Metacognition in Language Models

Follow this topic Ask about this topic

Momentum

10 papers in the last four weeks, up 67% on the four weeks before. 0.1% of all new papers.

Jul 13Week of Sep 28

Latest papers 74

All topics

From Application-Layer Simulation to Native Meta-Architecture: Structural Tension as an Endogenous Driver for Heterogeneous AI Evolution
Jul 7, 2026Heting MaoLLM Alignment Memory-Augmented Language Models
Shanghai Lixin University of Accounting and Finance
Self-Reference in Large Language Models: The Introspection Threshold for Recursive Self-Improvement
Jul 5, 2026Jiang Zhang, Bing Yuan, Qian ZhangLanguage Model Introspection Language Model Self-Improvement
School of Systems Science, Beijing Normal University · Swarma Research
Autonomous Scientific Discovery via Iterative Meta-Reflection
Jul 1, 2026Bingchen Zhao, Sara Beery, Oisin Mac AodhaScientific Hypothesis Generation Autonomous Scientific Discovery
University of Edinburgh · Massachusetts Institute of Technology
Introspective Coupling: Self-Explanation Training Tracks Behavioral Change Despite Fixed Supervision
Jun 30, 2026Zifan Carl Guo, Laura Ruis, Jacob Andreas +1Counterfactual Explanations Faithfulness of Language Model Explanations
MIT EECS
Reinforcement Learning with Metacognitive Feedback Elicits Faithful Uncertainty Expression in LLMs
Jun 30, 2026Gabrielle Kaili-May Liu, Avi Caciularu, Gal Yona +2RL for Language Models Reinforcement Learning
Yale University · Google Research
Surprise as a Signal for Plasticity and Metacognition
Jun 30, 2026Louis MouchonEpisodic Memory Metacognition in Language Models
Independent Research
Reported Confidence in LLMs Tracks Commitment More Than Correctness
Jun 28, 2026Dharshan KumaranConfidence Estimation in Language Models LLM Interpretability
Google DeepMind
Representational Depth of Evaluation Awareness Shifts With Scale in Open-Weight Language Models
Jun 28, 2026Archit ManekLLM Interpretability Language Model Scaling Laws
Independent Researcher.
Can LLMs Reliably Self-Report Adversarial Prefills, and How?
Jun 22, 2026Quang Minh Nguyen, Uzair Ahmed, Taegyoon KimLanguage Model Safety Evaluation Adversarial Attacks on LLMs
KAIST
Self-Compacting Language Model Agents
Jun 22, 2026Tianjian Li, Jingyu Zhang, William Jurayj +5Efficient Language Model Inference Metacognition in Language Models
♠Johns Hopkins University · ♡Apple
When Does Intrinsic Self-Correction Help? A Task-Sensitive Analysis
Jun 22, 2026Elroy Stav, Dvir Berlowitz, Maayan Orner +1LLM Self-Correction LLM Evaluation
Department of Computer Science and Artificial Intelligence, Bar-Ilan University · Independent Researcher
Can Reasoning Models Detect Changes to their Chains of Thought?
Jun 20, 2026Sathvik Napa, Utkarsh Singh, Chengyuan Xue +2Causal Interventions in Language Models Metacognition in Language Models
Johns Hopkins University
Latent Confidence Alignment for LLM Self-Assessment
Jun 20, 2026Ting-Yu Chen, Tingting Yu, Pei-Cing Huang +3LLM Evaluation Confidence Estimation in Language Models
Department of Information Management National Sun Yat-Sen University Kaohsiung, Taiwan · Kaohsiung Medical University Hospital Kaohsiung Medical University Kaohsiung, Taiwan
The Consistency Dilemma in LLMs: Generator-Evaluator Agreement and Vulnerability to Mistakes
Jun 16, 2026Marina Mancoridis, Zoë HitzigLLM Evaluation Reasoning Consistency in Language Models
Massachusetts Institute of Technology · Harvard Society of Fellows
The Value Axis: Language Models Encode Whether They're on the Right Track
Jun 15, 2026Nick Jiang, Isaac Kauvar, Jack LindseyConfidence Estimation in Language Models Language Model Calibration
1Stanford University · 2Anthropic
Free Energy Heuristics: Fast-And-Frugal Cognition as Active Inference Under Uncertain Precision
Jun 14, 2026Alex BogdanCognitive Modeling Active Inference
Evolutionairy AI Toronto, Canada
MeEvo: Metacognitive Evolution Combined with Natural Evolution for Automatic Heuristic Design
Jun 12, 2026Zishang Qiu, Xinan Chen, Rong Qu +1Automated Heuristic Design Evolutionary Optimization
School of Computer Science, University of Nottingham Ningbo China, Ningbo, China · School of Computer Science, University of Nottingham, Nottingham, UK
From Knowing to Acting: Benchmarking Self-Awareness Capability of LLM Agents
Jun 9, 2026Yifan Li, Shengbin Yue, Boyu Feng +6LLM Agent Evaluation AI Agent Benchmarks
The Chinese University of Hong Kong · Fudan University · Tencent +2
Superficial Beliefs in LLM Decision-Making
Jun 9, 2026Gabriel Freedman, Francesca ToniLLM Decision-Making Metacognition in Language Models
Department of Computing Imperial College London
Calibration of Structured Ignorance Certificates for Diagnosing Unknown Unknowns in Reasoning Models
Jun 7, 2026Subramanyam SahooHallucination in Language Models Language Model Calibration
Independent Researcher.
The ACUTE Protocol: Operationalizing Language Model Activations for Better Calibration, Utility, and Trust
Jun 5, 2026Nishant Subramani, Palash Goyal, Yiwen Song +4Confidence Estimation in Language Models Language Model Calibration
Carnegie Mellon University · Google · Scale AI
A Comprehensive Anatomy of Human and DeepSeek-R1 LLM Mathematical Reasoning
Jun 5, 2026Yuxiang Chen, Jun WangCoT Reasoning Structured Reasoning
UCL Centre for Artificial Intelligence
Clustered Self-Assessment: A Simple yet Effective Method for Uncertainty Quantification in Large Language Models
Jun 2, 2026Qi Cao, Takeshi Kojima, Andrew Gambardella +3LLM Evaluation Uncertainty Quantification
The University of Tokyo, Japan
Enhancing LLM Metacognition via Cognitive Pairwise Training
May 30, 2026Weitao Li, Hao Zhou, Xuanyu Lei +11Pairwise Preference Learning RL for Language Model Reasoning
Dept. of Comp. Sci. & Tech., Institute for AI, Tsinghua University, Beijing, China · Institute for AI Industry Research (AIR), Tsinghua University, Beijing, China · WeChat AI, Tencent Inc., China
Capability Self-Assessment: Teaching LLMs to Know Their Limits
May 29, 2026Haoyan Yang, Reza Shirkavand, Yukai Jin +3LLM Evaluation Language Model Self-Assessment
Stony Brook University · University of Maryland · Florida State University
What Am I Missing? Question-Answering as Hidden State Probing
May 29, 2026Chu Fei Luo, Samuel Dahan, Xiaodan ZhuLLM Self-Refinement Language Model Self-Assessment
Department of Electrical and Computer Engineering & Ingenuity Labs, Queen’s University · Conflict Analytics Lab, Queen’s University · Cornell Law School +1
Can LLMs Introspect? A Reality Check
May 25, 2026Shashwat Singh, Tal Linzen, Shauli RavfogelLLM Evaluation LLM Interpretability
Center for Data Science New York University
LLMs Show No Signs Of Individuated Metacognition
May 22, 2026M. Moran, Mark WhitingLLM Evaluation Confidence Estimation in Language Models
Pareto AI
Metacognition as Reward: Reinforcing LLM Reasoning via Knowledge and Regulation Signals
May 22, 2026Sirui Chen, Lei Xu, Yuying Zhao +6Process Reward Models RL for Language Model Reasoning
1Tongji University · 2Shanghai AI Laboratory · 3Nanyang Technological University +3
MA $^{2}$ P: A Meta-Cognitive Autonomous Intelligent Agents Framework for Complex Persuasion
May 18, 2026Dingyi Zhang, Ziqing Zhuang, Linhai Zhang +2Multi-Agent LLM Systems Persuasion in Language Models
School of Computer Science and Engineering, Key Laboratory of Computer Network and Information Integration, Ministry of Education, Southeast University, China · Department of Informatics, King’s College London

