Copertina

Monitor-Generate-Verify (MGV): Formalising Metacognitive Theory for Language Model Reasoning

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Oh, Nick, Gobet, Fernand
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Artificial Intelligence
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Automatic Adaptation to Concept Complexity and Subjective Natural Concepts: A Cognitive Model based on Chunking
di: Bennett, Dmitry, et al.
Pubblicazione: (2025)

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

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

Language Models Are Capable of Metacognitive Monitoring and Control of Their Internal Activations
di: Ji-An, Li, et al.
Pubblicazione: (2025)

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

Neurosymbolic Language Reasoning as Satisfiability Modulo Theory
di: Oh, Hyunseok, et al.
Pubblicazione: (2026)

Correct Answers from Sound Reasoning: Verifiable Process Supervision for Language Models
di: Kim, Kyuyoung, et al.
Pubblicazione: (2026)

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

Beyond Meta-Reasoning: Metacognitive Consolidation for Self-Improving LLM Reasoning
di: Zhuang, Ziqing, et al.
Pubblicazione: (2026)

Before you <think>, monitor: Implementing Flavell's metacognitive framework in LLMs
di: Oh, Nick
Pubblicazione: (2025)

A Decision-Theoretic Formalisation of Steganography With Applications to LLM Monitoring
di: Anwar, Usman, et al.
Pubblicazione: (2026)

Improving Metacognition and Uncertainty Communication in Language Models
di: Steyvers, Mark, et al.
Pubblicazione: (2025)

VERGE: Formal Refinement and Guidance Engine for Verifiable LLM Reasoning
di: Singh, Vikash, et al.
Pubblicazione: (2026)

A Relative-Budget Theory for Reinforcement Learning with Verifiable Rewards in Large Language Model Reasoning
di: Wachi, Akifumi, et al.
Pubblicazione: (2026)

Verifying Large Language Models' Reasoning Paths via Correlation Matrix Rank
di: Liu, Jiayu, et al.
Pubblicazione: (2025)

Causal Consistency Regularization: Training Verifiably Sensitive Reasoning in Large Language Models
di: Akter, Sanjeda, et al.
Pubblicazione: (2025)

Learning to Self-Verify Makes Language Models Better Reasoners
di: Chen, Yuxin, et al.
Pubblicazione: (2026)

Metacognitive Prompting Improves Understanding in Large Language Models
di: Wang, Yuqing, et al.
Pubblicazione: (2023)

RL Tango: Reinforcing Generator and Verifier Together for Language Reasoning
di: Zha, Kaiwen, et al.
Pubblicazione: (2025)

Metacognitive Myopia in Large Language Models
di: Scholten, Florian, et al.
Pubblicazione: (2024)

VerifiAgent: a Unified Verification Agent in Language Model Reasoning
di: Han, Jiuzhou, et al.
Pubblicazione: (2025)

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

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

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

Explaining Too Much? Understanding How Large Language Model Reasoning Traces Influence Performance and Metacognition
di: Fernandes, Daniela, et al.
Pubblicazione: (2026)

In Defence of Post-hoc Explainability
di: Oh, Nick
Pubblicazione: (2024)

Metacognitive Behavioral Tuning of Large Language Models for Multi-Hop Question Answering
di: Kim, Ik-hwan, et al.
Pubblicazione: (2026)

Metacognition and Uncertainty Communication in Humans and Large Language Models
di: Steyvers, Mark, et al.
Pubblicazione: (2025)

NP-Engine: Empowering Optimization Reasoning in Large Language Models with Verifiable Synthetic NP Problems
di: Li, Xiaozhe, et al.
Pubblicazione: (2025)

ProofSketch: Efficient Verified Reasoning for Large Language Models
di: Sheshanarayana, Disha, et al.
Pubblicazione: (2025)

Enigmata: Scaling Logical Reasoning in Large Language Models with Synthetic Verifiable Puzzles
di: Chen, Jiangjie, et al.
Pubblicazione: (2025)

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

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

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

MIRROR: A Hierarchical Benchmark for Metacognitive Calibration in Large Language Models
di: Wang, Jason Z
Pubblicazione: (2026)

Verifiable Process Rewards for Agentic Reasoning
di: Yuan, Huining, et al.
Pubblicazione: (2026)

VerifyBench: A Systematic Benchmark for Evaluating Reasoning Verifiers Across Domains
di: Li, Xuzhao, et al.
Pubblicazione: (2025)

Towards a Formalisation of Value-based Actions and Consequentialist Ethics
di: Wyner, Adam, et al.
Pubblicazione: (2024)

An Execution-Verified Multi-Language Benchmark for Code Semantic Reasoning
di: Li, Yikun, et al.
Pubblicazione: (2026)

A Proposal to Extend the Common Model of Cognition with Metacognition
di: Laird, John, et al.
Pubblicazione: (2025)