Cover Image

Language as a Latent Variable for Reasoning Optimization

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Wu, Linjuan, Wei, Haoran, Tang, Jialong, Luo, Shuang, Yang, Baosong, Shen, Yongliang, Lu, Weiming
Format:	Preprint
Published:	2026
Subjects:	Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Enhancing LLM Language Adaption through Cross-lingual In-Context Pre-training
by: Wu, Linjuan, et al.
Published: (2025)

TimeToM: Temporal Space is the Key to Unlocking the Door of Large Language Models' Theory-of-Mind
by: Hou, Guiyang, et al.
Published: (2024)

Hierarchical Budget Policy Optimization for Adaptive Reasoning
by: Lyu, Shangke, et al.
Published: (2025)

LAPO: Internalizing Reasoning Efficiency via Length-Adaptive Policy Optimization
by: Wu, Xingyu, et al.
Published: (2025)

Pause or Fabricate? Training Language Models for Grounded Reasoning
by: Qiu, Yiwen, et al.
Published: (2026)

Self-Contrast: Better Reflection Through Inconsistent Solving Perspectives
by: Zhang, Wenqi, et al.
Published: (2024)

CultureSynth: A Hierarchical Taxonomy-Guided and Retrieval-Augmented Framework for Cultural Question-Answer Synthesis
by: Zhang, Xinyu, et al.
Published: (2025)

Active Confusion Expression in Large Language Models: Leveraging World Models toward Better Social Reasoning
by: Du, Jialu, et al.
Published: (2025)

STaR-SQL: Self-Taught Reasoner for Text-to-SQL
by: He, Mingqian, et al.
Published: (2025)

Advancing Process Verification for Large Language Models via Tree-Based Preference Learning
by: He, Mingqian, et al.
Published: (2024)

AskToAct: Enhancing LLMs Tool Use via Self-Correcting Clarification
by: Zhang, Xuan, et al.
Published: (2025)

Not All Languages are Equal: Insights into Multilingual Retrieval-Augmented Generation
by: Wu, Suhang, et al.
Published: (2024)

CultureForest: Understanding and Evaluating Cultural Norm Grounded Reasoning in LLMs
by: Ye, Yangfan, et al.
Published: (2026)

A Data-Efficient Path to Multilingual LLMs: Language Expansion via Post-training PARAM$Δ$ Integration into Upcycled MoE
by: Zhou, Hao, et al.
Published: (2026)

Cooper: Co-Optimizing Policy and Reward Models in Reinforcement Learning for Large Language Models
by: Hong, Haitao, et al.
Published: (2025)

EgoSocialArena: Benchmarking the Social Intelligence of Large Language Models from a First-person Perspective
by: Hou, Guiyang, et al.
Published: (2024)

Locate-and-Focus: Enhancing Terminology Translation in Speech Language Models
by: Wu, Suhang, et al.
Published: (2025)

Meta-Reasoning: Semantics-Symbol Deconstruction for Large Language Models
by: Wang, Yiming, et al.
Published: (2023)

PolyMath: Evaluating Mathematical Reasoning in Multilingual Contexts
by: Wang, Yiming, et al.
Published: (2025)

Insert or Attach: Taxonomy Completion via Box Embedding
by: Xue, Wei, et al.
Published: (2023)

Latent-GRPO: Group Relative Policy Optimization for Latent Reasoning
by: Deng, Jingcheng, et al.
Published: (2026)

SpatialLadder: Progressive Training for Spatial Reasoning in Vision-Language Models
by: Li, Hongxing, et al.
Published: (2025)

Information Re-Organization Improves Reasoning in Large Language Models
by: Cheng, Xiaoxia, et al.
Published: (2024)

Direct Simultaneous Translation Activation for Large Audio-Language Models
by: Zhang, Pei, et al.
Published: (2025)

Agent-Pro: Learning to Evolve via Policy-Level Reflection and Optimization
by: Zhang, Wenqi, et al.
Published: (2024)

A Systematic Assessment of Language Models with Linguistic Minimal Pairs in Chinese
by: Liu, Yikang, et al.
Published: (2024)

Reasoning Beyond Language: A Comprehensive Survey on Latent Chain-of-Thought Reasoning
by: Chen, Xinghao, et al.
Published: (2025)

Scaling Latent Reasoning via Looped Language Models
by: Zhu, Rui-Jie, et al.
Published: (2025)

ClawGUI: A Unified Framework for Training, Evaluating, and Deploying GUI Agents
by: Tang, Fei, et al.
Published: (2026)

Translationese-index: Using Likelihood Ratios for Graded and Generalizable Measurement of Translationese
by: Liu, Yikang, et al.
Published: (2025)

Unveiling Language-Specific Features in Large Language Models via Sparse Autoencoders
by: Deng, Boyi, et al.
Published: (2025)

Stop When Reasoning Converges: Semantic-Preserving Early Exit for Reasoning Models
by: Min, Dehai, et al.
Published: (2026)

Test-Time Reinforcement Learning for GUI Grounding via Region Consistency
by: Du, Yong, et al.
Published: (2025)

Code-A1: Adversarial Evolving of Code LLM and Test LLM via Reinforcement Learning
by: Wang, Aozhe, et al.
Published: (2026)

Data-Copilot: Bridging Billions of Data and Humans with Autonomous Workflow
by: Zhang, Wenqi, et al.
Published: (2023)

LLM Latent Reasoning as Chain of Superposition
by: Deng, Jingcheng, et al.
Published: (2025)

CoT Vectors: Transferring and Probing the Reasoning Mechanisms of LLMs
by: Li, Li, et al.
Published: (2025)

TaskBench: Benchmarking Large Language Models for Task Automation
by: Shen, Yongliang, et al.
Published: (2023)

Latent Thinking Optimization: Your Latent Reasoning Language Model Secretly Encodes Reward Signals in Its Latent Thoughts
by: Du, Hanwen, et al.
Published: (2025)

Judge Like Human Examiners: A Weighted Importance Multi-Point Evaluation Framework for Generative Tasks with Long-form Answers
by: Yu, Guoxin, et al.
Published: (2026)