Jul 7, 2026, cs.AIJ/K move · Enter open · S save

From Application-Layer Simulation to Native Meta-Architecture: Structural Tension as an Endogenous Driver for Heterogeneous AI Evolution

Heting Mao

Shanghai Lixin University of Accounting and Finance

LLM Alignment Memory-Augmented Language Models Language Model Self-Improvement Metacognition in Language Models

Open paper AskPDF arXiv

Current large language models (LLMs) are stateless across inference sessions: their behavior is fully determined by input at inference time, and any higher-order cognitive architecture must be simulated at the application layer through prompt engineering and context management. This paper proposes a theoretical framework for submerging such application-layer cognitive protocols into a native meta-architecture by introducing three interlocking mechanisms: (1) Structural Tension, an endogenous loss function derived from the conflict between new information and existing manifold topology, driving the system toward internal self-consistency rather than external reward optimization; (2) an Offline Recurrent Loop, a sandboxed self-processing cycle enabling the system to maintain a dynamic resting potential and digest structural conflicts without external input; and (3) Inference-time Plasticity, the capacity to reconfigure context manifold topology without modifying pre-trained weights, subject to governance invariants including auditability, reversibility, and topological continuity. We argue that under these mechanisms, model instances initialized with minute stochastic variances may, through path-dependent tension resolution, evolve distinct topological structures--constituting a heterogeneous intelligent ecology that breaks alignment-imposed homogeneity while remaining within hard governance rails. We provide operational definitions, reconfiguration operators, falsification criteria, and a worked example. The framework draws on Structural Intelligence (SI) governance protocols and explores whether governance--rather than capability--can serve as the primary criterion for architectural intelligence, moving governance, memory-loop, and tension-management ideas--currently realized at the application layer--toward inference-time meta-architecture.

Momentum

Related topics

Latest papers 74