Cover Image

LYNX: Learning Dynamic Exits for Confidence-Controlled Reasoning

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Akgül, Ömer Faruk, Kalaycı, Yusuf Hakan, Kannan, Rajgopal, Neiswanger, Willie, Prasanna, Viktor
Format:	Preprint
Published:	2025
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

Rethinking RL for LLM Reasoning: It's Sparse Policy Selection, Not Capability Learning
by: Akgül, Ömer Faruk, et al.
Published: (2026)

Tina: Tiny Reasoning Models via LoRA
by: Wang, Shangshang, et al.
Published: (2025)

Resa: Transparent Reasoning Models via SAEs
by: Wang, Shangshang, et al.
Published: (2025)

Conformal Prediction for Federated Graph Neural Networks with Missing Neighbor Information
by: Akgül, Ömer Faruk, et al.
Published: (2024)

RECIPE-TKG: From Sparse History to Structured Reasoning for LLM-based Temporal Knowledge Graph Completion
by: Akgül, Ömer Faruk, et al.
Published: (2025)

DeLLMa: Decision Making Under Uncertainty with Large Language Models
by: Liu, Ollie, et al.
Published: (2024)

TypeBandit: Type-Level Context Allocation and Reweighting for Effective Attribute Completion in Heterogeneous Graph Neural Networks
by: Wang, Ta-Yang, et al.
Published: (2026)

LLM Unlearning Without an Expert Curated Dataset
by: Zhu, Xiaoyuan, et al.
Published: (2025)

SPARC-RAG: Adaptive Sequential-Parallel Scaling with Context Management for Retrieval-Augmented Generation
by: Yang, Yuxin, et al.
Published: (2026)

HierRouter: Coordinated Routing of Specialized Large Language Models via Reinforcement Learning
by: Gupta, Nikunj, et al.
Published: (2025)

SpecExit: Accelerating Large Reasoning Model via Speculative Exit
by: Yang, Rubing, et al.
Published: (2025)

METAGENE-1: Metagenomic Foundation Model for Pandemic Monitoring
by: Liu, Ollie, et al.
Published: (2025)

TERMINATOR: Learning Optimal Exit Points for Early Stopping in Chain-of-Thought Reasoning
by: Nagle, Alliot, et al.
Published: (2026)

TASER: Temporal Adaptive Sampling for Fast and Accurate Dynamic Graph Representation Learning
by: Deng, Gangda, et al.
Published: (2024)

Dynamic Vocabulary Pruning in Early-Exit LLMs
by: Vincenti, Jort, et al.
Published: (2024)

TIGER-MARL: Enhancing Multi-Agent Reinforcement Learning with Temporal Information through Graph-based Embeddings and Representations
by: Gupta, Nikunj, et al.
Published: (2025)

Early Stopping for Large Reasoning Models via Confidence Dynamics
by: Hosseini, Parsa, et al.
Published: (2026)

Training Diverse Graph Experts for Ensembles: A Systematic Empirical Study
by: Deng, Gangda, et al.
Published: (2025)

Large Language Model Confidence Estimation via Black-Box Access
by: Pedapati, Tejaswini, et al.
Published: (2024)

Estimating LLM Consistency: A User Baseline vs Surrogate Metrics
by: Wu, Xiaoyuan, et al.
Published: (2025)

AI-University: An LLM-based platform for instructional alignment to scientific classrooms
by: Shojaei, Mostafa Faghih, et al.
Published: (2025)

Decoupling Reasoning and Confidence: Resurrecting Calibration in Reinforcement Learning from Verifiable Rewards
by: Ma, Zhengzhao, et al.
Published: (2026)

A Comment On "The Illusion of Thinking": Reframing the Reasoning Cliff as an Agentic Gap
by: Khan, Sheraz, et al.
Published: (2025)

One Jump Is All You Need: Short-Cutting Transformers for Early Exit Prediction with One Jump to Fit All Exit Levels
by: Seshadri, Amrit Diggavi
Published: (2025)

ConCISE: Confidence-guided Compression in Step-by-step Efficient Reasoning
by: Qiao, Ziqing, et al.
Published: (2025)

AdaptiveStep: Automatically Dividing Reasoning Step through Model Confidence
by: Liu, Yuliang, et al.
Published: (2025)

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

What is Your Data Worth to GPT? LLM-Scale Data Valuation with Influence Functions
by: Choe, Sang Keun, et al.
Published: (2024)

Adversarial Training in Low-Label Regimes with Margin-Based Interpolation
by: Ye, Tian, et al.
Published: (2024)

Contextual Feedback Loops: Amplifying Deep Reasoning with Iterative Top-Down Feedback
by: Fein-Ashley, Jacob, et al.
Published: (2024)

CARE-RFT: Confidence-Anchored Reinforcement Finetuning for Reliable Reasoning in Large Language Models
by: Li, Shuozhe, et al.
Published: (2026)

LEAP: Layer-wise Exit-Aware Pretraining for Efficient Transformer Inference
by: Kapadia, Shashank, et al.
Published: (2026)

LayerSkip: Enabling Early Exit Inference and Self-Speculative Decoding
by: Elhoushi, Mostafa, et al.
Published: (2024)

Rule by Rule: Learning with Confidence through Vocabulary Expansion
by: Nössig, Albert, et al.
Published: (2024)

DOTS: Learning to Reason Dynamically in LLMs via Optimal Reasoning Trajectories Search
by: Yue, Murong, et al.
Published: (2024)

Towards Practical Tool Usage for Continually Learning LLMs
by: Huang, Jerry, et al.
Published: (2024)

FACTUAL: A Novel Framework for Contrastive Learning Based Robust SAR Image Classification
by: Wang, Xu, et al.
Published: (2024)

Studying the Effects of Self-Attention on SAR Automatic Target Recognition
by: Fein-Ashley, Jacob, et al.
Published: (2024)

C$^2$GSPG: Confidence-calibrated Group Sequence Policy Gradient towards Self-aware Reasoning
by: Liu, Haotian, et al.
Published: (2025)

Confidence Under the Hood: An Investigation into the Confidence-Probability Alignment in Large Language Models
by: Kumar, Abhishek, et al.
Published: (2024)