Cover Image

Credit Where It is Due: Cross-Modality Connectivity Drives Precise Reinforcement Learning for MLLM Reasoning

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Jiao, Zhengbo, Wang, Shaobo, Zhang, Zifan, Wang, Wei, Zhao, Bing, Wei, Hu, Zhang, Linfeng
Format:	Preprint
Published:	2026
Subjects:	Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Socratic-Geo: Synthetic Data Generation and Geometric Reasoning via Multi-Agent Interaction
by: Jiao, Zhengbo, et al.
Published: (2026)

Agentic Proposing: Enhancing Large Language Model Reasoning via Compositional Skill Synthesis
by: Jiao, Zhengbo, et al.
Published: (2026)

Policy of Thoughts: Scaling LLM Reasoning via Test-time Policy Evolution
by: Jiao, Zhengbo, et al.
Published: (2026)

Cross-Modal Distillation For Widely Differing Modalities
by: Zhao, Cairong, et al.
Published: (2025)

Socratic-Zero : Bootstrapping Reasoning via Data-Free Agent Co-evolution
by: Wang, Shaobo, et al.
Published: (2025)

Reasoning or Memorization? Unreliable Results of Reinforcement Learning Due to Data Contamination
by: Wu, Mingqi, et al.
Published: (2025)

CircuitSeer: Mining High-Quality Data by Probing Mathematical Reasoning Circuits in LLMs
by: Wang, Shaobo, et al.
Published: (2025)

IndustryCode: A Benchmark for Industry Code Generation
by: Zeng, Puyu, et al.
Published: (2026)

Sce2DriveX: A Generalized MLLM Framework for Scene-to-Drive Learning
by: Zhao, Rui, et al.
Published: (2025)

Benchmarking MLLM-based Web Understanding: Reasoning, Robustness and Safety
by: Liu, Junliang, et al.
Published: (2025)

MedReasoner: Reinforcement Learning Drives Reasoning Grounding from Clinical Thought to Pixel-Level Precision
by: Yan, Zhonghao, et al.
Published: (2025)

Discovering Process-Outcome Credit in Multi-Step LLM Reasoning
by: Wang, Xiangwei, et al.
Published: (2026)

Reinforced MLLM: A Survey on RL-Based Reasoning in Multimodal Large Language Models
by: Zhou, Guanghao, et al.
Published: (2025)

When Safe Unimodal Inputs Collide: Optimizing Reasoning Chains for Cross-Modal Safety in Multimodal Large Language Models
by: Cai, Wei, et al.
Published: (2025)

ESearch-R1: Learning Cost-Aware MLLM Agents for Interactive Embodied Search via Reinforcement Learning
by: Zhou, Weijie, et al.
Published: (2025)

Medical MLLM is Vulnerable: Cross-Modality Jailbreak and Mismatched Attacks on Medical Multimodal Large Language Models
by: Huang, Xijie, et al.
Published: (2024)

ThinkDrive: Chain-of-Thought Guided Progressive Reinforcement Learning Fine-Tuning for Autonomous Driving
by: Zhao, Chang, et al.
Published: (2026)

TRACER: Turn-level Regret Matching with Inner Reinforcement Credit for Cooperative Multi-LLM Reasoning
by: Li, Chusen, et al.
Published: (2026)

GPG: A Simple and Strong Reinforcement Learning Baseline for Model Reasoning
by: Chu, Xiangxiang, et al.
Published: (2025)

DRAFT-RL: Multi-Agent Chain-of-Draft Reasoning for Reinforcement Learning-Enhanced LLMs
by: Li, Yuanhao, et al.
Published: (2025)

Learning to Model Diverse Driving Behaviors in Highly Interactive Autonomous Driving Scenarios with Multi-Agent Reinforcement Learning
by: Weiwei, Liu, et al.
Published: (2024)

From Reasoning Chains to Verifiable Subproblems: Curriculum Reinforcement Learning Enables Credit Assignment for LLM Reasoning
by: Jiang, Xitai, et al.
Published: (2026)

Tempo-R0: A Video-MLLM for Temporal Video Grounding through Efficient Temporal Sensing Reinforcement Learning
by: Yue, Feng, et al.
Published: (2025)

EGL-SCA: Structural Credit Assignment for Co-Evolving Instructions and Tools in Graph Reasoning Agents
by: Yuan, Zike, et al.
Published: (2026)

AMR-SD: Asymmetric Meta-Reflective Self-Distillation for Token-Level Credit Assignment
by: Wei, Zhenlin, et al.
Published: (2026)

GlyphBanana: Advancing Precise Text Rendering Through Agentic Workflows
by: Yan, Zexuan, et al.
Published: (2026)

EFRame: Deeper Reasoning via Exploration-Filter-Replay Reinforcement Learning Framework
by: Wang, Chen, et al.
Published: (2025)

Rethinking the Sampling Criteria in Reinforcement Learning for LLM Reasoning: A Competence-Difficulty Alignment Perspective
by: Kong, Deyang, et al.
Published: (2025)

Multi-level Advantage Credit Assignment for Cooperative Multi-Agent Reinforcement Learning
by: Zhao, Xutong, et al.
Published: (2025)

Connect, Collapse, Corrupt: Learning Cross-Modal Tasks with Uni-Modal Data
by: Zhang, Yuhui, et al.
Published: (2024)

Well Begun, Half Done: Reinforcement Learning with Prefix Optimization for LLM Reasoning
by: Sun, Yiliu, et al.
Published: (2025)

SynGR: Unleashing the Potential of Cross-Modal Synergy for Generative Recommendation
by: Chen, Wei, et al.
Published: (2026)

GoT-R1: Unleashing Reasoning Capability of MLLM for Visual Generation with Reinforcement Learning
by: Duan, Chengqi, et al.
Published: (2025)

dLLM-Cache: Accelerating Diffusion Large Language Models with Adaptive Caching
by: Liu, Zhiyuan, et al.
Published: (2025)

Sparse Threats, Focused Defense: Criticality-Aware Robust Reinforcement Learning for Safe Autonomous Driving
by: Wei, Qi, et al.
Published: (2026)

PiCA: Pivot-Based Credit Assignment for Search Agentic Reinforcement Learning
by: Liu, Dongyi, et al.
Published: (2026)

GeoRef: Referring Expressions in Geometry via Task Formulation, Synthetic Supervision, and Reinforced MLLM-based Solutions
by: Liu, Bing, et al.
Published: (2025)

From Intuition to Investigation: A Tool-Augmented Reasoning MLLM Framework for Generalizable Face Anti-Spoofing
by: Zhang, Haoyuan, et al.
Published: (2026)

Exact Is Easier: Credit Assignment for Cooperative LLM Agents
by: Chen, Yanjun, et al.
Published: (2026)

UNSEEN: Enhancing Dataset Pruning from a Generalization Perspective
by: Xu, Furui, et al.
Published: (2025)