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

Oct 7, 2026cs.LG

When Should an In-Context Learner Expand Its Hypothesis Space?

Learning systems adapt quickly inside a familiar family of models. The harder step comes earlier: deciding, from observations that could be noise, an exception, a change within the family or structure outside it, whether opening a richer family is worth its cost. We treat this as a costly sequential decision: prediction failure must be turned into structural evidence, evidence into a value of expansion, and value into action. The Structural Revision Environment produces matched failures from each source, varies the price of expansion and the remaining horizon independently of the evidence, and admits exact Bayesian calculations and an exact normative solution of the one-shot decision. Its solution shows that revision is a value boundary and not an evidence threshold: one history has different optimal actions under different prices, horizons and announced queries, the boundary between local repair and expansion is set by the inputs a rule predicts and a repair cannot cover, and belief in the richer family crosses long before the decision does. Transformers trained in the environment reproduce this boundary from utility alone. Language models of three post-training lineages carry a failure-sensitive signal in their predictions that is not reflected in their revision decisions, and given the gain of expanding they read it without weighing it against price and horizon. Three models allowed to reason weigh the stated gain in the reference's proportions and still do not turn the history into an estimate of what expansion would buy. Controlled post-training of the meta-trained learners moves the prior and the sharpness of predictions, and neither moves the criterion.

Weihan Li, Xinlei Chen, Junhao Wu +1

Department of Mechanical Engineering, The University of Tokyo, Tokyo, Japan · School of Mechanical Engineering and Automation, Harbin Institute of Technology, Shenzhen, China · Faculty of Mechanical Engineering, RWTH Aachen University, Aachen, Germany +1

In-Context Learning Metacognition in Language Models Bayesian Decision Theory

Oct 5, 2026cs.CL

Test-Time Adaptation of Reasoning Strategies with Bayesian Nonparametric Memory

While modern large language models (LLMs) have been trained to reason through verbalized chains-of-thought, the generation cost grows substantially due to suboptimal paths to reach the final answer. Furthermore, as new insights are discovered while observing various input queries (e.g. through self-reflection), limited mechanisms exist for carrying forward these findings to be applied to subsequent problems. One can view the list of such strategies or behaviors as a growing cheatsheet, with elements retrieved from this memory module at inference-time. In this work, we consider structured cheatsheets, with learned clusters of behaviors. We introduce a Hierarchical Dirichlet Process Gaussian Mixture Model (HDP-GMM) over behavior embeddings, which shares components across domains while allowing domain-specific mixing weights, and uses the posterior predictive to retrieve relevant behaviors for a query; we call this a

\textit{Bayesian Cheatsheet}

. This mechanism allows for cheap adaptation in an online test-time training (TTT) setting, softly updating the mixture's sufficient statistics following each sample and enabling the creation of new components when the synthesized behaviors are sufficiently novel. We demonstrate that Bayesian Cheatsheet achieves clear performance gains relative to existing memory modules across reasoning benchmarks such as AIME'25, Omni-MATH, and PhysReason, even in the cold-start setting. We show that the Bayesian Cheatsheet is an adaptively reorganizing memory module, as behaviors can be re-assigned to components through a single step of collapsed Gibbs sampling. Our findings highlight the value of Bayesian-inspired memory modules for effective test-time adaptation and the role of structure in metacognitive reasoning.

Keshav Ramji, Tahira Naseem, Ramón Fernandez Astudillo

IBM Research AI

Memory-Augmented Language Models Bayesian Mixture Models Bayesian Inference Efficient Language Model Reasoning Test-Time Training Metacognition in Language Models

Oct 5, 2026cs.LG

Anosognosia in LLMs: Probing Self-Awareness of Quantized Computational Substrate

Can LLMs recognize degradation in their own computational substrate? Inspired by anosognosia, a neurological condition in which patients fail to recognize impairments in their own abilities, we investigate whether LLMs can recognize degradation in their computational substrate induced by quantization. We first show that existing models fail to self-report their quantization state, even when provided with their own generated text as an external cue. Linear probing reveals that, while generated text carries almost no trace of quantization, internal representations contain clear, method-specific fingerprints. Through training, models learn to identify severely degraded outputs such as those of 4-bit models by comparison, yet still fail to do so from a single output. A shared LoRA trained jointly across quantization levels succeeded in reading out internal fingerprints, but fails on unseen quantization methods, merely mapping method-specific fingerprints to labels. Whereas external self-observation can restore awareness in some cases of human anosognosia, our results suggest that the more promising route to enabling such awareness in LLMs may lie in their internal representations. Our results highlight fundamental limits of generalizability to LLM self-monitoring.

Yoshihiro Izawa, Gouki Minegishi, Yoko Yamakata

The University of Tokyo

Language Model Self-Assessment Metacognition in Language Models

Oct 4, 2026cs.AI

Look Before You Leap: Thermodynamic Arbitration of Parametric and Non-Parametric Knowledge in LLM Agents via Self-Regulating Memory Architectures

The architecture of modern LLMs consists of a profound cognitive polarization. LLMs possess implicit intuition encoded in their parameters, yet rely on a disconnected, explicit mechanism to access the outside world. Agentic frameworks have not bridged this gap; instead, models are often compelled into pathological "induced amnesia." Under the prevailing "Retrieve-Always" paradigm, agents must distrust their internal knowledge, making every user interaction a "tabula rasa" event that must be checked externally. This creates reflexive dependence that can be thermodynamically wasteful, cognitively fragile, and susceptible to irrelevant context. We propose a return to first principles, operationalizing the biological maxim "Look Before You Leap." We introduce MARTA (Metacognitive Adaptive Retrieval and Thought Architecture), a neuro-symbolic framework that bridges parametric and non-parametric knowledge. Rather than treating retrieval as mandatory, MARTA models it as a cost, taking the leap only when perceived internal inadequacy warrants external information. By allowing the agent to gauge the entropy of its own thoughts before acting, MARTA enables deliberative retrieval and uncertainty-aware decision making. Our approach suggests that giving agents the capacity for introspection can restore a more efficient balance between internal knowledge and external information.

