Imagen de Portada

Done Is Better than Perfect: Unlocking Efficient Reasoning by Structured Multi-Turn Decomposition

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Zeng, Zihao, Huang, Xuyao, Li, Boxiu, Zhang, Hao, Deng, Zhijie
Formato:	Preprint
Publicado:	2025
Materias:	Artificial Intelligence
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

SIFT: Grounding LLM Reasoning in Contexts via Stickers
por: Zeng, Zihao, et al.
Publicado: (2025)

TPS-Bench: Evaluating AI Agents' Tool Planning \& Scheduling Abilities in Compounding Tasks
por: Xu, Hanwen, et al.
Publicado: (2025)

RealSafe-R1: Safety-Aligned DeepSeek-R1 without Compromising Reasoning Capability
por: Zhang, Yichi, et al.
Publicado: (2025)

AdaMoE: Token-Adaptive Routing with Null Experts for Mixture-of-Experts Language Models
por: Zeng, Zihao, et al.
Publicado: (2024)

DIANOIA: Diagnostic Decomposition and Joint Optimization for Multi-Agent Reasoning
por: Yang, Yiming, et al.
Publicado: (2026)

Two Heads are Better than One: Distilling Large Language Model Features Into Small Models with Feature Decomposition and Mixture
por: Fu, Tianhao, et al.
Publicado: (2025)

Not All Thoughts are Generated Equal: Efficient LLM Reasoning via Multi-Turn Reinforcement Learning
por: Ning, Yansong, et al.
Publicado: (2025)

Not All Turns Are Equally Hard: Adaptive Thinking Budgets For Efficient Multi-Turn Reasoning
por: Jali, Neharika, et al.
Publicado: (2026)

ChatAD: Reasoning-Enhanced Time-Series Anomaly Detection with Multi-Turn Instruction Evolution
por: Sun, Hui, et al.
Publicado: (2026)

HES-SQL: Hybrid Reasoning for Efficient Text-to-SQL with Structural Skeleton Guidance
por: Qiu, Suming, et al.
Publicado: (2025)

Anytime Safe PAC Efficient Reasoning
por: Yu, Chengyao, et al.
Publicado: (2026)

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

InterMT: Multi-Turn Interleaved Preference Alignment with Human Feedback
por: Chen, Boyuan, et al.
Publicado: (2025)

The Devil is in the Condition Numbers: Why is GLU Better than non-GLU Structure?
por: Lyu, Xingyu, et al.
Publicado: (2026)

Matrix as Plan: Structured Logical Reasoning with Feedback-Driven Replanning
por: Chen, Ke, et al.
Publicado: (2026)

ShorterBetter: Guiding Reasoning Models to Find Optimal Inference Length for Efficient Reasoning
por: Yi, Jingyang, et al.
Publicado: (2025)

Efficient Detection of LLM-generated Texts with a Bayesian Surrogate Model
por: Miao, Yibo, et al.
Publicado: (2023)

MMCR: Advancing Visual Language Model in Multimodal Multi-Turn Contextual Reasoning
por: Yan, Dawei, et al.
Publicado: (2025)

Visual Generation Unlocks Human-Like Reasoning through Multimodal World Models
por: Wu, Jialong, et al.
Publicado: (2026)

Making Implicit Premises Explicit in Logical Understanding of Enthymemes
por: Feng, Xuyao, et al.
Publicado: (2026)

Batch Speculative Decoding Done Right
por: Zhang, Ranran Haoran, et al.
Publicado: (2025)

TRACER: Turn-level Regret Matching with Inner Reinforcement Credit for Cooperative Multi-LLM Reasoning
por: Li, Chusen, et al.
Publicado: (2026)

RedStar: Does Scaling Long-CoT Data Unlock Better Slow-Reasoning Systems?
por: Xu, Haotian, et al.
Publicado: (2025)

Well Begun, Half Done: Reinforcement Learning with Prefix Optimization for LLM Reasoning
por: Sun, Yiliu, et al.
Publicado: (2025)

MathChat: Benchmarking Mathematical Reasoning and Instruction Following in Multi-Turn Interactions
por: Liang, Zhenwen, et al.
Publicado: (2024)

CA-BERT: Leveraging Context Awareness for Enhanced Multi-Turn Chat Interaction
por: Liu, Minghao, et al.
Publicado: (2024)

GRPO and Reflection Reward for Mathematical Reasoning in Large Language Models
por: Wang, Zhijie
Publicado: (2026)

ST-Raptor: LLM-Powered Semi-Structured Table Question Answering
por: Tang, Zirui, et al.
Publicado: (2025)

TABQAWORLD: Optimizing Multimodal Reasoning for Multi-Turn Table Question Answering
por: Kwok, Tung Sum Thomas, et al.
Publicado: (2026)

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

Dynamic Task Vector Grouping for Efficient Multi-Task Prompt Tuning
por: Zhang, Pieyi, et al.
Publicado: (2025)

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

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

$\textbf{Re}^{2}$: Unlocking LLM Reasoning via Reinforcement Learning with Re-solving
por: Wang, Pinzheng, et al.
Publicado: (2026)

MatryoshkaKV: Adaptive KV Compression via Trainable Orthogonal Projection
por: Lin, Bokai, et al.
Publicado: (2024)

Do Multi-Agents Dream of Electric Screens? Achieving Perfect Accuracy on AndroidWorld Through Task Decomposition
por: Favreau, Pierre-Louis, et al.
Publicado: (2026)

General Modular Harness for LLM Agents in Multi-Turn Gaming Environments
por: Zhang, Yuxuan, et al.
Publicado: (2025)

Identification of Entailment and Contradiction Relations between Natural Language Sentences: A Neurosymbolic Approach
por: Feng, Xuyao, et al.
Publicado: (2024)

Are We Done with MMLU?
por: Gema, Aryo Pradipta, et al.
Publicado: (2024)

Unify Variables in Neural Scaling Laws for General Audio Representations via Embedding Effective Rank
por: Deng, Xuyao, et al.
Publicado: (2025)