Imagen de Portada

Beyond Meta-Reasoning: Metacognitive Consolidation for Self-Improving LLM Reasoning

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Zhuang, Ziqing, Zhang, Linhai, Si, Jiasheng, Zhou, Deyu, He, Yulan
Formato:	Preprint
Publicado:	2026
Materias:	Artificial Intelligence
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Test-Time Personalization: A Diagnostic Framework and Probabilistic Fix for Scaling Failures
por: Zhang, Linhai, et al.
Publicado: (2026)

RGAR: Recurrence Generation-augmented Retrieval for Factual-aware Medical Question Answering
por: Liang, Sichu, et al.
Publicado: (2025)

Rehearse With User: Personalized Opinion Summarization via Role-Playing based on Large Language Models
por: Zhang, Yanyue, et al.
Publicado: (2025)

Meta-R1: Empowering Large Reasoning Models with Metacognition
por: Dong, Haonan, et al.
Publicado: (2025)

CoT2-Meta: Budgeted Metacognitive Control for Test-Time Reasoning
por: Ma, Siyuan, et al.
Publicado: (2026)

Fine-grainedly Synthesize Streaming Data Based On Large Language Models With Graph Structure Understanding For Data Sparsity
por: Zhang, Xin, et al.
Publicado: (2024)

DINER: Debiasing Aspect-based Sentiment Analysis with Multi-variable Causal Inference
por: Wu, Jialong, et al.
Publicado: (2024)

STAR: Constraint LoRA with Dynamic Active Learning for Data-Efficient Fine-Tuning of Large Language Models
por: Zhang, Linhai, et al.
Publicado: (2024)

Searching Meta Reasoning Skeleton to Guide LLM Reasoning
por: Zhang, Ziying, et al.
Publicado: (2025)

On Information Self-Locking in Reinforcement Learning for Active Reasoning of LLM agents
por: Zou, Deyu, et al.
Publicado: (2026)

Cog-Rethinker: Hierarchical Metacognitive Reinforcement Learning for LLM Reasoning
por: Sun, Zexu, et al.
Publicado: (2025)

Metacognitive Reuse: Turning Recurring LLM Reasoning Into Concise Behaviors
por: Didolkar, Aniket, et al.
Publicado: (2025)

Metacognition as Reward: Reinforcing LLM Reasoning via Knowledge and Regulation Signals
por: Chen, Sirui, et al.
Publicado: (2026)

MA$^{2}$P: A Meta-Cognitive Autonomous Intelligent Agents Framework for Complex Persuasion
por: Zhang, Dingyi, et al.
Publicado: (2026)

Adapting Like Humans: A Metacognitive Agent with Test-time Reasoning
por: Li, Yang, et al.
Publicado: (2025)

Respecting Self-Uncertainty in On-Policy Self-Distillation for Efficient LLM Reasoning
por: Ke, Junlong, et al.
Publicado: (2026)

Mirror: A Multiple-perspective Self-Reflection Method for Knowledge-rich Reasoning
por: Yan, Hanqi, et al.
Publicado: (2024)

Large, Small or Both: A Novel Data Augmentation Framework Based on Language Models for Debiasing Opinion Summarization
por: Zhang, Yanyue, et al.
Publicado: (2024)

Agents Require Metacognitive and Strategic Reasoning to Succeed in the Coming Labor Markets
por: Zhang, Simpson, et al.
Publicado: (2025)

Bridging Social Psychology and LLM Reasoning: Conflict-Aware Meta-Review Generation via Cognitive Alignment
por: Chen, Wei, et al.
Publicado: (2025)

Entropy-Aware Speculative Decoding Toward Improved LLM Reasoning
por: Su, Tiancheng, et al.
Publicado: (2025)

Language Models Coupled with Metacognition Can Outperform Reasoning Models
por: Khandelwal, Vedant, et al.
Publicado: (2025)

Know What You Know: Metacognitive Entropy Calibration for Verifiable RL Reasoning
por: Zhao, Qiannian, et al.
Publicado: (2026)

What Really Improves Mathematical Reasoning: Structured Reasoning Signals Beyond Pure Code
por: Zhao, Yuze, et al.
Publicado: (2026)

Beyond the Trade-off: Self-Supervised Reinforcement Learning for Reasoning Models' Instruction Following
por: Ren, Qingyu, et al.
Publicado: (2025)

WebWalker: Benchmarking LLMs in Web Traversal
por: Wu, Jialong, et al.
Publicado: (2025)

Evaluating LLM Reasoning Beyond Correctness and CoT
por: Abbasloo, Soheil
Publicado: (2025)

Truly Self-Improving Agents Require Intrinsic Metacognitive Learning
por: Liu, Tennison, et al.
Publicado: (2025)

MCPO: Mastery-Consolidated Policy Optimization for Large Reasoning Models
por: Liao, Zhaokang, et al.
Publicado: (2026)

MetaCogAgent: A Metacognitive Multi-Agent LLM Framework with Self-Aware Task Delegation
por: Wang, Chenyu, et al.
Publicado: (2026)

Boosting LLM Reasoning via Spontaneous Self-Correction
por: Zhao, Xutong, et al.
Publicado: (2025)

CAP-CoT: Cycle Adversarial Prompt for Improving Chain of Thoughts in LLM Reasoning
por: Chen, Shuxu, et al.
Publicado: (2026)

Seirênes: Adversarial Self-Play with Evolving Distractions for LLM Reasoning
por: Zhang, Chi, et al.
Publicado: (2026)

Think$^{2}$: Grounded Metacognitive Reasoning in Large Language Models
por: Elenjical, Abraham Paul, et al.
Publicado: (2026)

PRISM-MCTS: Learning from Reasoning Trajectories with Metacognitive Reflection
por: Cheng, Siyuan, et al.
Publicado: (2026)

Self-Evolving Curriculum for LLM Reasoning
por: Chen, Xiaoyin, et al.
Publicado: (2025)

On LLM-Based Scientific Inductive Reasoning Beyond Equations
por: Lin, Brian S., et al.
Publicado: (2025)

Monitor-Generate-Verify (MGV): Formalising Metacognitive Theory for Language Model Reasoning
por: Oh, Nick, et al.
Publicado: (2025)

Meta-TTRL: A Metacognitive Framework for Self-Improving Test-Time Reinforcement Learning in Unified Multimodal Models
por: Tan, Lit Sin, et al.
Publicado: (2026)

Improving Retrieval Augmented Language Model with Self-Reasoning
por: Xia, Yuan, et al.
Publicado: (2024)