CoRE: Enhancing Metacognition with Label-free Self-evaluation in LRMs
Fuente:
arXiv
Saved in:
| Main Authors: | Li, Haoxi, Bai, Sikai, Zhang, Jie, Guo, Song |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Similar Items
TTVS: Boosting Self-Exploring Reinforcement Learning via Test-time Variational Synthesis
by: Bai, Sikai, et al.
Published: (2026)
by: Bai, Sikai, et al.
Published: (2026)
DiEP: Adaptive Mixture-of-Experts Compression through Differentiable Expert Pruning
by: Bai, Sikai, et al.
Published: (2025)
by: Bai, Sikai, et al.
Published: (2025)
From LLMs to LRMs: Rethinking Pruning for Reasoning-Centric Models
by: Ding, Longwei, et al.
Published: (2026)
by: Ding, Longwei, et al.
Published: (2026)
CoRE: Concept-Reasoning Expansion for Continual Brain Lesion Segmentation
by: Chen, Qianqian, et al.
Published: (2026)
by: Chen, Qianqian, et al.
Published: (2026)
BARREL: Boundary-Aware Reasoning for Factual and Reliable LRMs
by: Yang, Junxiao, et al.
Published: (2025)
by: Yang, Junxiao, et al.
Published: (2025)
LNPT: Label-free Network Pruning and Training
by: Xiao, Jinying, et al.
Published: (2024)
by: Xiao, Jinying, et al.
Published: (2024)
DiPrompT: Disentangled Prompt Tuning for Multiple Latent Domain Generalization in Federated Learning
by: Bai, Sikai, et al.
Published: (2024)
by: Bai, Sikai, et al.
Published: (2024)
Black-box Gradient Attack on Graph Neural Networks: Deeper Insights in Graph-based Attack and Defense
by: Zhan, Haoxi, et al.
Published: (2021)
by: Zhan, Haoxi, et al.
Published: (2021)
Enhancing LLM Metacognition via Cognitive Pairwise Training
by: Li, Weitao, et al.
Published: (2026)
by: Li, Weitao, et al.
Published: (2026)
Combating Data Imbalances in Federated Semi-supervised Learning with Dual Regulators
by: Bai, Sikai, et al.
Published: (2023)
by: Bai, Sikai, et al.
Published: (2023)
Your thoughts tell who you are: Characterize the reasoning patterns of LRMs
by: Chen, Yida, et al.
Published: (2025)
by: Chen, Yida, et al.
Published: (2025)
Metis: Learning to Jailbreak LLMs via Self-Evolving Metacognitive Policy Optimization
by: Zhou, Huilin, et al.
Published: (2026)
by: Zhou, Huilin, et al.
Published: (2026)
Rethinking Self-Distillation: Label Averaging and Enhanced Soft Label Refinement with Partial Labels
by: Jeong, Hyeonsu, et al.
Published: (2024)
by: Jeong, Hyeonsu, et al.
Published: (2024)
CoRE: Condition-based Reasoning for Identifying Outcome Variance in Complex Events
by: Vallurupalli, Sai, et al.
Published: (2025)
by: Vallurupalli, Sai, et al.
Published: (2025)
Dictionary-Learning-Based Data Pruning for System Identification
by: Wang, Tingna, et al.
Published: (2025)
by: Wang, Tingna, et al.
Published: (2025)
CoRE: A Fine-Grained Code Reasoning Benchmark Beyond Output Prediction
by: Gao, Jun, et al.
Published: (2026)
by: Gao, Jun, et al.
Published: (2026)
Label-free Monitoring of Self-Supervised Learning Progress
by: Xu, Isaac, et al.
Published: (2024)
by: Xu, Isaac, et al.
Published: (2024)
A Physics Enhanced Residual Learning (PERL) Framework for Vehicle Trajectory Prediction
by: Long, Keke, et al.
Published: (2023)
by: Long, Keke, et al.
Published: (2023)
KV-CoRE: Benchmarking Data-Dependent Low-Rank Compressibility of KV-Caches in LLMs
by: Chen, Jian, et al.
Published: (2026)
by: Chen, Jian, et al.
Published: (2026)
HAIM-DRL: Enhanced Human-in-the-loop Reinforcement Learning for Safe and Efficient Autonomous Driving
by: Huang, Zilin, et al.
Published: (2024)
by: Huang, Zilin, et al.
Published: (2024)
A Phone-based Distributed Ambient Temperature Measurement System with An Efficient Label-free Automated Training Strategy
by: Chen, Dayin, et al.
Published: (2024)
by: Chen, Dayin, et al.
Published: (2024)
LLMs Show No Signs Of Individuated Metacognition
by: Moran, M., et al.