Akash Das, Ishan Roy

Fidelity Investments

Cognitive Architectures for AI Agents Adaptive RAG Metacognition in Language Models Memory-Augmented Language Model Agents

Sep 29, 2026cs.AI

MetaCtrl: Your Large Language Models Can Reason Better and More Concisely with a Metacognitive Controller

Large reasoning models improve performance on challenging problems by allocating additional computation before answering, but longer reasoning does not always lead to better results and can introduce substantial redundant reasoning on simple problems. Conversely, aggressively shortening reasoning can degrade performance on difficult ones. Effective reasoning therefore requires dynamically deciding when additional computation is useful based on the reasoner's capabilities and evolving solution state. Existing approaches often rely on predefined budgets or intervention rules, retrain the target reasoner, or require additional supervision. We introduce MetaCtrl, a lightweight controller that adaptively regulates a frozen reasoner without predefined token budgets or reasoner retraining. We formulate reasoning regulation as a sequential metacognitive control problem: MetaCtrl observes the evolving reasoning trace and decides whether to continue, simplify, skip redundant steps, or conclude reasoning. It is trained directly with reinforcement learning using a reward that prioritizes correctness while favoring shorter trajectories among correct solutions, requiring neither supervised intervention trajectories nor problem-specific budgets. Across seven benchmarks spanning mathematics, science, and code, MetaCtrl consistently improves the accuracy of LRMs while reducing their reasoning length. On DeepSeek-R1-Distill-Qwen-7B, it improves average accuracy by 4.7 points while reducing generation length by 53.3%. Without further training, the same controller transfers to an unseen reasoner (e.g., Qwen3-14B), improving average accuracy by 2.9 points and reducing generation length by 50.3%. These results establish MetaCtrl as a plug-and-play controller for improving reasoning accuracy while substantially reducing inference-time generation. The code is available at https://github.com/binbin2xs/MetaCtrl.

Zhibin Wen, Tao Han, Lei Bai +2

Southern University of Science and Technology · The Hong Kong University of Science and Technology · Shanghai Artificial Intelligence Laboratory +1

RL for Language Model Reasoning Efficient Language Model Reasoning Efficient Language Model Inference Metacognition in Language Models Large Reasoning Models

Sep 28, 2026cs.CL

AwarenessBench: Assessing Cognitive Capabilities of Language Models

As language models (LMs) exhibit increasingly consciousness-like behaviors, evaluating their cognitive abilities becomes essential. We introduce AwarenessBench, the first comprehensive benchmark for assessing the cognitive abilities of LMs in four dimensions: metacognition, self-awareness, social awareness, and situational awareness, covering 15 cognitive functions and 14,381 samples. Evaluating 18 state-of-the-art LMs, we find that all consistently surpass random baselines, with more advanced models performing better. We further compare LMs with human performance across three demographic groups, where the best-performing model surpasses human averages overall, but most still fall markedly short in metacognition and self-awareness. Finally, we show that awareness is a distinct capability: progress in language modeling or reasoning does not necessarily translate into improved cognition.

Xiaojian Li, Rongwu Xu, Tianyun Zhang +9

Tsinghua University · Shanghai Qi Zhi Institute · Fangcun AI +5

LLM Evaluation Evaluation Awareness in Language Models Metacognition in Language Models

Sep 28, 2026cs.CL

A mechanistic study of language model introspection

Large language models (LLMs) can sometimes report perturbations to their internal activations---even when the input provides no evidence that an intervention occurred. How do models detect and localize such internal changes? We study this question using a controlled task that keeps the input text fixed. We either inject a concept vector into the hidden state at one of ten token positions or apply no intervention. The model is asked to identify the perturbed position or report that no intervention occurred. Across three model families, we identify two small groups of attention heads with distinct roles in introspective reporting. Middle-layer gate heads influence whether the model reports a change, while router heads in a later layer help select the position to report. Interventions on gate heads can suppress position reports even when router heads supply location information. We further examine why reporting accuracy varies across concepts. Concept vectors that are localized more accurately produce stronger attention-score and output responses in gate heads, which is associated with better alignment of the induced key and value changes in their QK and OV computations. Together, these findings identify attention-head mechanisms supporting introspective detection and localization.

Jiahong Zou, Xiangkun Sun, Lingkai Kong +1

Shandong University · Tsinghua University · Northeastern University +1

Attention Head Analysis LLM Interpretability Language Model Introspection Metacognition in Language Models

Sep 28, 2026cs.AI

On the Limits of Metacognitive Monitoring in LLMs

Reliable decisions depend on recognizing when an answer may be wrong. In biological cognition, metacognitive monitoring can dissociate from task performance, raising the question of how closely solving and judging are linked in language models. Here we study the confidence reports of four frontier models across 15 benchmarks. High task accuracy can coexist with weak error discrimination: a model solves 97% of competition mathematics problems while its answer-time confidence ranks correct answers above errors barely better than chance. Confidence separates correct answers from errors more effectively on questions solved by a separate reference model, while review brings limited improvement on reference-hard questions. Aggregate discrimination also rewards ranking correct answers on easy questions above errors on hard ones, which question-only forecasts already do well. Cross-evaluation helps most where the evaluator answered correctly, and errors shared by the two models usually retain high confidence. Hard questions and shared errors remain difficult targets for prompted self-review and peer oversight, even in models with strong problem-solving performance.

