Image de couverture de livre

Mutual Reasoning Makes Smaller LLMs Stronger Problem-Solvers

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Qi, Zhenting, Ma, Mingyuan, Xu, Jiahang, Zhang, Li Lyna, Yang, Fan, Yang, Mao
Format:	Preprint
Publié:	2024
Sujets:	Computation and Language
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

LongRoPE: Extending LLM Context Window Beyond 2 Million Tokens
par: Ding, Yiran, et autres
Publié: (2024)

rStar-Math: Small LLMs Can Master Math Reasoning with Self-Evolved Deep Thinking
par: Guan, Xinyu, et autres
Publié: (2025)

Fewer is More: Boosting LLM Reasoning with Reinforced Context Pruning
par: Huang, Xijie, et autres
Publié: (2023)

Reverse Thinking Makes LLMs Stronger Reasoners
par: Chen, Justin Chih-Yao, et autres
Publié: (2024)

LoongRL: Reinforcement Learning for Advanced Reasoning over Long Contexts
par: Wang, Siyuan, et autres
Publié: (2025)

Beyond Prompt Content: Enhancing LLM Performance via Content-Format Integrated Prompt Optimization
par: Liu, Yuanye, et autres
Publié: (2025)

rStar-Coder: Scaling Competitive Code Reasoning with a Large-Scale Verified Dataset
par: Liu, Yifei, et autres
Publié: (2025)

When Attention Collapses: How Degenerate Layers in LLMs Enable Smaller, Stronger Models
par: Sanyal, Sunny, et autres
Publié: (2024)

Blar-SQL: Faster, Stronger, Smaller NL2SQL
par: Domínguez, José Manuel, et autres
Publié: (2024)

SAPO: Self-Adaptive Process Optimization Makes Small Reasoners Stronger
par: Chen, Kaiyuan, et autres
Publié: (2026)

DuQuant: Distributing Outliers via Dual Transformation Makes Stronger Quantized LLMs
par: Lin, Haokun, et autres
Publié: (2024)

GReaTer: Gradients over Reasoning Makes Smaller Language Models Strong Prompt Optimizers
par: Das, Sarkar Snigdha Sarathi, et autres
Publié: (2024)

ImpRIF: Stronger Implicit Reasoning Leads to Better Complex Instruction Following
par: Yang, Yuancheng, et autres
Publié: (2026)

It Helps to Take a Second Opinion: Teaching Smaller LLMs to Deliberate Mutually via Selective Rationale Optimisation
par: Patnaik, Sohan, et autres
Publié: (2025)

LongRoPE2: Near-Lossless LLM Context Window Scaling
par: Shang, Ning, et autres
Publié: (2025)

Achieving >97% on GSM8K: Deeply Understanding the Problems Makes LLMs Better Solvers for Math Word Problems
par: Zhong, Qihuang, et autres
Publié: (2024)

rStar2-Agent: Agentic Reasoning Technical Report
par: Shang, Ning, et autres
Publié: (2025)

MathDuels: Evaluating LLMs as Problem Posers and Solvers
par: Xu, Zhiqiu, et autres
Publié: (2026)

LLMEval-Logic: A Solver-Verified Chinese Benchmark for Logical Reasoning of LLMs with Adversarial Hardening
par: Zhang, Ming, et autres
Publié: (2026)

Can LLMs Rank the Harmfulness of Smaller LLMs? We are Not There Yet
par: Atil, Berk, et autres
Publié: (2025)

Mixed Distillation Helps Smaller Language Model Better Reasoning
par: Li, Chenglin, et autres
Publié: (2023)

ElaLoRA: Elastic & Learnable Low-Rank Adaptation for Efficient Model Fine-Tuning
par: Chang, Huandong, et autres
Publié: (2025)

Self-Correction Makes LLMs Better Parsers
par: Zhang, Ziyan, et autres
Publié: (2025)

Prompt Orchestration Markup Language
par: Zhang, Yuge, et autres
Publié: (2025)

GSM-Plus: A Comprehensive Benchmark for Evaluating the Robustness of LLMs as Mathematical Problem Solvers
par: Li, Qintong, et autres
Publié: (2024)

Exploring Performance Contrasts in TableQA: Step-by-Step Reasoning Boosts Bigger Language Models, Limits Smaller Language Models
par: Yang, Haoyan, et autres
Publié: (2024)

Stronger Re-identification Attacks through Reasoning and Aggregation
par: Charpentier, Lucas Georges Gabriel, et autres
Publié: (2025)

Nondeterministic Polynomial-time Problem Challenge: An Ever-Scaling Reasoning Benchmark for LLMs
par: Yang, Chang, et autres
Publié: (2025)

Stronger Models are NOT Stronger Teachers for Instruction Tuning
par: Xu, Zhangchen, et autres
Publié: (2024)

When Less Language is More: Language-Reasoning Disentanglement Makes LLMs Better Multilingual Reasoners
par: Zhao, Weixiang, et autres
Publié: (2025)

A Single Layer to Explain Them All:Understanding Massive Activations in Large Language Models
par: Shi, Zeru, et autres
Publié: (2026)

Solver-Independent Automated Problem Formulation via LLMs for High-Cost Simulation-Driven Design
par: Li, Yuchen, et autres
Publié: (2025)

CoT Vectors: Transferring and Probing the Reasoning Mechanisms of LLMs
par: Li, Li, et autres
Publié: (2025)

Beyond Answers: Transferring Reasoning Capabilities to Smaller LLMs Using Multi-Teacher Knowledge Distillation
par: Tian, Yijun, et autres
Publié: (2024)

Hint Tuning: Less Data Makes Better Reasoners
par: Fan, Siqi, et autres
Publié: (2026)

Catch Me If You Can: How Smaller Reasoning Models Pretend to Reason with Mathematical Fidelity
par: Sahoo, Subramanyam, et autres
Publié: (2025)

What Makes Math Word Problems Challenging for LLMs?
par: Srivatsa, KV Aditya, et autres
Publié: (2024)

Thinking-Free Policy Initialization Makes Distilled Reasoning Models More Effective and Efficient Reasoners
par: Xu, Xin, et autres
Publié: (2025)

Mitigating Forgetting Between Supervised and Reinforcement Learning Yields Stronger Reasoners
par: Yuan, Xiangchi, et autres
Publié: (2025)

Failure Makes the Agent Stronger: Enhancing Accuracy through Structured Reflection for Reliable Tool Interactions
par: Su, Junhao, et autres
Publié: (2025)