight that the MLLM trained with GRPO-D on one multimodal task can be effectively transferred to another task, underscoring the superior generalized reasoning capabilities of our proposed OThink-MR1 model.

Discussion (0). Sign in to comment.

Forward citations

Cited by 7 Pith papers

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

  1. BVS: Bayesian Visual Search with Multimodal Large Language Model for Fine-grained Perception

    cs.CV 2026-07 conditional novelty 6.0 of 10

    BVS combines early-stop attention rollout priors with a scale-aware non-stationary kernel and GP-UCB to locate tiny objects in UHR images more accurately and with fewer MLLM queries than prior visual-search methods.

  2. VL-Cogito: Progressive Curriculum Reinforcement Learning for Advanced Multimodal Reasoning

    cs.CV 2025-07 conditional novelty 6.0 of 10

    VL-Cogito, trained with progressive curriculum RL, online difficulty weighting, and dynamic length rewards, matches or beats prior reasoning MLLMs on ten multimodal benchmarks.

  3. OCR-Reasoning Benchmark: Unveiling the True Capabilities of MLLMs in Complex Text-Rich Image Reasoning

    cs.LG 2025-05 conditional novelty 6.0 of 10

    OCR-Reasoning, a 1,069-question benchmark with reasoning-chain annotations for text-rich images, finds that no evaluated multimodal model surpasses 50% accuracy.

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

    cs.CV 2025-11 conditional novelty 5.0 of 10

    Fine-tuning Qwen2.5-VL on VisReason, a 489K-example multi-round visual chain-of-thought dataset (165K with pseudo-depth), modestly improves LLM-judged visual reasoning scores, with caveats about self-referential 3D ev...

  5. APO: Enhancing Reasoning Ability of MLLMs via Asymmetric Policy Optimization

    cs.LG 2025-06 conditional novelty 5.0 of 10

    Asymmetric Policy Optimization, with adaptive KL shaping and length regularization for wrong answers, improves reasoning in a 3B multimodal model without hurting general performance.

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

    cs.CV 2025-06 conditional novelty 5.0 of 10

    WeThink, a 120K-image QA dataset with AI-generated reasoning paths, combined with hybrid-reward reinforcement learning, improves a 7B vision-language model across 14 benchmarks.

  7. Reinforcement Fine-Tuning Powers Reasoning Capability of Multimodal Large Language Models

    cs.CL 2025-05 conditional novelty 2.0 of 10

    A survey-style position paper claims that reinforcement fine-tuning powers reasoning in multimodal LLMs, summarizing over a hundred recent works and proposing five future research directions.

Pith tools