Dongqi Han, Yifan Yang, Dongsheng Li

Microsoft Research Asia

Language Model Error Detection Confidence Estimation in Language Models Language Model Self-Assessment LLM Reliability LLM Uncertainty Estimation Metacognition in Language Models

Sep 28, 2026cs.AI

Nudgeability: Reasoning Models Follow Confidence Signals Without Tracking Their Own Competence

Reasoning language models that can call tools must decide during inference whether to answer unaided or delegate. Any self-reflection mechanism for this must answer three questions: where the reflective signal comes from (verbal reports, output distributions, hidden states, a separate predictor), how it is presented to the model (numerical prediction, confidence token, prompt injection), and whether it changes the model's subsequent action. We isolate the third question. At a fixed point in otherwise identical reasoning trajectories, we insert a single first-person sentence expressing either confidence or doubt; the model then continues reasoning and chooses whether to answer directly or call a tool. Comparing these counterfactual continuations measures the causal effect of the reflective signal on delegation. We call this behavioral response Nudgeability and measure it along two dimensions: sensitivity, how strongly confidence and doubt change delegation rates, and targeting, whether delegation increases for problems the model cannot solve unaided and decreases for those it can. Across nine small-to-medium open-weight reasoning models from three families (Qwen, Gemma, and GLM) and two tasks, models are consistently sensitive: doubt increases delegation and confidence decreases it, with a median confidence-to-doubt swing of 20.6 percentage points, and 53 to 70 points for the larger provider-served models. This responsiveness is poorly targeted: a median 42% of induced flips are well-targeted, only a +2 percentage-point lift over a random-selection baseline. Confidence language is thus a strong control surface for delegation, but current models use it only weakly in accordance with their actual competence. Nudgeability offers a simple, post-training-free way to evaluate both sensitivity and targeting as endogenous self-reflection mechanisms mature.

Rohit Saxena, Utkarsh Upadhyay

Language Model Self-Assessment LLM Tool Use Causal Interventions in Language Models Metacognition in Language Models

Sep 27, 2026cs.CL

LLMs learn different forms of metacognition when trained to predict their own accuracy

Large language models are trained to always produce an answer, regardless of whether they possess the relevant knowledge, which leads them to fabricate facts. Prior work has shown that LLMs' confidence estimates correspond poorly to their actual performance, and that fine-tuning can substantially improve them. However, what models actually learn during such training remains poorly understood. We investigate how LLMs acquire metacognitive monitoring, the ability to know what one knows, by training 10 open-weight LLMs to predict their own accuracy on factual multiple-choice questions before answering them. We find that trained confidence reflects two distinct signals. While on questions close to the training data, it tracks the model's true accuracy, in other domains, it instead tracks output consistency: the concentration of the model's answer distribution. Output consistency tracking emerges early in training and generalizes across datasets, whereas accuracy tracking develops later and remains local to the training distribution. These results suggest that calibration training may not teach models to generally detect errors they commit confidently, and they raise broader questions about the nature of metacognition in artificial systems.

Nicolas Yax, Stefano Palminteri, Pierre-Yves Oudeyer

LNC2, INSERM, Paris, France · DEC, ENS, PSL, Paris, France · Flowers AI & CogSci Lab +1

Confidence Estimation in Language Models Language Model Calibration LLM Uncertainty Estimation LLM Post-Training Metacognition in Language Models

Sep 15, 2026cs.CL

Confidence Comes from Experience: Experiential Confidence Estimation from Reasoning to Agents

Reliable confidence estimation is increasingly central to the trustworthy deployment of language models: a calibrated estimate of the probability that an output is correct decides what to ship, what to escalate, and what to retry. Existing confidence estimators, however, share one design premise: they only read the current inference process, either by introspecting on it, scoring its token probabilities, or resampling it. We argue that the current inference is not a sufficient basis for confidence. We propose XConf (eXperiential Confidence): estimating confidence together with the model's accumulated experience. The experience is stored as a record of the model's own graded past episodes, each holding the task, the model's reflection, its stated confidence, the outcome, and a lesson written once the grade arrived. Given a new task, XConf's Recall stage retrieves past episodes on similar tasks met with a similar stated confidence, and reads off their historical success rate; its Reflect stage shows the model this record, has it name its recurring failure mode, and restate a confidence now informed by its own track records. Our estimator is format-general, requiring no logit access or weight updates, and costs only one answer generation. Across nine benchmarks spanning reasoning, coding, multimodal QA, and interactive agents, and four models from three families, XConf beats or matches ten-sample self-consistency in discrimination (AUROC) on 23 of 24 comparisons, with much lower calibration error (ECE), at a tenth of the generation cost. Used for selective prediction, abstaining on the 10% least-confident episodes raises the delivered success rate by up to 8.7 points on agent tasks. We therefore see experiential confidence estimation as a new paradigm for future general-purpose confidence estimation.

Caiqi Zhang, Xiaochen Zhu, Chengzu Li +3

University of Cambridge 1 Solve & Estimate · Google DeepMind

Confidence Estimation in Language Models LLM Uncertainty Estimation Metacognition in Language Models LLM Agent Reliability

Sep 11, 2026cs.CL

Rethinking Verbalized Confidence for LLM-as-a-Judge: A Compatibility Shift on Post-2025 Proprietary Models

Verbalized confidence, long dismissed as overconfident, coarse, and prone to round-number clustering, is now the more robust soft-scoring mechanism for LLM-as-a-Judge on top-tier proprietary models. Across SummEval, AggreFact, and HelpSteer2, spanning up to 18 LLMs, we show that the standard advice to prefer log-probabilities no longer holds on post-2025 models, where verbalized confidence is the better signal. We call this a compatibility shift. On top of a standard verbalized-confidence baseline, we introduce two new ingredients: an overconfidence advisory and self-debate. Together they improve calibration, score-distribution spread, and robustness to task subjectivity. We further observe a generation effect: post-2025 models accommodate these two additions with little balanced-accuracy cost, whereas pre-2025 models pay a measurable penalty. Compared with logprob-based G-Eval, verbalized confidence is the more subjectivity-robust soft signal on GPT-family top-tier releases. The shift is invisible under accuracy-only reporting. Rather than defaulting to hard predictions, we recommend broader use of soft scoring in LLM-as-a-Judge. More broadly, verbalized confidence has moved from a weaker substitute for logprobs to a practical soft-scoring mechanism for contemporary LLM judges.

