Pith. sign in

REVIEW 12 cited by

R1-ShareVL: Incentivizing Reasoning Capability of Multimodal Large Language Models via Share-GRPO

Not yet reviewed by Pith; the record is open.

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 2505.16673 v1 pith:JP7CKGEP submitted 2025-05-22 cs.CV cs.AIcs.CL

R1-ShareVL: Incentivizing Reasoning Capability of Multimodal Large Language Models via Share-GRPO

classification cs.CV cs.AIcs.CL
keywords reasoningquestionshare-grpoduringexpandedspacetrajectoriesacross
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

In this work, we aim to incentivize the reasoning ability of Multimodal Large Language Models (MLLMs) via reinforcement learning (RL) and develop an effective approach that mitigates the sparse reward and advantage vanishing issues during RL. To this end, we propose Share-GRPO, a novel RL approach that tackle these issues by exploring and sharing diverse reasoning trajectories over expanded question space. Specifically, Share-GRPO first expands the question space for a given question via data transformation techniques, and then encourages MLLM to effectively explore diverse reasoning trajectories over the expanded question space and shares the discovered reasoning trajectories across the expanded questions during RL. In addition, Share-GRPO also shares reward information during advantage computation, which estimates solution advantages hierarchically across and within question variants, allowing more accurate estimation of relative advantages and improving the stability of policy training. Extensive evaluations over six widely-used reasoning benchmarks showcase the superior performance of our method. Code will be available at https://github.com/HJYao00/R1-ShareVL.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 12 Pith papers

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

  1. Are Tools Always Beneficial? Learning to Invoke Tools Adaptively for Dual-Mode Multimodal LLM Reasoning

    cs.CL 2026-05 conditional novelty 7.0

    AutoTool uses reinforcement learning with dual-mode rewards to train multimodal LLMs to adaptively choose between tool-assisted and text-centric reasoning, yielding accuracy and efficiency gains on V* and POPE benchmarks.

  2. Reflection Anchors for Propagation-Aware Visual Retention in Long-Chain Multimodal Reasoning

    cs.CV 2026-05 unverdicted novelty 7.0

    RAPO uses an information-theoretic lower bound on visual gain to select high-entropy reflection anchors and optimizes a chain-masked KL surrogate, delivering gains over baselines on reasoning benchmarks across LVLM backbones.

  3. R1-VL: Learning to Reason with Multimodal Large Language Models via Step-wise Group Relative Policy Optimization

    cs.AI 2025-03 conditional novelty 7.0

    R1-VL uses StepGRPO with rule-based StepRAR and StepRVR rewards to let MLLMs learn step-by-step reasoning beyond imitation of positive paths.

  4. H-OPD: Confidence Aware Heterogeneous Multi-Teacher Multimodal On-policy Distillation

    cs.CV 2026-07 conditional novelty 6.0

    Token-level confidence arbitration between VL and text teachers during on-policy distillation improves multimodal student reasoning over single-teacher OPD and GRPO.

  5. Are Tools Always Beneficial? Learning to Invoke Tools Adaptively for Dual-Mode Multimodal LLM Reasoning

    cs.CL 2026-05 unverdicted novelty 6.0

    AutoTool uses dual-mode RL to let MLLMs adaptively choose tool use or text-only reasoning, reporting 21.8% accuracy gain on V* and 44.9% efficiency gain on POPE versus baselines.

  6. Reinforcing Multimodal Reasoning Against Visual Degradation

    cs.CV 2026-05 unverdicted novelty 6.0

    ROMA improves MLLM robustness to seen and unseen visual corruptions by +2.3-2.4% over GRPO on seven reasoning benchmarks while matching clean accuracy.

  7. Chart-FR1: Visual Focus-Driven Fine-Grained Reasoning on Dense Charts

    cs.CV 2026-05 unverdicted novelty 6.0

    Chart-FR1 uses Focus-CoT for linking reasoning to visual cues and Focus-GRPO reinforcement learning with efficiency rewards to outperform prior MLLMs on dense chart reasoning tasks.

  8. Co-Evolving Policy Distillation

    cs.LG 2026-04 unverdicted novelty 6.0

    CoPD integrates multiple expert capabilities by running parallel RLVR training with bidirectional online policy distillation among experts, outperforming mixed RLVR and sequential OPD while surpassing domain-specific ...

  9. STRIVE: Structured Spatiotemporal Exploration for Reinforcement Learning in Video Question Answering

    cs.CV 2026-04 unverdicted novelty 6.0

    STRIVE stabilizes RL for video QA by creating spatiotemporal video variants and using importance-aware sampling, yielding consistent gains over baselines on six benchmarks.

  10. Switch-Reasoner: Learn When to Think in Multitask Mixtures via Reinforcement Learning

    cs.CV 2026-07 conditional novelty 5.0

    A GRPO framework that treats thinking as a tool call and uses dual-level regulation so multimodal models learn when to reason versus answer directly.

  11. LASER: A Corrective Lens for LVLMs via Visual Attention Preservation and Sink Suppression

    cs.CV 2026-07 unverdicted novelty 5.0

    LASER uses Visual Grounding Reward and Sink Suppression Reward to preserve visual attention trajectories and suppress sink tokens, reducing visual forgetting in LVLMs.

  12. Consistency as Inductive Bias: Learning Cross-View Invariance for Robust Multimodal Reasoning

    cs.CV 2026-06 unverdicted novelty 4.0

    ConsistRoll enforces cross-view consistency during RLVR training for MLLMs by joint rewards on grouped original and augmented views, yielding robustness gains on math, general, and hallucination benchmarks.