Cover Image

A2R: An Asymmetric Two-Stage Reasoning Framework for Parallel Reasoning

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Wang, Ziqi, Niu, Boye, Li, Zhongli, Meng, Linghui, Liu, Jing, Zheng, Zhi, Xu, Tong, Wu, Hua, Wang, Haifeng, Chen, Enhong
Format:	Preprint
Published:	2025
Subjects:	Artificial Intelligence Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

A Survey on Parallel Reasoning
by: Wang, Ziqi, et al.
Published: (2025)

Generating Event-oriented Attribution for Movies via Two-Stage Prefix-Enhanced Multimodal LLM
by: Lyu, Yuanjie, et al.
Published: (2024)

Native Parallel Reasoner: Reasoning in Parallelism via Self-Distilled Reinforcement Learning
by: Wu, Tong, et al.
Published: (2025)

RM-R1: Reward Modeling as Reasoning
by: Chen, Xiusi, et al.
Published: (2025)

Beyond Two-Stage Training: Cooperative SFT and RL for LLM Reasoning
by: Chen, Liang, et al.
Published: (2025)

Retrieve-Plan-Generation: An Iterative Planning and Answering Framework for Knowledge-Intensive LLM Generation
by: Lyu, Yuanjie, et al.
Published: (2024)

Interpretable Contrastive Monte Carlo Tree Search Reasoning
by: Gao, Zitian, et al.
Published: (2024)

UniMEL: A Unified Framework for Multimodal Entity Linking with Large Language Models
by: Qi, Liu, et al.
Published: (2024)

Character-R1: Enhancing Role-Aware Reasoning in Role-Playing Agents via RLVR
by: Tang, Yihong, et al.
Published: (2026)

Learning How and What to Memorize: Cognition-Inspired Two-Stage Optimization for Evolving Memory
by: Xu, Derong, et al.
Published: (2026)

Legal Mathematical Reasoning with LLMs: Procedural Alignment through Two-Stage Reinforcement Learning
by: Zhang, Kepu, et al.
Published: (2025)

Two-Stage Reasoning-Infused Learning: Improving Classification with LLM-Generated Reasoning
by: Henrichsen, Mads, et al.
Published: (2025)

Dual Knowledge-Enhanced Two-Stage Reasoner for Multimodal Dialog Systems
by: Chen, Xiaolin, et al.
Published: (2025)

Gazal-R1: Achieving State-of-the-Art Medical Reasoning with Parameter-Efficient Two-Stage Training
by: Adly, Ahmed M., et al.
Published: (2025)

Parallel Test-Time Scaling for Latent Reasoning Models
by: You, Runyang, et al.
Published: (2025)

L-MARS: Legal Multi-Agent Workflow with Orchestrated Reasoning and Agentic Search
by: Wang, Ziqi, et al.
Published: (2025)

IE as Cache: Information Extraction Enhanced Agentic Reasoning
by: Lv, Hang, et al.
Published: (2026)

More Edits, More Stable: Understanding the Lifelong Normalization in Sequential Model Editing
by: Ma, Xin, et al.
Published: (2026)

LMM-R1: Empowering 3B LMMs with Strong Reasoning Abilities Through Two-Stage Rule-Based RL
by: Peng, Yingzhe, et al.
Published: (2025)

Learning to Reason Across Parallel Samples for LLM Reasoning
by: Qi, Jianing, et al.
Published: (2025)

What Makes In-context Learning Effective for Mathematical Reasoning: A Theoretical Analysis
by: Liu, Jiayu, et al.
Published: (2024)

Learning to Reason via Mixture-of-Thought for Logical Reasoning
by: Zheng, Tong, et al.
Published: (2025)

Stop When Enough: Adaptive Early-Stopping for Chain-of-Thought Reasoning
by: Sun, Renliang, et al.
Published: (2025)

DuaShepherd: Integrating Stepwise Correctness and Potential Rewards for Mathematical Reasoning
by: Wu, Yuanhao, et al.
Published: (2025)

Parallel-R1: Towards Parallel Thinking via Reinforcement Learning
by: Zheng, Tong, et al.
Published: (2025)

BioRAG: A RAG-LLM Framework for Biological Question Reasoning
by: Wang, Chengrui, et al.
Published: (2024)

$V_1$: Unifying Generation and Self-Verification for Parallel Reasoners
by: Singh, Harman, et al.
Published: (2026)

OpenR: An Open Source Framework for Advanced Reasoning with Large Language Models
by: Wang, Jun, et al.
Published: (2024)

Adaptive Termination for Multi-round Parallel Reasoning: An Universal Semantic Entropy-Guided Framework
by: Xu, Zenan, et al.
Published: (2025)

A Knowledge-Injected Curriculum Pretraining Framework for Question Answering
by: Lin, Xin, et al.
Published: (2024)

From Harm to Help: Turning Reasoning In-Context Demos into Assets for Reasoning LMs
by: Wang, Haonan, et al.
Published: (2025)

Dynamic Thinking-Token Selection for Efficient Reasoning in Large Reasoning Models
by: Guo, Zhenyuan, et al.
Published: (2026)

Brain-Inspired Two-Stage Approach: Enhancing Mathematical Reasoning by Imitating Human Thought Processes
by: Chen, Yezeng, et al.
Published: (2024)

DyFlow: Dynamic Workflow Framework for Agentic Reasoning
by: Wang, Yanbo, et al.
Published: (2025)

What Really Improves Mathematical Reasoning: Structured Reasoning Signals Beyond Pure Code
by: Zhao, Yuze, et al.
Published: (2026)

Benchmarking Large Language Models for Conversational Question Answering in Multi-instructional Documents
by: Wu, Shiwei, et al.
Published: (2024)

Think in Parallel, Answer as One: Logit Averaging for Open-Ended Reasoning
by: Wang, Haonan, et al.
Published: (2025)

SpecSteer: Synergizing Local Context and Global Reasoning for Efficient Personalized Generation
by: Lv, Hang, et al.
Published: (2026)

Fuzzy Reasoning Chain (FRC): An Innovative Reasoning Framework from Fuzziness to Clarity
by: Chen, Ping, et al.
Published: (2025)

In-Context Former: Lightning-fast Compressing Context for Large Language Model
by: Wang, Xiangfeng, et al.
Published: (2024)