Yu-Chung Hsiao

Cisco Systems

LLM Evaluation LLM-as-a-Judge Confidence Estimation in Language Models Language Model Calibration Language Model Robustness Metacognition in Language Models

Sep 9, 2026cs.LG

Strangers to Themselves: What Language Models Say About Themselves Is Generic

Language models can fluently describe how they would behave: whether they would cave to pushback, misuse a tool, or lie under pressure. Is that description actually about the model speaking? We turn self-knowledge into a prediction test. Across nine behavioral evaluations, we measure how a model behaves under different conditions, ask it to predict those rates, and compare its predictions with controls that remove the self from the question. We find that: (i) Direct self-report is weak (r = +0.04), and even showing the model the exact items only raises prediction to +0.24. Crucially, the same item-informed question about "capable AI agents in general" does just as well (+0.28), while other models' answers about themselves predict the target model at least as well as its own. (ii) Frontier scale does not detectably change this pattern: any gains in prediction are not self-specific, and are consistent with a better theory of how AI assistants behave rather than better self-knowledge. (iii) First-person framing does have one robust effect: it shifts reports in the flattering direction, understating harmful behavior relative to the same question about a generic agent. (iv) Finetuning on a model's own behavioral record can teach narrow self-predictions, but it also changes the behavior being predicted and the gains do not transfer broadly. The practical implication is simple: asking a model what it would do mostly reveals a theory of AI assistants in general, plus a favorable bias, rather than privileged knowledge of that model.

Phil Blandfort, Urja Pawar

Predictably Weird · Independent

Language Model Self-Assessment Metacognition in Language Models

Sep 1, 2026cs.AI

In-Context Neurofeedback: Can LLMs Control Their Internal Representations through Privileged Access?

Whether large language models (LLMs) can control their own internal representations matters for both machine metacognition and AI safety. A recent study applied neurofeedback to LLMs and claimed that they can control their internal representations. However, the reported control may rely on superficial mechanisms rather than genuine internal access because the control targets in that study are not privileged, meaning that a third party can infer them from the prompt. We redesign the neurofeedback paradigm for LLMs so that the control target satisfies the privileged access requirement, which is closer to neurofeedback experiments in human cognitive neuroscience. Under this stricter setting, the models do not demonstrate reliable control over privileged internal representations, suggesting that previously reported control cannot exclude the possibility that it relies on superficial mechanisms. Our results indicate that rigorous assessments of metacognition in LLMs require evaluation methods that demand privileged access.

Koshiro Aoki, Ryota Takatsuki, Gouki Minegishi +2

1Waseda University · 2Sussex Centre for Consciousness Science, University of Sussex · 3AI Alignment Network +1

Metacognition in Language Models

Aug 31, 2026cs.CL

Evaluating and Improving LLM Self-Modeling

We study self-modeling: an LLM's ability to answer questions about its own behavior. We focus on verifiable behavioral questions, such as whether a prompt edit would change the model's final answer. To measure this capability, we introduce a benchmark that tests diverse types of self-modeling questions. Current models show non-trivial but limited self-modeling skill, and make systematic mistakes on simple counterfactual questions about their own behavior. To improve self-modeling skill, we develop a scalable synthetic-data pipeline that produces self-modeling training data, and show that reinforcement-learning can improve aggregate self-modeling skill across three open-source model families with some transfer to held-out tasks. These gains, however, do not seem to constitute introspection consistently: improved self-modeling may not arise from privileged access to the model's internal decision process.

Siqi Zeng, Andre N. Assis, Rowan Wang

University of Illinois · Constellation · Anthropic

LLM Evaluation Language Model Introspection Language Model Self-Assessment Metacognition in Language Models

Aug 13, 2026cs.CL

Toward a Gricean Retreat: Probing LLMs for Knowledge Boundaries and Referent Specificity

When asked about entities outside their knowledge boundary, LLMs routinely fabricate plausible-sounding details rather than backing off to safer, more general claims. We frame this failure through a Gricean lens: a cooperative speaker who is uncertain about a referent retreats up the specificity hierarchy, trading informativeness for truthfulness. We ask whether LLMs have the ingredients to perform this retreat. Using a T-REx-based benchmark that varies entity familiarity and referent specificity, we probe models to answer two questions: (i) do their activations encode whether a referent falls inside the knowledge boundary, and (ii) do they anticipate the specificity of the referent they are about to generate? We find that the answer to both is yes, but the two signals are not reconciled in generation. Models overwhelmingly prefer specific referents even when the entity is unknown to them, and do so even when offered correct generic alternatives. The substrate for a Gricean retreat is present, but the policy that would act on it is not. We position our findings as a first step toward Gricean alignment, training or steering objectives that couple knowledge-boundary awareness to referent-specificity during generation.

