Cover Image

Do LLMs Encode Functional Importance of Reasoning Tokens?

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Singh, Janvijay, Hakkani-Tür, Dilek
Format:	Preprint
Published:	2026
Subjects:	Computation and Language Artificial Intelligence Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

On the Shelf Life of Fine-Tuned LLM-Judges: Future-Proofing, Backward-Compatibility, and Question Generalization
by: Singh, Janvijay, et al.
Published: (2025)

Neural Networks for Learnable and Scalable Influence Estimation of Instruction Fine-Tuning Data
by: Agarwal, Ishika, et al.
Published: (2025)

Self-Improving LLM Agents at Test-Time
by: Acikgoz, Emre Can, et al.
Published: (2025)

Persuade Me if You Can: A Framework for Evaluating Persuasion Effectiveness and Susceptibility Among Large Language Models
by: Bozdag, Nimet Beyza, et al.
Published: (2025)

MIRAGE: A Benchmark for Multimodal Information-Seeking and Reasoning in Agricultural Expert-Guided Conversations
by: Dongre, Vardhan, et al.
Published: (2025)

AcquisitionSynthesis: Targeted Data Generation using Acquisition Functions
by: Agarwal, Ishika, et al.
Published: (2026)

ToolRL: Reward is All Tool Learning Needs
by: Qian, Cheng, et al.
Published: (2025)

SMART: Self-Aware Agent for Tool Overuse Mitigation
by: Qian, Cheng, et al.
Published: (2025)

Do We Need Adam? Surprisingly Strong and Sparse Reinforcement Learning with SGD in LLMs
by: Mukherjee, Sagnik, et al.
Published: (2026)

Embodied Multi-Agent Coordination by Aligning World Models Through Dialogue
by: Dongre, Vardhan, et al.
Published: (2026)

AURA: A Diagnostic Framework for Tracking User Satisfaction of Interactive Planning Agents
by: Kim, Takyoung, et al.
Published: (2025)

Question Generation for Assessing Early Literacy Reading Comprehension
by: Yang, Xiaocheng, et al.
Published: (2025)

Current Agents Fail to Leverage World Model as Tool for Foresight
by: Qian, Cheng, et al.
Published: (2026)

User Preference Modeling for Conversational LLM Agents: Weak Rewards from Retrieval-Augmented Interaction
by: Hao, Yuren, et al.
Published: (2026)

Simulating User Agents for Embodied Conversational-AI
by: Philipov, Daniel, et al.
Published: (2024)

SIMU: Selective Influence Machine Unlearning
by: Agarwal, Anu, et al.
Published: (2025)

Confidence Estimation for LLM-Based Dialogue State Tracking
by: Sun, Yi-Jyun, et al.
Published: (2024)

Large Language Models as User-Agents for Evaluating Task-Oriented-Dialogue Systems
by: Kazi, Taaha, et al.
Published: (2024)

Variation in Verification: Understanding Verification Dynamics in Large Language Models
by: Zhou, Yefan, et al.
Published: (2025)

TokenButler: Token Importance is Predictable
by: Akhauri, Yash, et al.
Published: (2025)

MOCHA: Are Code Language Models Robust Against Multi-Turn Malicious Coding Prompts?
by: Wahed, Muntasir, et al.
Published: (2025)

MemGuard: Preventing Memory Contamination in Long-Term Memory-Augmented Large Language Models
by: Ha, Hyeonjeong, et al.
Published: (2026)

Sparking Scientific Creativity via LLM-Driven Interdisciplinary Inspiration
by: Kargupta, Priyanka, et al.
Published: (2026)

ReIn: Conversational Error Recovery with Reasoning Inception
by: Kim, Takyoung, et al.
Published: (2026)

ReSpAct: Harmonizing Reasoning, Speaking, and Acting Towards Building Large Language Model-Based Conversational AI Agents
by: Dongre, Vardhan, et al.
Published: (2024)

Goal Alignment in LLM-Based User Simulators for Conversational AI
by: Mehri, Shuhaib, et al.
Published: (2025)

Do Not Let Low-Probability Tokens Over-Dominate in RL for LLMs
by: Yang, Zhihe, et al.
Published: (2025)

When Attention Closes: How LLMs Lose the Thread in Multi-Turn Interaction
by: Dongre, Vardhan, et al.
Published: (2026)

Aligning LLMs with Individual Preferences via Interaction
by: Wu, Shujin, et al.
Published: (2024)

Understanding Token Probability Encoding in Output Embeddings
by: Cho, Hakaze, et al.
Published: (2024)

How Likely Do LLMs with CoT Mimic Human Reasoning?
by: Bao, Guangsheng, et al.
Published: (2024)

Unsupervised Human Preference Learning
by: Shashidhar, Sumuk, et al.
Published: (2024)

TD-EVAL: Revisiting Task-Oriented Dialogue Evaluation by Combining Turn-Level Precision with Dialogue-Level Comparisons
by: Acikgoz, Emre Can, et al.
Published: (2025)

Learning to Reason with Mixture of Tokens
by: Jain, Adit, et al.
Published: (2025)

YourBench: Easy Custom Evaluation Sets for Everyone
by: Shashidhar, Sumuk, et al.
Published: (2025)

Parity-Aware Byte-Pair Encoding: Improving Cross-lingual Fairness in Tokenization
by: Foroutan, Negar, et al.
Published: (2025)

Learning to Route LLMs with Confidence Tokens
by: Chuang, Yu-Neng, et al.
Published: (2024)

Exposing the Achilles' Heel: Evaluating LLMs Ability to Handle Mistakes in Mathematical Reasoning
by: Singh, Joykirat, et al.
Published: (2024)

SpeakRL: Synergizing Reasoning, Speaking, and Acting in Language Models with Reinforcement Learning
by: Acikgoz, Emre Can, et al.
Published: (2025)

When Do LLMs Reason? A Dynamical Systems View via Entropy Phase Transitions
by: Xia, Wei, et al.
Published: (2026)