Copertina

ParaThinker: Native Parallel Thinking as a New Paradigm to Scale LLM Test-time Compute

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Wen, Hao, Su, Yifan, Zhang, Feifei, Liu, Yunxin, Liu, Yunhao, Zhang, Ya-Qin, Li, Yuanchun
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Computation and Language Artificial Intelligence
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

BudgetThinker: Empowering Budget-aware LLM Reasoning with Control Tokens
di: Wen, Hao, et al.
Pubblicazione: (2025)

AutoDroid: LLM-powered Task Automation in Android
di: Wen, Hao, et al.
Pubblicazione: (2023)

A First Look At Efficient And Secure On-Device LLM Inference Against KV Leakage
di: Yang, Huan, et al.
Pubblicazione: (2024)

Scaling Test-time Compute for LLM Agents
di: Zhu, King, et al.
Pubblicazione: (2025)

ChainStream: An LLM-based Framework for Unified Synthetic Sensing
di: Liu, Jiacheng, et al.
Pubblicazione: (2024)

LLM-Explorer: Towards Efficient and Affordable LLM-based Exploration for Mobile Apps
di: Zhao, Shanhui, et al.
Pubblicazione: (2025)

SituatedThinker: Grounding LLM Reasoning with Real-World through Situated Thinking
di: Liu, Junnan, et al.
Pubblicazione: (2025)

LightThinker: Thinking Step-by-Step Compression
di: Zhang, Jintian, et al.
Pubblicazione: (2025)

V-Thinker: Interactive Thinking with Images
di: Qiao, Runqi, et al.
Pubblicazione: (2025)

When More Thinking Hurts: Overthinking in LLM Test-Time Compute Scaling
di: Zhou, Shu, et al.
Pubblicazione: (2026)

VLA-Thinker: Boosting Vision-Language-Action Models through Thinking-with-Image Reasoning
di: Wang, Chaoyang, et al.
Pubblicazione: (2026)

AutoDroid-V2: Boosting SLM-based GUI Agents via Code Generation
di: Wen, Hao, et al.
Pubblicazione: (2024)

VR-Thinker: Boosting Video Reward Models through Thinking-with-Image Reasoning
di: Wang, Qunzhong, et al.
Pubblicazione: (2025)

Thinker: Learning to Think Fast and Slow
di: Chung, Stephen, et al.
Pubblicazione: (2025)

Learning to Think from Multiple Thinkers
di: Joshi, Nirmit, et al.
Pubblicazione: (2026)

SmallThinker: A Family of Efficient Large Language Models Natively Trained for Local Deployment
di: Song, Yixin, et al.
Pubblicazione: (2025)

KVShare: An LLM Service System with Efficient and Effective Multi-Tenant KV Cache Reuse
di: Yang, Huan, et al.
Pubblicazione: (2025)

SSR: Speculative Parallel Scaling Reasoning in Test-time
di: Chu, Yuanlin, et al.
Pubblicazione: (2025)

Towards Thinking-Optimal Scaling of Test-Time Compute for LLM Reasoning
di: Yang, Wenkai, et al.
Pubblicazione: (2025)

Think Twice: Enhancing LLM Reasoning by Scaling Multi-round Test-time Thinking
di: Tian, Xiaoyu, et al.
Pubblicazione: (2025)

An Empirical Study of LLM Reasoning Ability Under Strict Output Length Constraint
di: Sun, Yi, et al.
Pubblicazione: (2025)

New Evaluation Paradigm for Lexical Simplification
di: Qiang, Jipeng, et al.
Pubblicazione: (2025)

Audio-Thinker: Guiding Audio Language Model When and How to Think via Reinforcement Learning
di: Wu, Shu, et al.
Pubblicazione: (2025)

AgentProg: Empowering Long-Horizon GUI Agents with Program-Guided Context Management
di: Tian, Shizuo, et al.
Pubblicazione: (2025)

GraphThinker: Reinforcing Temporally Grounded Video Reasoning with Event Graph Thinking
di: Cheng, Zixu, et al.
Pubblicazione: (2026)

LongVT: Incentivizing "Thinking with Long Videos" via Native Tool Calling
di: Yang, Zuhao, et al.
Pubblicazione: (2025)

Parallel Loop Transformer for Efficient Test-Time Computation Scaling
di: Wu, Bohong, et al.
Pubblicazione: (2025)

Think-J: Learning to Think for Generative LLM-as-a-Judge
di: Huang, Hui, et al.
Pubblicazione: (2025)

FrameThinker: Learning to Think with Long Videos via Multi-Turn Frame Spotlighting
di: He, Zefeng, et al.
Pubblicazione: (2025)

OctoThinker: Mid-training Incentivizes Reinforcement Learning Scaling
di: Wang, Zengzhi, et al.
Pubblicazione: (2025)

Pest-Thinker: Learning to Think and Reason like Entomologists via Reinforcement Learning
di: Li, Xueheng, et al.
Pubblicazione: (2026)

Spin Elasticity:A New Paradigm for Spintronics
di: Gao, Zhong-Chen, et al.
Pubblicazione: (2026)

Compass-Thinker-7B Technical Report
di: Zeng, Anxiang, et al.
Pubblicazione: (2025)

Video-Thinker: Sparking "Thinking with Videos" via Reinforcement Learning
di: Wang, Shijian, et al.
Pubblicazione: (2025)

Adaptive Parallel Monte Carlo Tree Search for Efficient Test-time Compute Scaling
di: Kim, Hongbeen, et al.
Pubblicazione: (2026)

VisRef: Visual Refocusing while Thinking Improves Test-Time Scaling in Multi-Modal Large Reasoning Models
di: Ghosal, Soumya Suvra, et al.
Pubblicazione: (2026)

Vec-LUT: Vector Table Lookup for Parallel Ultra-Low-Bit LLM Inference on Edge Devices
di: Li, Xiangyu, et al.
Pubblicazione: (2025)

Thinking Before You Speak: A Proactive Test-time Scaling Approach
di: Liu, Cong, et al.
Pubblicazione: (2025)

Visual Para-Thinker: Divide-and-Conquer Reasoning for Visual Comprehension
di: Xu, Haoran, et al.
Pubblicazione: (2026)

Diffusion-SAFE: Diffusion-Native Human-to-Robot Driving Handover for Shared Autonomy
di: Fan, Yunxin, et al.
Pubblicazione: (2025)