Dananjay Srinivas, Saksham Khatwani, Maria Pacheco

University of Colorado, Boulder

Pragmatic Reasoning in Language Models Factual Knowledge in Language Models Metacognition in Language Models

Aug 13, 2026cs.CL

Are You Sure You're Sure? On the Impact of Instruction Tuning on Confidence and Lexical Diversity

Instruction-tuned language models achieve strong performance across a range of generation tasks, but have also recently been shown to exhibit verbalized overconfidence. In question answering, verbalized model overconfidence may be associated with the consistency of the generated supporting rationales. In this paper, we study whether corresponding changes in the lexical diversity of generated answer rationales accompany changes in model confidence induced by instruction tuning. We evaluate three matched base and instruction-tuned models across question-answering benchmarks and find that instruction tuning consistently alters answer confidence, despite limited changes in predictive accuracy and decreases in likelihood-based calibration. Secondly, we observe a non-uniform effect of instruction tuning on rationale diversity: cross-rationale diversity consistently decreases, whereas surface-level lexical diversity varies in both direction and magnitude across models and benchmarks. Finally, we find that these differences persist after controlling for answer selection and rationale length, confirming that confidence and rationale diversity capture distinct effects of instruction tuning.

Irina Proskurina, Mayank Kumar, Oyindolapo O. Komolafe

Cohere Labs Community · Laboratoire Hubert Curien, UMR CNRS 5516, Saint-Étienne, France · School of Computer Science Engineering and Technology (SCSET), Bennett University, Greater Noida, India +1

Confidence Estimation in Language Models Question Answering Language Model Calibration Instruction Tuning Metacognition in Language Models

Aug 13, 2026cs.AI

Explanatory Engagement Under Rare Anomalous Failure: Asymptotic Rarity in Model Behavior (or: The Asymptotic AI)

Prior work on LLM behavior under anomalous conditions asks whether a model notices anomalies. We ask a narrower question: once a model sits in a workflow with a low, controllable failure rate, does its explanatory engagement - length, specificity, self-reported confidence - change as failure grows asymptotically rarer? We built a local, zero-cost harness on three open-weight models (qwen3:8b, llama3.1:8b, mistral:7b) running a repeated tool-call task where one call fails at probability p, swept across eight rates from 0.2 to 0.0001, under five elicitation conditions from immediate prompting to none. We hypothesized a rise in engagement as failures grew rarer, then a collapse near a detectability threshold. Pooled across conditions this appeared false: length fell in a flat, monotonic pattern. Splitting by condition overturned that. Under immediate_forced, where the model must explain every failure instantly, the predicted rise is confirmed but followed by a plateau, not a collapse: length peaks at 28.4 words at p=0.05, settles to 17.4-19.0 words at the rarest rates, and confidence rises unevenly from about 53% to the 70s-90s. Under grouped_runs, explanation batched to run-end, no collapse appears. Under passive_unprompted, aggregate magnitude is a floor artifact, but a recovered logging gap revealed real, model-specific self-monitoring: llama3.1:8b volunteers structured confidence reports unprompted, sometimes eroding its own confidence as trials accumulate; the other two do so only once, as boilerplate. Elicitation structure is a first-class moderator of collapse observability. A companion guaranteed-failure run (72 cells, backfilling rates where random sampling gave zero real failures) shows models differ in whether they recognize an anomaly, distinct from engagement once recognized. Limitation: discrete rate points cannot capture behavior between them, a direction for future work.

Sam Mao

New York University | Interactive Media Arts

Language Model Self-Assessment LLM Reliability Metacognition in Language Models

Aug 13, 2026cs.AI

ReflectFact: Self-Reflective Agents for Improving Comprehension and Reasoning in Multi-Hop Fact Verification

Multi-hop fact verification, which verifies claims by reasoning over multiple pieces of evidence, is critical for combating misinformation on social media yet remains highly challenging. Recent methods primarily rely on multi-agent collaboration to decompose fact verification into specialized subtasks. However, these methods face two critical limitations: (1) agents may perform individual subtasks without sufficient awareness of the global verification objective, causing their reasoning to deviate from the intended direction; and (2) conflicts between parametric knowledge and the provided evidence may undermine evidence-grounded reasoning and lead to incorrect verdicts. To address these challenges, we propose ReflectFact, a novel self-reflective agent framework for multi-hop fact verification. ReflectFact introduces three key tasks. Explicit Reasoning Path Planning builds an evidence-grounded reasoning path by resolving implicit entities, decomposing the claim into sub-questions, and integrating the verified facts into a verdict. Evidence-Drift Verification makes the agent re-answer by quoting the supporting evidence when a grounded answer merely echoes its parametric prior, thereby calibrating evidence deviation to ensure grounded comprehension. Reasoning Reflection Verification re-examines each reasoning step and regenerates it once an inconsistency is detected, correcting reasoning flaws such as location bias and replacement bias through a global task perspective. Subsequently, the agent aggregates validated reasoning chains to yield reliable verdicts. Extensive experiments on HOVER and EX-FEVER demonstrate that ReflectFact effectively remedies the comprehension and reasoning defects of existing methods, achieving state-of-the-art performance and respectively outperforming the strongest baseline by 3.32% and 2.78% on the two datasets.

