Cover Image

Taming the Thinker: Conditional Entropy Shaping for Adaptive LLM Reasoning

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Wei, Shuyu, Sun, Jian, Qiu, Delai, Wang, Yining, Liu, Shengping, Liang, Jiaen, Fu, Ying, Huang, Wei, Sang, Jitao
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

Zipper-LoRA: Dynamic Parameter Decoupling for Speech-LLM based Multilingual Speech Recognition
by: Mei, Yuxiang, et al.
Published: (2026)

LaTER: Efficient Test-Time Reasoning via Latent Exploration and Explicit Verification
by: Li, Xuan, et al.
Published: (2026)

Investigating and Enhancing Vision-Audio Capability in Omnimodal Large Language Models
by: Hu, Rui, et al.
Published: (2025)

VAPO: End-to-end Slide-Enhanced Speech Recognition with Omni-modal Large Language Models
by: Hu, Rui, et al.
Published: (2025)

How Much Can RAG Help the Reasoning of LLM?
by: Liu, Jingyu, et al.
Published: (2024)

ASP2LJ : An Adversarial Self-Play Laywer Augmented Legal Judgment Framework
by: Chang, Ao, et al.
Published: (2025)

Semantic Pivots Enable Cross-Lingual Transfer in Large Language Models
by: He, Kaiyu, et al.
Published: (2025)

Transparentize the Internal and External Knowledge Utilization in LLMs with Trustworthy Citation
by: Shen, Jiajun, et al.
Published: (2025)

Self-Guided Defense: Adaptive Safety Alignment for Reasoning Models via Synthesized Guidelines
by: Wang, Yuhang, et al.
Published: (2025)

SituatedThinker: Grounding LLM Reasoning with Real-World through Situated Thinking
by: Liu, Junnan, et al.
Published: (2025)

CDEval: A Benchmark for Measuring the Cultural Dimensions of Large Language Models
by: Wang, Yuhang, et al.
Published: (2023)

Improving Weak-to-Strong Generalization with Scalable Oversight and Ensemble Learning
by: Sang, Jitao, et al.
Published: (2024)

Parser-Oriented Structural Refinement for a Stable Layout Interface in Document Parsing
by: Liu, Fuyuan, et al.
Published: (2026)

PARL: Position-Aware Relation Learning Network for Document Layout Analysis
by: Liu, Fuyuan, et al.
Published: (2026)

FocalOrder: Focal Preference Optimization for Reading Order Detection
by: Liu, Fuyuan, et al.
Published: (2026)

GeneralThinker: Domain-General Reasoning through Likelihood-Guided Answer-Conditioned Optimization
by: Piao, Shengmin, et al.
Published: (2026)

Mind with Eyes: from Language Reasoning to Multimodal Reasoning
by: Lin, Zhiyu, et al.
Published: (2025)

ARES: Multimodal Adaptive Reasoning via Difficulty-Aware Token-Level Entropy Shaping
by: Chen, Shuang, et al.
Published: (2025)

KAG-Thinker: Interactive Thinking and Deep Reasoning in LLMs via Knowledge-Augmented Generation
by: Zhang, Dalong, et al.
Published: (2025)

Positional Failures in Long-Context LLMs: A Blind Spot in Reasoning Benchmarks
by: Zhang, Chuyifei, et al.
Published: (2026)

BayesRAG: Probabilistic Mutual Evidence Corroboration for Multimodal Retrieval-Augmented Generation
by: Li, Xuan, et al.
Published: (2026)

Learn to Reason Efficiently with Adaptive Length-based Reward Shaping
by: Liu, Wei, et al.
Published: (2025)

Bridging the gap: A comparative exploration of Speech-LLM and end-to-end architecture for multilingual conversational ASR
by: Mei, Yuxiang, et al.
Published: (2026)

LightThinker++: From Reasoning Compression to Memory Management
by: Zhu, Yuqi, et al.
Published: (2026)

Reasoning with Exploration: An Entropy Perspective
by: Cheng, Daixuan, et al.
Published: (2025)

SmartThinker: Learning to Compress and Preserve Reasoning by Step-Level Length Control
by: He, Xingyang, et al.
Published: (2025)

Mitigating Overthinking through Reasoning Shaping
by: Song, Feifan, et al.
Published: (2025)

TypedThinker: Diversify Large Language Model Reasoning with Typed Thinking
by: Wang, Danqing, et al.
Published: (2024)

Tackling the Inherent Difficulty of Noise Filtering in RAG
by: Liu, Jingyu, et al.
Published: (2026)

Revisiting Entropy in Reinforcement Learning for Large Reasoning Models
by: Jin, Renren, et al.
Published: (2025)

Leaky Thoughts: Large Reasoning Models Are Not Private Thinkers
by: Green, Tommaso, et al.
Published: (2025)

The Markovian Thinker: Architecture-Agnostic Linear Scaling of Reasoning
by: Aghajohari, Milad, et al.
Published: (2025)

ChartThinker: A Contextual Chain-of-Thought Approach to Optimized Chart Summarization
by: Liu, Mengsha, et al.
Published: (2024)

C2F-Thinker: Coarse-to-Fine Reasoning with Hint-Guided Reinforcement Learning for Multimodal Sentiment Analysis
by: Luo, Miaosen, et al.
Published: (2026)

Adaptive Termination for Multi-round Parallel Reasoning: An Universal Semantic Entropy-Guided Framework
by: Xu, Zenan, et al.
Published: (2025)

SpiralThinker: Latent Reasoning through an Iterative Process with Text-Latent Interleaving
by: Piao, Shengmin, et al.
Published: (2025)

Optimizing Multi-Hop Document Retrieval Through Intermediate Representations
by: Lin, Jiaen, et al.
Published: (2025)

How Reliable is Multilingual LLM-as-a-Judge?
by: Fu, Xiyan, et al.
Published: (2025)

Stop When Enough: Adaptive Early-Stopping for Chain-of-Thought Reasoning
by: Sun, Renliang, et al.
Published: (2025)

Reasoning Shapes Alignment: Investigating Cultural Alignment in Large Reasoning Models with Cultural Norms
by: Wang, Yuhang, et al.
Published: (2025)