Image de couverture de livre

Evidence for Limited Metacognition in LLMs

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteur principal:	Ackerman, Christopher
Format:	Preprint
Publié:	2025
Sujets:	Machine Learning Artificial Intelligence
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Selective Deficits in LLM Mental Self-Modeling in a Behavior-Based Test of Theory of Mind
par: Ackerman, Christopher
Publié: (2026)

Metacognitive Capabilities of LLMs: An Exploration in Mathematical Problem Solving
par: Didolkar, Aniket, et autres
Publié: (2024)

Inspection and Control of Self-Generated-Text Recognition Ability in Llama3-8b-Instruct
par: Ackerman, Christopher, et autres
Publié: (2024)

Metis: Learning to Jailbreak LLMs via Self-Evolving Metacognitive Policy Optimization
par: Zhou, Huilin, et autres
Publié: (2026)

Mitigating Many-Shot Jailbreaking
par: Ackerman, Christopher M., et autres
Publié: (2025)

Knowledge-Centric Metacognitive Learning
par: Kumar, Arun, et autres
Publié: (2024)

The Metacognitive Probe: Five Behavioural Calibration Diagnostics for LLMs
par: Oliveira, Rafael C. T.
Publié: (2026)

Cog-Rethinker: Hierarchical Metacognitive Reinforcement Learning for LLM Reasoning
par: Sun, Zexu, et autres
Publié: (2025)

Metacognitive Reuse: Turning Recurring LLM Reasoning Into Concise Behaviors
par: Didolkar, Aniket, et autres
Publié: (2025)

Competence-Aware AI Agents with Metacognition for Unknown Situations and Environments (MUSE)
par: Valiente, Rodolfo, et autres
Publié: (2024)

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

SCI: A Metacognitive Control for Signal Dynamics
par: Meesala, Vishal Joshua
Publié: (2025)

Limits of PRM-Guided Tree Search for Mathematical Reasoning with LLMs
par: Cinquin, Tristan, et autres
Publié: (2025)

Robustness is Important: Limitations of LLMs for Data Fitting
par: Liu, Hejia, et autres
Publié: (2025)

Comprehension Without Competence: Architectural Limits of LLMs in Symbolic Computation and Reasoning
par: Zhang, Zheng
Publié: (2025)

Explainable AML Triage with LLMs: Evidence Retrieval and Counterfactual Checks
par: Torres, Dorothy, et autres
Publié: (2026)

A Fragile Number Sense: Probing the Elemental Limits of Numerical Reasoning in LLMs
par: Rahman, Roussel, et autres
Publié: (2025)

Meta-TTRL: A Metacognitive Framework for Self-Improving Test-Time Reinforcement Learning in Unified Multimodal Models
par: Tan, Lit Sin, et autres
Publié: (2026)

When the Loop Closes: Architectural Limits of In-Context Isolation, Metacognitive Co-option, and the Two-Target Design Problem in Human-LLM Systems
par: Cheng, Z., et autres
Publié: (2026)

A Practical Guide for Evaluating LLMs and LLM-Reliant Systems
par: Rudd, Ethan M., et autres
Publié: (2025)

ZebraLogic: On the Scaling Limits of LLMs for Logical Reasoning
par: Lin, Bill Yuchen, et autres
Publié: (2025)

State Stream Transformer (SST) : Emergent Metacognitive Behaviours Through Latent State Persistence
par: Aviss, Thea
Publié: (2025)

BiLLM: Pushing the Limit of Post-Training Quantization for LLMs
par: Huang, Wei, et autres
Publié: (2024)

Hypertokens: Holographic Associative Memory in Tokenized LLMs
par: Augeri, Christopher James
Publié: (2025)

The Compliance Trap: How Structural Constraints Degrade Frontier AI Metacognition Under Adversarial Pressure
par: Kumar, Rahul
Publié: (2026)

Data Distribution as a Lever for Guiding Optimizers Toward Superior Generalization in LLMs
par: Gangavarapu, Tushaar, et autres
Publié: (2026)

Modality Collapse as Mismatched Decoding: Information-Theoretic Limits of Multimodal LLMs
par: Billa, Jayadev
Publié: (2026)

Compute-Optimal LLMs Provably Generalize Better With Scale
par: Finzi, Marc, et autres
Publié: (2025)

LLMs learn governing principles of dynamical systems, revealing an in-context neural scaling law
par: Liu, Toni J. B., et autres
Publié: (2024)

Early Evidence of Vibe-Proving with Consumer LLMs: A Case Study on Spectral Region Characterization with ChatGPT-5.2 (Thinking)
par: Verbeken, Brecht, et autres
Publié: (2026)

ModuLoRA: Finetuning 2-Bit LLMs on Consumer GPUs by Integrating with Modular Quantizers
par: Yin, Junjie, et autres
Publié: (2023)

seqBench: A Tunable Benchmark to Quantify Sequential Reasoning Limits of LLMs
par: Ramezanali, Mohammad, et autres
Publié: (2025)

Dialogue Without Limits: Constant-Sized KV Caches for Extended Responses in LLMs
par: Ghadia, Ravi, et autres
Publié: (2025)

GTBench: Uncovering the Strategic Reasoning Limitations of LLMs via Game-Theoretic Evaluations
par: Duan, Jinhao, et autres
Publié: (2024)

AutoOR: Scalably Post-training LLMs to Autoformalize Operations Research Problems
par: Motwani, Sumeet Ramesh, et autres
Publié: (2026)

On Limitations of the Transformer Architecture
par: Peng, Binghui, et autres
Publié: (2024)

Zeroth-Order Fine-Tuning of LLMs with Extreme Sparsity
par: Guo, Wentao, et autres
Publié: (2024)

LLMs Judging LLMs: A Simplex Perspective
par: Vossler, Patrick, et autres
Publié: (2025)

On Limitation of Transformer for Learning HMMs
par: Hu, Jiachen, et autres
Publié: (2024)

ECPO: Evidence-Coupled Policy Optimization for Evidence-Certified Candidate Ranking
par: Hu, Miaobo, et autres
Publié: (2026)