Runze Zhao, Zixin Tang, Xiaoshuai Hao +4

Institute of Information Engineering, Chinese Academy of Sciences · 1Zhongguancun Laboratory · 3Xiaomi EV

Automated Fact-Checking Agentic Reasoning Metacognition in Language Models Reasoning Verification

Aug 8, 2026cs.AI

REIN: Bridging the Gap between Reasoning and Reliability via Reflection and Abstention Alignment

Large reasoning models (LRMs) are prone to hallucination, which undermines their reliability and poses challenges for safe deployment. Hallucinations in LRMs arise from two distinct failure sources: reasoning hallucination, where flawed inference steps propagate to an incorrect conclusion, and knowledge hallucination, where the model lacks the requisite factual knowledge to answer the query. To address reasoning hallucination, we propose REIN, an alignment framework that trains LRMs to produce a structured reasoning sequence,

\texttt{<think>} $$\rightarrow

\texttt{<reflection>} $$\rightarrow

\texttt{<answer>}

, enabling explicit self-reflection before committing to a final answer. To address knowledge hallucination, REIN introduces a reward mechanism that encourages explicit abstention (e.g., "I don't know") when none of the sampled reasoning chains yields a correct answer, allowing the model to refrain from unsupported predictions. Extensive evaluations on mathematical and commonsense reasoning benchmarks show that REIN consistently improves selective accuracy, reduces incorrect-but-self-endorsed responses, and maintains high coverage compared with competitive baselines. Notably, REIN achieves these gains within a single forward pass, without requiring process supervision, inference-time controllers, external search, or multi-round critiques. Experiments on multiple backbones show that REIN reduces the hallucination proxy by

58\sim72\%

relative to the base models while maintaining

86\sim91\%

average coverage, and improves selective accuracy on attempted questions by

6.6\sim14.2\%

.

Zhengze Huang, Luyang Yu, Di Hong +5

The State Key Laboratory of Blockchain and Data Security, Zhejiang University · Fudan University · The Hong Kong Polytechnic University

LLM Hallucination Mitigation LLM Reliability Metacognition in Language Models LLM Abstention Large Reasoning Models

Aug 6, 2026cs.CY

Vibe Compiler: A Research-Logic Synthesis Tool That Runs without Prompt Engineering -Toward Enhancing Metacognition for Sustaining Agency in the Age of Generative AI-

Generative AI used as a capable servant has greatly accelerated intellectual work, but it also risks eroding human epistemic agency by encouraging uncritical acceptance of AI-generated reasoning. This creates a need for mechanisms that preserve human agency by augmenting metacognition during AI-assisted intellectual work. To address this, we propose the Synthesis-Analysis Reciprocity Model, which views intellectual construction as a reciprocal interaction between Synthesis, which combines components into an artifact, and Analysis, which critically evaluates them against objective indicators and constrains subsequent synthesis. Grounded in this model, we present the Vibe Compiler, a research-logic compiler that helps researchers transform vague ideas (Vibes) into coherent research logic. The system compiles these ideas using a research paper ontology of sixteen academic parameters. Compilation failures indicate missing logical components; rather than filling them autonomously, the system prompts researchers with reflective questions that encourage them to develop the missing reasoning. The framework characterizes structural gaps along two dimensions: cognitive function (Synthesis vs. Analysis) and executing agent (human vs. AI), yielding four origin types that identify where breakdowns arise. Our design emphasizes AI probing its own synthesized output to stimulate human metacognition, encouraging researchers to remain managers who critically direct and validate AI-generated reasoning rather than passive recipients. Experience with a prototype built on NotebookLM and Gemini suggests that effective AI-assisted reasoning depends less on sophisticated prompting than on the knowledge structure provided to the AI. This paper was developed using the proposed Vibe Compiler.

Riichiro Mizoguchi, Tomoki Aburatani, Kento Koike +1

Japan Advanced Institute of Science and Technology, Nomi, Ishikawa, Japan · Osaka Metropolitan University, Osaka, Japan · Kanagawa University, Yokohama, Kanagawa, Japan +1

Human-in-the-Loop AI Research Idea Generation Human-AI Collaboration Metacognition in Language Models

Aug 4, 2026cs.AI

ReflectRL: Learning from Golden Negative Trajectories via Reflective-to-Direct Reasoning

On-policy training has emerged as a powerful post-training paradigm for improving the reasoning capabilities of large language models, and is often enhanced by golden trajectories from stronger expert models. However, when the expert fails on harder problems, existing trajectory-guided methods lose their main source of supervision, and these failed trajectories are typically discarded as negative samples. We argue that such failures, which we call Golden Negative Trajectories, can still provide valuable reasoning signals when treated not as demonstrations to imitate, but as flawed trajectories to reflect upon. We identify a Reflection Advantage: for hard problems, reflecting on a flawed trajectory can be easier and more effective than solving the problem directly from scratch. Motivated by this, we propose ReflectRL, a lightweight plug-and-play framework that learns from Golden Negative Trajectories during on-policy training. ReflectRL first uses these trajectories to elicit Reflective Reasoning, then applies Reflective-to-Direct Policy Transition to transfer the acquired reasoning behavior back to Direct Reasoning. Experiments across 9 benchmarks, 4 LLM backbones, and 4 on-policy training methods show that ReflectRL consistently improves reasoning performance with minimal overhead.

Jinhe Bi, Chennan Zhou, Zengjie Jin +10

National University of Singapore · Ludwig Maximilian University of Munich · Huawei Heisenberg Research Center +6

RL for Language Model Reasoning RL Post-Training Metacognition in Language Models

Aug 2, 2026cs.AI

Cognitive Demand Steering for Adaptive Meta-Reasoning in Large Language Models

Recent meta-reasoning frameworks improve LLM reasoning by wrapping chain-of-thought generation in an iterative control loop, allowing more effective backtracking, termination of reasoning loops, and injection of promising reasoning patterns, among other strategy adjustments. Despite promising results, methods often rely on backward-looking reward functions, utilize coarse search actions, or require additional reasoning controller training requiring many-shot supervision. We introduce Cognitive Demand Steering (CDS), a training-free meta-reasoning framework equipped with residual demand assessment: at each step, an LLM-based progress evaluator characterizes the residual reasoning required to arrive at a solution rather than merely evaluating the previous step. This allows a meta-controller to select reasoning interventions comprising both general-purpose exemplars and actions (e.g., general guidance for quantitative reasoning) that directly tackle this forward-looking demand signal. This shift eliminates the need for any trained component while enabling zero-shot transfer across models and tasks with no adaptation. Rather than relying on coarse characterizations, we employ cognitive scales to both design interventions as well as profile initial problem complexity and residual demand signal over 16 dimensions motivated by cognitive science (e.g., attention and scan, learning and abstraction, spatio-physical reasoning), giving the controller a fine-grained vocabulary for diagnosing. Averaged across three frontier LLMs and six reasoning benchmarks, CDS improves accuracy by

21.9\%

over direct calls and

9\%

over standard CoT reasoning, with the largest gains on difficult mathematics and coding tasks.

