Imagen de Portada

Rectifying LLM Thought from Lens of Optimization

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Liu, Junnan, Liu, Hongwei, Zhang, Songyang, Chen, Kai
Formato:	Preprint
Publicado:	2025
Materias:	Computation and Language Artificial Intelligence
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Deciphering Trajectory-Aided LLM Reasoning: An Optimization Perspective
por: Liu, Junnan, et al.
Publicado: (2025)

Are Your LLMs Capable of Stable Reasoning?
por: Liu, Junnan, et al.
Publicado: (2024)

Dissecting Tool-Integrated Reasoning: An Empirical Study and Analysis
por: Zhao, Yufeng, et al.
Publicado: (2025)

CompassVerifier: A Unified and Robust Verifier for LLMs Evaluation and Outcome Reward
por: Liu, Shudong, et al.
Publicado: (2025)

Coding Triangle: How Does Large Language Model Understand Code?
por: Zhang, Taolin, et al.
Publicado: (2025)

CompassJudger-1: All-in-one Judge Model Helps Model Evaluation and Evolution
por: Cao, Maosong, et al.
Publicado: (2024)

Condor: Enhance LLM Alignment with Knowledge-Driven Data Synthesis and Refinement
por: Cao, Maosong, et al.
Publicado: (2025)

Forest-of-Thought: Scaling Test-Time Compute for Enhancing LLM Reasoning
por: Bi, Zhenni, et al.
Publicado: (2024)

CompassJudger-2: Towards Generalist Judge Model via Verifiable Rewards
por: Zhang, Taolin, et al.
Publicado: (2025)

The Emergence of Abstract Thought in Large Language Models Beyond Any Language
por: Chen, Yuxin, et al.
Publicado: (2025)

Thoughts-as-Planning: Latent World Models for Chain-of-Thoughts Optimization via Reinforcement Planning
por: Liu, Dong, et al.
Publicado: (2026)

Ada-LEval: Evaluating long-context LLMs with length-adaptable benchmarks
por: Wang, Chonghua, et al.
Publicado: (2024)

HalluLens: LLM Hallucination Benchmark
por: Bang, Yejin, et al.
Publicado: (2025)

Mousse: Rectifying the Geometry of Muon with Curvature-Aware Preconditioning
por: Zhang, Yechen, et al.
Publicado: (2026)

AgentDropoutV2: Optimizing Information Flow in Multi-Agent Systems via Test-Time Rectify-or-Reject Pruning
por: Wang, Yutong, et al.
Publicado: (2026)

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

Upfront Chain-of-Thought: A Cooperative Framework for Chain-of-Thought Compression
por: Li, Chengzhengxu, et al.
Publicado: (2025)

The Molecular Structure of Thought: Mapping the Topology of Long Chain-of-Thought Reasoning
por: Chen, Qiguang, et al.
Publicado: (2026)

Fractured Chain-of-Thought Reasoning
por: Liao, Baohao, et al.
Publicado: (2025)

Is Chain-of-Thought Reasoning of LLMs a Mirage? A Data Distribution Lens
por: Zhao, Chengshuai, et al.
Publicado: (2025)

Scalable Chain of Thoughts via Elastic Reasoning
por: Xu, Yuhui, et al.
Publicado: (2025)

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

AIPO: Learning to Reason from Active Interaction
por: Liu, Junnan, et al.
Publicado: (2026)

CultureScope: A Dimensional Lens for Probing Cultural Understanding in LLMs
por: Zhang, Jinghao, et al.
Publicado: (2025)

Graphs of Research: Citation Evolution Graphs as Supervision for Research Idea Generation
por: Gao, Songyang, et al.
Publicado: (2026)

GTA: A Benchmark for General Tool Agents
por: Wang, Jize, et al.
Publicado: (2024)

Smooth Reading: Bridging the Gap of Recurrent LLM to Self-Attention LLM on Long-Context Tasks
por: Liu, Kai, et al.
Publicado: (2025)

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

Knowledge-Infused Legal Wisdom: Navigating LLM Consultation through the Lens of Diagnostics and Positive-Unlabeled Reinforcement Learning
por: Wu, Yang, et al.
Publicado: (2024)

Learning Composable Chains-of-Thought
por: Yin, Fangcong, 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)

Mixture of insighTful Experts (MoTE): The Synergy of Thought Chains and Expert Mixtures in Self-Alignment
por: Liu, Zhili, et al.
Publicado: (2024)

JE-IRT: A Geometric Lens on LLM Abilities through Joint Embedding Item Response Theory
por: Yao, Louie Hong, et al.
Publicado: (2025)

Next-Generation Database Interfaces: A Survey of LLM-based Text-to-SQL
por: Hong, Zijin, et al.
Publicado: (2024)

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

Language Rectified Flow: Advancing Diffusion Language Generation with Probabilistic Flows
por: Zhang, Shujian, et al.
Publicado: (2024)

MTMT: Consolidating Multiple Thinking Modes to Form a Thought Tree for Strengthening LLM
por: Li, Changcheng, et al.
Publicado: (2024)

Rectifying Demonstration Shortcut in In-Context Learning
por: Jang, Joonwon, et al.
Publicado: (2024)

Trustworthy Reasoning: Evaluating and Enhancing Factual Accuracy in LLM Intermediate Thought Processes
por: Jiao, Rui, et al.
Publicado: (2025)

Thought-Augmented Planning for LLM-Powered Interactive Recommender Agent
por: Yu, Haocheng, et al.
Publicado: (2025)