Cover Image

Thinking by Doing: Building Efficient World Model Reasoning in LLMs via Multi-turn Interaction

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Shu, Bao, Cai, Yan, Sun, Jianjian, Han, Chunrui, Yu, En, Zhao, Liang, Hu, Jingcheng, Zhang, Yinmin, Lv, Haoran, Peng, Yuang, Ge, Zheng, Zhang, Xiangyu, Jiang, Daxin, Yue, Xiangyu
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

Open Vision Reasoner: Transferring Linguistic Cognitive Behavior for Visual Reasoning
by: Wei, Yana, et al.
Published: (2025)

Open-Reasoner-Zero: An Open Source Approach to Scaling Up Reinforcement Learning on the Base Model
by: Hu, Jingcheng, et al.
Published: (2025)

Perception-R1: Pioneering Perception Policy with Reinforcement Learning
by: Yu, En, et al.
Published: (2025)

Small Language Model Meets with Reinforced Vision Vocabulary
by: Wei, Haoran, et al.
Published: (2024)

Exploring Recurrent Long-term Temporal Fusion for Multi-view 3D Perception
by: Han, Chunrui, et al.
Published: (2023)

Multi-matrix Factorization Attention
by: Hu, Jingcheng, et al.
Published: (2024)

OneChart: Purify the Chart Structural Extraction via One Auxiliary Token
by: Chen, Jinyue, et al.
Published: (2024)

General OCR Theory: Towards OCR-2.0 via a Unified End-to-end Model
by: Wei, Haoran, et al.
Published: (2024)

Slow Perception: Let's Perceive Geometric Figures Step-by-step
by: Wei, Haoran, et al.
Published: (2024)

Do LLMs Build World Models From Text? A Multilingual Diagnostic of Spatial Reasoning
by: Pan, Zhikai, et al.
Published: (2026)

Focus Anywhere for Fine-grained Multi-page Document Understanding
by: Liu, Chenglong, et al.
Published: (2024)

Foot-In-The-Door: A Multi-turn Jailbreak for LLMs
by: Weng, Zixuan, et al.
Published: (2025)

Perception in Reflection
by: Wei, Yana, et al.
Published: (2025)

DreamLLM: Synergistic Multimodal Comprehension and Creation
by: Dong, Runpei, et al.
Published: (2023)

DGAE: Diffusion-Guided Autoencoder for Efficient Latent Representation Learning
by: Liu, Dongxu, et al.
Published: (2025)

DistTrain: Addressing Model and Data Heterogeneity with Disaggregated Training for Multimodal Large Language Models
by: Zhang, Zili, et al.
Published: (2024)

DreamBench++: A Human-Aligned Benchmark for Personalized Image Generation
by: Peng, Yuang, et al.
Published: (2024)

PRIME: A Process-Outcome Alignment Benchmark for Verifiable Reasoning in Mathematics and Engineering
by: Wang, Xiangfeng, et al.
Published: (2026)

PerPO: Perceptual Preference Optimization via Discriminative Rewarding
by: Zhu, Zining, et al.
Published: (2025)

PaCoRe: Learning to Scale Test-Time Compute with Parallel Coordinated Reasoning
by: Hu, Jingcheng, et al.
Published: (2026)

M-DocSum: Do LVLMs Genuinely Comprehend Interleaved Image-Text in Document Summarization?
by: Yan, Haolong, et al.
Published: (2025)

How Likely Do LLMs with CoT Mimic Human Reasoning?
by: Bao, Guangsheng, et al.
Published: (2024)

SophiaVL-R1: Reinforcing MLLMs Reasoning with Thinking Reward
by: Fan, Kaixuan, et al.
Published: (2025)

Unhackable Temporal Rewarding for Scalable Video MLLMs
by: Yu, En, et al.
Published: (2025)

Multimodal Long Video Modeling Based on Temporal Dynamic Context
by: Hao, Haoran, et al.
Published: (2025)

Deep But Reliable: Advancing Multi-turn Reasoning for Thinking with Images
by: Yang, Wenhao, et al.
Published: (2025)

ThinkEdit: Interpretable Weight Editing to Mitigate Overly Short Thinking in Reasoning Models
by: Sun, Chung-En, et al.
Published: (2025)

Mind-Paced Speaking: A Dual-Brain Approach to Real-Time Reasoning in Spoken Language Models
by: Wu, Donghang, et al.
Published: (2025)

Merlin:Empowering Multimodal LLMs with Foresight Minds
by: Yu, En, et al.
Published: (2023)

An Empirical Study of Reasoning Steps in Thinking Code LLMs
by: Xue, Haoran, et al.
Published: (2025)

WebVR: Benchmarking Multimodal LLMs for WebPage Recreation from Videos via Human-Aligned Visual Rubrics
by: Dai, Yuhong, et al.
Published: (2026)

GeoArena: Evaluating Open-World Geographic Reasoning in Large Vision-Language Models
by: Jia, Pengyue, et al.
Published: (2025)

DialogueReason: Rule-Based RL Sparks Dialogue Reasoning in LLMs
by: Shu, Yubo, et al.
Published: (2025)

Thinking vs. Doing: Agents that Reason by Scaling Test-Time Interaction
by: Shen, Junhong, et al.
Published: (2025)

CCSPNet-Joint: Efficient Joint Training Method for Traffic Sign Detection Under Extreme Conditions
by: Hong, Haoqin, et al.
Published: (2023)

Improving Latent Reasoning in LLMs via Soft Concept Mixing
by: Wang, Kang, et al.
Published: (2025)

Confidence Estimation for LLMs in Multi-turn Interactions
by: Zhang, Caiqi, et al.
Published: (2026)

ShapeLLM: Universal 3D Object Understanding for Embodied Interaction
by: Qi, Zekun, et al.
Published: (2024)

When LLMs Copy to Think: Uncovering Copy-Guided Attacks in Reasoning LLMs
by: Li, Yue, et al.
Published: (2025)

R-Align: Enhancing Generative Reward Models through Rationale-Centric Meta-Judging
by: Lai, Yanlin, et al.
Published: (2026)