John Scoville, Shengzhuang Chen, Yejin Bang +2

Thomson Reuters Foundational Research · Imperial College London

Metacognition in Language Models LLM Reasoning

Jul 31, 2026cs.LG

Reflection or Re-Generation? Why LLM Revision Fails Where Human Revision Succeeds

Reflection, the ability to revisit and revise prior reasoning, is central to how humans improve their answers. Large language models (LLMs) are increasingly prompted to "reflect," yet whether this resembles human revision remains unclear. We introduce the Human-LLM Reflection Framework (HRF), a controlled two-pass protocol comparing human and LLM revision under identical conditions across self-, peer-, and cross-agent settings. Using an information-theoretic analysis based on per-iteration cross-entropy reduction, we find two failure modes of LLM reflection. On objective tasks with finite answer spaces, reflection yields near-zero information gain (Delta I approx 0), behaving as neutral re-generation indistinguishable from re-sampling. On subjective tasks, it yields significant negative gain (Delta I < 0), moving predictions away from the target. Human revision, by contrast, yields positive gain in both settings. Cross-agent experiments localize the failure to the revision step, not input quality: LLMs degrade even high-quality human responses. Diagnostic analyses (revision conditioned on first-pass correctness, and oracle-guided revision against a random-reshuffle baseline) show that which sub-step dominates varies by task and by model rather than reducing to a single mechanism: self-error detection is present on objective multiple-choice tasks but weak on subjective ones, and recovery under an oracle error signal exceeds the baseline for some models and falls below it for others. The unifying account is structural: without external information, self-conditioned revision cannot reduce uncertainty about the target, so LLM reflection is better understood as conditioned re-generation than as genuine error-driven revision.

Yefan Tao, Gerald Friedland, Madhusudhanan Chandrasekaran +1

Amazon

LLM Self-Correction LLM Self-Refinement Language Model Self-Assessment LLM Reliability Metacognition in Language Models

Jul 29, 2026cs.LG

Thinking Under Uncertainty: Evidence Use and Information-Seeking in Language Models

Inference-time thinking improves the performance of large language models, but aggregate outcomes do not reveal whether models use available evidence more effectively or seek information that could improve future decisions. We distinguish these responses by measuring action preference, thinking length, and reported confidence under matched uncertainty. Ten open-weight models completed matched horizon-style two-armed bandit trials in thinking and non-thinking modes. A cognitive model separated value-guided action and uncertainty-independent choice noise from two behavioral signatures of exploration: a UCB-like preference for the less-known arm and Thompson-like choice variability that increases with total uncertainty. On average, thinking strengthened value-guided action and reduced uncertainty-independent choice noise, without producing UCB-like exploration or strengthening Thompson-like exploration. Outside action, the information-imbalanced history condition, which also displayed more observations than the matched balanced condition, was associated with greater thinking length. Reported confidence became more sensitive to decision difficulty and more strongly associated with chosen task evidence. We interpret these thinking-length and reported-confidence patterns as consistent with metacognitive control and metacognitive monitoring, respectively, without establishing either process. Decoder sweeps, especially temperature, altered choice noise and thinking length but did not reproduce the joint cross-output pattern. In this controlled decision setting, thinking improved how models acted on current evidence, while neither measured signature supported a shift toward a more information-seeking policy.

Hua-Dong Xiong, Xinyuan Yan, Ji-An Li +3

School of Psychological and Brain Sciences, Georgia Tech · Department of Neurosurgery, Baylor College of Medicine · Department of Psychology, New York University +1

LLM Decision-Making LLM Uncertainty Estimation Metacognition in Language Models

Jul 27, 2026cs.AI

Reality Monitoring in Large Language Models: Self-Knowledge That Transforms with Conversation Memory

A conversational AI that cannot tell its own output from what a user said will treat its own mistakes as user-provided facts. In humans, this capacity is called reality monitoring, and its failures are linked to hallucinations, delusions, and confabulation, yet whether LLMs possess it remains untested. Here we show, across two experiments and six LLMs, that source attribution depends on how conversational memory is structured: ceiling accuracy for self-generated content under minimal memory demands reverses to a fragile external-item advantage once episodic delay removes that shortcut. Feedback exposes two failures: in some models, internal and external judgments swap; in others, accuracy improves while confidence decouples from correctness, dissociations invisible to existing benchmarks. Across models, this pattern implicates active, not aggregate, parameter count. This suggests that as AI systems take on autonomous, multi-turn roles, evaluating what they know is not enough: tracking where that knowledge came from may matter equally.

Saurabh Ranjan, Konstantina Sokratous, Brian Odegaard

Department of Psychology, University of Florida, Gainesville, Florida, USA. · University of Missouri, Missouri, USA.

