Cover Image

Does RLVR Extend Reasoning Boundaries? Investigating Capability Expansion in Vision-Language Models

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Shen, Minghe, Zhi, Zhuo, Liu, Chonghan, Xing, Shuo, Tu, Zhengzhong, Liu, Che
Format:	Preprint
Published:	2025
Subjects:	Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

DINO-R1: Incentivizing Reasoning Capability in Vision Foundation Models
by: Pan, Chenbin, et al.
Published: (2025)

The Debate on RLVR Reasoning Capability Boundary: Shrinkage, Expansion, or Both? A Two-Stage Dynamic View
by: Yao, Xinhao, et al.
Published: (2025)

How Does Controllability Emerge In Language Models During Pretraining?
by: She, Jianshu, et al.
Published: (2025)

Data Mixing Optimization for Supervised Fine-Tuning of Large Language Models
by: Li, Yuan, et al.
Published: (2025)

V2X-UniPool: Unifying Multimodal Perception and Knowledge Reasoning for Autonomous Driving
by: Luo, Xuewen, et al.
Published: (2025)

Edge-Based Multimodal Sensor Data Fusion with Vision Language Models (VLMs) for Real-time Autonomous Vehicle Accident Avoidance
by: Yang, Fengze, et al.
Published: (2025)

NuScenes-SpatialQA: A Spatial Understanding and Reasoning Benchmark for Vision-Language Models in Autonomous Driving
by: Tian, Kexin, et al.
Published: (2025)

Towards Long-window Anchoring in Vision-Language Model Distillation
by: Zhou, Haoyi, et al.
Published: (2025)

Large Language Models' Reasoning Stalls: An Investigation into the Capabilities of Frontier Models
by: McGinness, Lachlan, et al.
Published: (2025)

CAPS: Cascaded Adaptive Pairwise Selection for Efficient Parallel Reasoning
by: Lin, Fangzhou, et al.
Published: (2026)

PathCal: State-Aware Reflection-Marker Calibration for Efficient Reasoning
by: Jiang, Lingyu, et al.
Published: (2026)

MedVLM-R1: Incentivizing Medical Reasoning Capability of Vision-Language Models (VLMs) via Reinforcement Learning
by: Pan, Jiazhen, et al.
Published: (2025)

Does LLM Alignment Really Need Diversity? An Empirical Study of Adapting RLVR Methods for Moral Reasoning
by: Zhang, Zhaowei, et al.
Published: (2026)

Generalization of RLVR Using Causal Reasoning as a Testbed
by: Lu, Brian, et al.
Published: (2025)

Demystifying the Visual Quality Paradox in Multimodal Large Language Models
by: Xing, Shuo, et al.
Published: (2025)

RBF++: Quantifying and Optimizing Reasoning Boundaries across Measurable and Unmeasurable Capabilities for Chain-of-Thought Reasoning
by: Chen, Qiguang, et al.
Published: (2025)

Investigating The Functional Roles of Attention Heads in Vision Language Models: Evidence for Reasoning Modules
by: Jiang, Yanbei, et al.
Published: (2025)

DeepThinkVLA: Enhancing Reasoning Capability of Vision-Language-Action Models
by: Yin, Cheng, et al.
Published: (2025)

Think in Sentences: Explicit Sentence Boundaries Enhance Language Model's Capabilities
by: Liu, Zhichen, et al.
Published: (2026)

T2T-VICL: Unlocking the Boundaries of Cross-Task Visual In-Context Learning via Implicit Text-Driven VLMs
by: Xia, Shao-Jun, et al.
Published: (2025)

DisCO: Reinforcing Large Reasoning Models with Discriminative Constrained Optimization
by: Li, Gang, et al.
Published: (2025)

SeePhys Pro: Diagnosing Modality Transfer and Blind-Training Effects in Multimodal RLVR for Physics Reasoning
by: Xiang, Kun, et al.
Published: (2026)

DRAMA-X: A Fine-grained Intent Prediction and Risk Reasoning Benchmark For Driving
by: Godbole, Mihir, et al.
Published: (2025)

Stop Before You Fail: Operational Capability Boundaries for Mitigating Unproductive Reasoning in Large Reasoning Models
by: Zhang, Qingjie, et al.
Published: (2025)

ReasonAny: Incorporating Reasoning Capability to Any Model via Simple and Effective Model Merging
by: Yang, Junyao, et al.
Published: (2026)

Distilling Mathematical Reasoning Capabilities into Small Language Models
by: Zhu, Xunyu, et al.
Published: (2024)

Trade-offs in Large Reasoning Models: An Empirical Analysis of Deliberative and Adaptive Reasoning over Foundational Capabilities
by: Zhao, Weixiang, et al.
Published: (2025)

Extending RLVR to Open-Ended Tasks via Verifiable Multiple-Choice Reformulation
by: Zhang, Mengyu, et al.
Published: (2025)

Aware First, Think Less: Dynamic Boundary Self-Awareness Drives Extreme Reasoning Efficiency in Large Language Models
by: Chen, Qiguang, et al.
Published: (2025)

Endowing Embodied Agents with Spatial Reasoning Capabilities for Vision-and-Language Navigation
by: Bai, Qianqian, et al.
Published: (2025)

Zero-shot Object Navigation with Vision-Language Models Reasoning
by: Wen, Congcong, et al.
Published: (2024)

ImplicitMemBench: Measuring Unconscious Behavioral Adaptation in Large Language Models
by: Qin, Chonghan, et al.
Published: (2026)

Quantile Advantage Estimation: Stabilizing RLVR for LLM Reasoning
by: Wu, Junkang, et al.
Published: (2025)

On the Direction of RLVR Updates for LLM Reasoning: Identification and Exploitation
by: Huang, Kexin, et al.
Published: (2026)

Geometry of Knowledge Allows Extending Diversity Boundaries of Large Language Models
by: Bystroński, Mateusz, et al.
Published: (2025)

Unlocking Exploration in RLVR: Uncertainty-aware Advantage Shaping for Deeper Reasoning
by: Xie, Can, et al.
Published: (2025)

CAPF: Guiding Search-Agent Rollouts with Credit-Attenuated Privileged Feedback
by: Chen, Bin, et al.
Published: (2026)

Reasoning Depth and Environment Complexity: A Controlled Study of RLVR Data Allocation across Logical Reasoning Tasks
by: Zhu, Yihua, et al.
Published: (2026)

GraphInstruct: Empowering Large Language Models with Graph Understanding and Reasoning Capability
by: Luo, Zihan, et al.
Published: (2024)

AdaRing: Towards Ultra-Light Vision-Language Adaptation via Cross-Layer Tensor Ring Decomposition
by: Huang, Ying, et al.
Published: (2025)