Cover Image

Not All Thoughts are Generated Equal: Efficient LLM Reasoning via Multi-Turn Reinforcement Learning

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Ning, Yansong, Li, Wei, Fang, Jun, Tan, Naiqiang, Liu, Hao
Format:	Preprint
Published:	2025
Subjects:	Computation and Language Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Agent-Omit: Adaptive Context Omission for Efficient LLM Agents
by: Ning, Yansong, et al.
Published: (2026)

DeepTravel: An End-to-End Agentic Reinforcement Learning Framework for Autonomous Travel Planning Agents
by: Ning, Yansong, et al.
Published: (2025)

Satori: Reinforcement Learning with Chain-of-Action-Thought Enhances LLM Reasoning via Autoregressive Search
by: Shen, Maohao, et al.
Published: (2025)

Bag of Tricks for Inference-time Computation of LLM Reasoning
by: Liu, Fan, et al.
Published: (2025)

Adaptive Stopping for Multi-Turn LLM Reasoning
by: Zhou, Xiaofan, et al.
Published: (2026)

SPIRAL: Self-Play on Zero-Sum Games Incentivizes Reasoning via Multi-Agent Multi-Turn Reinforcement Learning
by: Liu, Bo, et al.
Published: (2025)

CARFT: Boosting LLM Reasoning via Contrastive Learning with Annotated Chain-of-Thought-based Reinforced Fine-Tuning
by: Zhu, Wenqiao, et al.
Published: (2025)

Self-Compression of Chain-of-Thought via Multi-Agent Reinforcement Learning
by: Chen, Yiqun, et al.
Published: (2026)

RAGEN: Understanding Self-Evolution in LLM Agents via Multi-Turn Reinforcement Learning
by: Wang, Zihan, et al.
Published: (2025)

Reinforcement Learning for Chain of Thought Compression with One-Domain-to-All Generalization
by: Li, Hanyu, et al.
Published: (2025)

Reason Like a Radiologist: Chain-of-Thought and Reinforcement Learning for Verifiable Report Generation
by: Jing, Peiyuan, et al.
Published: (2025)

VAGEN: Reinforcing World Model Reasoning for Multi-Turn VLM Agents
by: Wang, Kangrui, et al.
Published: (2025)

Focused Chain-of-Thought: Efficient LLM Reasoning via Structured Input Information
by: Struppek, Lukas, et al.
Published: (2025)

Ada-R1: Hybrid-CoT via Bi-Level Adaptive Reasoning Optimization
by: Luo, Haotian, et al.
Published: (2025)

DiMA: An LLM-Powered Ride-Hailing Assistant at DiDi
by: Ning, Yansong, et al.
Published: (2025)

CSRP: Chain-of-Thought Reasoning for Chinese Text Correction via Reinforcement Learning with Efficiency-Aware Rewards
by: Tian, Wei, et al.
Published: (2026)

The Evolution of Thought: Tracking LLM Overthinking via Reasoning Dynamics Analysis
by: Wei, Zihao, et al.
Published: (2025)

AgenticMath: Enhancing LLM Reasoning via Agentic-based Math Data Generation
by: Liu, Xianyang, et al.
Published: (2025)

Offline Reinforcement Learning for LLM Multi-Step Reasoning
by: Wang, Huaijie, et al.
Published: (2024)

Table as Thought: Exploring Structured Thoughts in LLM Reasoning
by: Sun, Zhenjie, et al.
Published: (2025)

PAG: Multi-Turn Reinforced LLM Self-Correction with Policy as Generative Verifier
by: Jiang, Yuhua, et al.
Published: (2025)

InftyThink+: Effective and Efficient Infinite-Horizon Reasoning via Reinforcement Learning
by: Yan, Yuchen, et al.
Published: (2026)

From Intents to Conversations: Generating Intent-Driven Dialogues with Contrastive Learning for Multi-Turn Classification
by: Liu, Junhua, et al.
Published: (2024)

Tracing Thought: Using Chain-of-Thought Reasoning to Identify the LLM Behind AI-Generated Text
by: Agrahari, Shifali, et al.
Published: (2025)

LLM-Driven Multi-Turn Task-Oriented Dialogue Synthesis for Realistic Reasoning
by: Zhu, Yu, et al.
Published: (2026)

Thought Manipulation: External Thought Can Be Efficient for Large Reasoning Models
by: Liu, Yule, et al.
Published: (2025)

Generative Adversarial Reasoner: Enhancing LLM Reasoning with Adversarial Reinforcement Learning
by: Liu, Qihao, et al.
Published: (2025)

Breaking Contextual Inertia: Reinforcement Learning with Single-Turn Anchors for Stable Multi-Turn Interaction
by: Chen, Xingwu, et al.
Published: (2026)

Similarity is Not All You Need: Endowing Retrieval Augmented Generation with Multi Layered Thoughts
by: Gan, Chunjing, et al.
Published: (2024)

Consistently Simulating Human Personas with Multi-Turn Reinforcement Learning
by: Abdulhai, Marwa, et al.
Published: (2025)

Skeleton-of-Thought: Prompting LLMs for Efficient Parallel Generation
by: Ning, Xuefei, et al.
Published: (2023)

ETR: Entropy Trend Reward for Efficient Chain-of-Thought Reasoning
by: Xiong, Xuan, et al.
Published: (2026)

Tool-Star: Empowering LLM-Brained Multi-Tool Reasoner via Reinforcement Learning
by: Dong, Guanting, et al.
Published: (2025)

Not All Experts are Equal: Efficient Expert Pruning and Skipping for Mixture-of-Experts Large Language Models
by: Lu, Xudong, et al.
Published: (2024)

MA-RAG: Multi-Agent Retrieval-Augmented Generation via Collaborative Chain-of-Thought Reasoning
by: Nguyen, Thang, et al.
Published: (2025)

ReasonFlux: Hierarchical LLM Reasoning via Scaling Thought Templates
by: Yang, Ling, et al.
Published: (2025)

Beyond Imitation: Learning Key Reasoning Steps from Dual Chain-of-Thoughts in Reasoning Distillation
by: Dai, Chengwei, et al.
Published: (2024)

Triplet-Structured Knowledge Integration for Multi-Turn Medical Reasoning
by: Meng, Zhaohan, et al.
Published: (2025)

Not All Rollouts are Useful: Down-Sampling Rollouts in LLM Reinforcement Learning
by: Xu, Yixuan Even, et al.
Published: (2025)

Consistency of Large Reasoning Models Under Multi-Turn Attacks
by: Li, Yubo, et al.
Published: (2026)