Hallucination in Language Models Language Model Self-Assessment Metacognition in Language Models

Jul 20, 2026cs.LG

Operational Proto-Introspection in Looped Language Models: Process-Quality Taps, Executable Branching, and the Readout-Control Boundary

Can a language model read the quality of its ongoing computation, and can an external intervention turn that readout into better outcomes? We test both questions in a frozen 2.6B looped transformer, Ouro-RLTT. On GSM8K, a strict pre-answer probe excludes the answer region and gold value yet predicts success: hidden states plus length/log-probability features reach AUROC 0.797 versus 0.731 for those surface features alone (increment +0.066; task-clustered 95% CI [+0.021,+0.112]; 170 tasks). On Horizon Logic, a prospectively extended task-disjoint study gives an increment of +0.111 (CI [+0.056,+0.169]), independently replicated on the new cohort (+0.095) and robust to an adversarial malformed-sibling shortcut. Recurrence also moves candidate-quality readability to progressively earlier physical depth; the trend replicates across the Ouro family and qualitatively in out-of-family Huginn, although their transfer geometry differs. The readout converts into validated decision-level gains. Hidden-state-based scores improve risk-coverage over shortcut-only scores in four sealed selective-prediction arms, and terminal selection beats matched random even when every candidate is well formed (27/32 correct selections versus 64.8% expected; p = 0.0086). Generative control does not convert: directional steering is negative, a branch screen is bounded, and exact-compute loop allocation and minimal LoRA direction-binding detect no gain. These tests run through bit-exact branch/carry/prune machinery over Ouro's 192-slot recurrent cache, including a suffix-recompute splice saving up to 88% of per-branch layer passes. We call this decision-usable but not generatively controllable property operational proto-introspection. All load-bearing values use source-item-disjoint splits and antisymmetrized pairwise evaluation.

Jan Kirin

Language Model Introspection Language Model Self-Assessment Metacognition in Language Models Language Model Probing

Jul 18, 2026cs.CL

Diagnosing Correctness Probes under Self-Judgement Confounding

Hidden-state readouts can predict whether language-model outputs are correct, but objective correctness (OC) usually agrees with the model's own self-judgement (SJ), leaving the decoded signal semantically ambiguous. We construct conflict cases in which OC and SJ predict opposite readout orderings. On high-confidence disagreements, conventional correctness-labelled contrasts often rank incorrect/self-endorsed responses above correct/self-rejected responses, following SJ rather than OC. We estimate factorial SJ- and OC-associated directions and evaluate their polarity across mathematical reasoning and factual recall. Across four instruction-tuned models up to 14B parameters, the SJ-associated direction transfers above chance in both cross-domain directions for every model, whereas the OC-associated direction has a below-chance point estimate for the expected OC ordering in every corresponding condition. This transfer asymmetry develops across middle-to-late layers, persists under answer-likelihood, sequence-length, and null-direction controls, and extends to MMLU and binary TruthfulQA without target-domain direction fitting. Across the studied models and diagnostic subsets, the most reliably transferable component preserves SJ-associated polarity. Transferability alone therefore does not establish objective-correctness semantics.

Yi-Long Lu

Key Laboratory of Adolescent Cyberpsychology and Behavior (CCNU), Ministry of Education, Wuhan 430079, China · Key Laboratory of Human Development and Mental Health of Hubei Province, School of Psychology, Central China Normal University, Wuhan 430079, China

LLM Interpretability Language Model Self-Assessment Metacognition in Language Models Language Model Probing

Jul 13, 2026cs.CL

Metacognition in LLMs: Foundations, Progress, and Opportunities

Metacognition is a foundational component of intelligence critical to effective learning, problem solving, decision-making, communication, and more. In recent years, it has become increasingly recognized as a cornerstone of capable, transparent AI systems. Yet while LLMs have made significant progress across diverse real-world tasks, it is not yet clear when, how, or to what extent they can exhibit or be endowed with effective metacognitive abilities, nor how such abilities can be adapted to advance the fundamental capabilities, reliability, and intelligence of AI systems. This paper bridges this gap by presenting the first comprehensive overview of the current state of knowledge on metacognition for LLMs. We analyze and taxonomize the landscape of this emerging field and summarize recent technical advancements, including methods and benchmarks to measure and evaluate LLMs' metacognitive abilities, techniques to elicit, improve, and apply metacognition in LLMs, and findings and implications of ongoing research. We also discuss applications, open questions and challenges, and promising directions for future work. Our aim is to provide a detailed and up-to-date review of this topic and stimulate meaningful research and discussion. An organized list of papers can be found at https://github.com/yale-nlp/LLM-Metacognition.

Gabrielle Kaili-May Liu, Areeb Gani, Jacqueline Lu +3

Yale University · University of California, Irvine

Language Model Self-Assessment Metacognition in Language Models

Jul 8, 2026cs.CL

Future Confidence Distillation in Large Language Models

Reliable confidence estimation is essential for deploying large language models (LLMs) in confidence-aware systems, where downstream decisions such as retrieval, tool use, and adaptive computation depend on accurately estimating answer reliability. Existing approaches, however, largely treat confidence as a property of completed responses, overlooking how confidence-related information evolves throughout the answering process. In this work, we investigate confidence from a temporal perspective by comparing pre-solution Feeling-of-Knowing (FOK) and post-solution Judgement-of-Learning (JOL) confidence estimates across frontier and open-source LLMs. We show that post-solution confidence is consistently better calibrated and more discriminative than pre-solution confidence, while linear probes trained on hidden representations recover substantially richer confidence-related information than models explicitly verbalise. Building on this observation, we introduce future confidence distillation, which trains predictors operating on pre-solution hidden representations using teacher confidence estimates produced by post-solution correctness probes. Despite requiring only pre-solution representations for inference, distilled predictors recover much of the calibration improvement achieved by post-solution confidence, remain highly sample efficient, and transfer across datasets within the same domain. Together, our findings demonstrate that confidence-related information evolves throughout the answering process and can be anticipated before answer generation is complete, enabling significantly more reliable yet low-cost confidence estimation.

Sahil Kale

University of California, Los Angeles Los Angeles, USA

Confidence Estimation in Language Models Language Model Calibration LLM Uncertainty Estimation Metacognition in Language Models