Published: (2026)
by: Moran, M., et al.
Published: (2026)
The Metacognitive Monitoring Battery: A Cross-Domain Benchmark for LLM Self-Monitoring
by: Cacioli, Jon-Paul
Published: (2026)
by: Cacioli, Jon-Paul
Published: (2026)
Training-free Heterogeneous Model Merging
by: Xu, Zhengqi, et al.
Published: (2024)
by: Xu, Zhengqi, et al.
Published: (2024)
When the Loop Closes: Architectural Limits of In-Context Isolation, Metacognitive Co-option, and the Two-Target Design Problem in Human-LLM Systems
by: Cheng, Z., et al.
Published: (2026)
by: Cheng, Z., et al.
Published: (2026)
Not All Data are Good Labels: On the Self-supervised Labeling for Time Series Forecasting
by: Yang, Yuxuan, et al.
Published: (2025)
by: Yang, Yuxuan, et al.
Published: (2025)
Evidence for Limited Metacognition in LLMs
by: Ackerman, Christopher
Published: (2025)
by: Ackerman, Christopher
Published: (2025)
Class-aware and Augmentation-free Contrastive Learning from Label Proportion
by: Wang, Jialiang, et al.
Published: (2024)
by: Wang, Jialiang, et al.
Published: (2024)
Confidence Freeze: Early Success Induces a Metastable Decoupling of Metacognition and Behaviour
by: Zhang, Zhipeng, et al.
Published: (2026)
by: Zhang, Zhipeng, et al.
Published: (2026)
Metacognitive Capabilities of LLMs: An Exploration in Mathematical Problem Solving
by: Didolkar, Aniket, et al.
Published: (2024)
by: Didolkar, Aniket, et al.
Published: (2024)
Parsing the Language of Expression: Enhancing Symbolic Regression with Domain-Aware Symbolic Priors
by: Huang, Sikai, et al.
Published: (2025)
by: Huang, Sikai, et al.
Published: (2025)
Traffic expertise meets residual RL: Knowledge-informed model-based residual reinforcement learning for CAV trajectory control
by: Sheng, Zihao, et al.
Published: (2024)
by: Sheng, Zihao, et al.
Published: (2024)
Meta-TTRL: A Metacognitive Framework for Self-Improving Test-Time Reinforcement Learning in Unified Multimodal Models
by: Tan, Lit Sin, et al.
Published: (2026)
by: Tan, Lit Sin, et al.
Published: (2026)
Fat-Cat: Document-Driven Metacognitive Multi-Agent System for Complex Reasoning
by: Yang, Tong, et al.
Published: (2026)
by: Yang, Tong, et al.
Published: (2026)
Metacognitive Sensitivity for Test-Time Dynamic Model Selection
by: Trinh, Le Tuan Minh, et al.
Published: (2025)
by: Trinh, Le Tuan Minh, et al.
Published: (2025)
Are Recommenders Self-Aware? Label-Free Recommendation Performance Estimation via Model Uncertainty
by: Li, Jiayu, et al.
Published: (2025)
by: Li, Jiayu, et al.
Published: (2025)
Seismic Traveltime Tomography with Label-free Learning
by: Wang, Feng, et al.
Published: (2024)
by: Wang, Feng, et al.
Published: (2024)
Label-free evaluation of lung and heart transplant biopsies using tissue autofluorescence-based virtual staining
by: Li, Yuzhu, et al.
Published: (2024)
by: Li, Yuzhu, et al.
Published: (2024)
BadLabel: A Robust Perspective on Evaluating and Enhancing Label-noise Learning
by: Zhang, Jingfeng, et al.
Published: (2023)
by: Zhang, Jingfeng, et al.
Published: (2023)
Knowledge-Centric Metacognitive Learning
by: Kumar, Arun, et al.
Published: (2024)
by: Kumar, Arun, et al.
Published: (2024)
Similar Items
-
TTVS: Boosting Self-Exploring Reinforcement Learning via Test-time Variational Synthesis
by: Bai, Sikai, et al.
Published: (2026) -
DiEP: Adaptive Mixture-of-Experts Compression through Differentiable Expert Pruning
by: Bai, Sikai, et al.
Published: (2025) -
From LLMs to LRMs: Rethinking Pruning for Reasoning-Centric Models
by: Ding, Longwei, et al.
Published: (2026) -
CoRE: Concept-Reasoning Expansion for Continual Brain Lesion Segmentation
by: Chen, Qianqian, et al.
Published: (2026) -
BARREL: Boundary-Aware Reasoning for Factual and Reliable LRMs
by: Yang, Junxiao, et al.
Published: (2025)