Adapting Like Humans: A Metacognitive Agent with Test-time Reasoning

• URL: http://arxiv.org/abs/2511.23262v1
• Date: Fri, 28 Nov 2025 15:15:47 GMT
• Title: Adapting Like Humans: A Metacognitive Agent with Test-time Reasoning
• Authors: Yang Li, Zhiyuan He, Yuxuan Huang, Zhuhanling Xiao, Chao Yu, Meng Fang, Kun Shao, Jun Wang,
• Abstract summary: Recent Vision-Language Models (VLMs) exhibit strong perceptual reasoning abilities, yet they often struggle to adapt efficiently when encountering novel tasks at test time.<n>In contrast, humans leverage the metacognitive model with memory, enabling continuous strategy refinement through metacognitive control when faced with new challenges.<n>We propose metacognitive test-time reasoning (MCTR), a framework that equips models with the ability to learn, adapt, and improve during test time through metacognitive self-updating.
• Score: 38.92106966820126
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Recent Vision-Language Models (VLMs) exhibit strong perceptual reasoning abilities, yet they often struggle to adapt efficiently when encountering novel tasks at test time. In contrast, humans leverage the metacognitive model with memory, enabling continuous strategy refinement through metacognitive control when faced with new challenges. To bridge this gap, we propose metacognitive test-time reasoning (MCTR), a framework that equips models with the ability to learn, adapt, and improve during test time through metacognitive self-updating. Inspired by the dual structure of human metacognition, MCTR comprises meta-level and object-level VLM reasoning modules, each equipped with dedicated memory systems for hierarchical adaptive reasoning. Specifically, MCTR consists of (1) a meta-reasoning module which incrementally builds a structured memory by discovering and storing task-relevant rules, environmental patterns, and action-outcome relationships from test-time observations as natural language descriptions; and (2) an action-reasoning module that determines optimal actions through context-aware perception and strategic reasoning by dynamically retrieving and integrating knowledge from memory. The action-reasoning module continuously updates its policy through proposed metacognitive test-time reinforcement learning, adapting as knowledge memory evolves. We evaluate MCTR on 45 Atari games (33 seen, 12 unseen). MCTR demonstrates robust test-time adaptation, achieving 9/12 top-1 results on unseen games compared with baselines. Analyses through ablations, learning dynamics, and case studies reveal the complementary contributions of both components and show meta-reasoning evolving toward human-like adaptation strategies.

Related papers

• Fine-Tuning Language Models to Know What They Know [17.81468268125168]
  This study proposes a framework to measure metacognitive ability $d_rmtype2'$ using a dual-prompt method.<n>It then introduces Evolution Strategy for Metacognitive Alignment (ESMA) to bind a model's internal knowledge to its explicit behaviors.<n>ESMA demonstrates robust generalization across diverse untrained settings, indicating a enhancement in the model's ability to reference its own knowledge.
  arXiv  Detail & Related papers  (2026-02-02T04:08:13Z)
• Cognitive Foundations for Reasoning and Their Manifestation in LLMs [63.12951576410617]
  Large language models (LLMs) solve complex problems yet fail on simpler variants, suggesting they achieve correct outputs through mechanisms fundamentally different from human reasoning.<n>We synthesize cognitive science research into a taxonomy of 28 cognitive elements spanning reasoning invariants, meta-cognitive controls, representations for organizing reasoning & knowledge, and transformation operations.<n>We develop test-time reasoning guidance that automatically scaffold successful structures, improving performance by up to 66.7% on complex problems.
  arXiv  Detail & Related papers  (2025-11-20T18:59:00Z)
• PISA: A Pragmatic Psych-Inspired Unified Memory System for Enhanced AI Agency [50.712873697511206]
  Existing work often lacks adaptability to diverse tasks and overlooks the constructive and task-oriented role of AI agent memory.<n>We propose PISA, a pragmatic, psych-inspired unified memory system that treats memory as a constructive and adaptive process.<n>Our empirical evaluation, conducted on the existing LOCOMO benchmark and our newly proposed AggQA benchmark for data analysis tasks, confirms that PISA sets a new state-of-the-art by significantly enhancing adaptability and long-term knowledge retention.
  arXiv  Detail & Related papers  (2025-10-12T10:34:35Z)
• Towards Meta-Cognitive Knowledge Editing for Multimodal LLMs [71.8547241246169]
  We introduce CogEdit, a novel benchmark designed to evaluate MLLMs' meta-cognitive knowledge editing abilities.<n>We propose MIND, a framework that constructs a meta-knowledge memory for self-awareness, employs game-theoretic interactions to monitor knowledge activation, and incorporates label refinement for noise-robust updates.
  arXiv  Detail & Related papers  (2025-09-06T13:26:04Z)
• Fuzzy, Symbolic, and Contextual: Enhancing LLM Instruction via Cognitive Scaffolding [3.553493344868413]
  We study how prompt-level inductive biases influence the cognitive behavior of large language models (LLMs) in instructional dialogue.<n>We introduce a symbolic scaffolding method paired with a short-term memory schema designed to promote adaptive, structured reasoning.<n>Preliminary results show that our full system consistently outperforms baseline variants.
  arXiv  Detail & Related papers  (2025-08-28T20:46:13Z)
• Thinking Beyond Tokens: From Brain-Inspired Intelligence to Cognitive Foundations for Artificial General Intelligence and its Societal Impact [27.722167796617114]
  This paper offers a cross-disciplinary synthesis of artificial intelligence, cognitive neuroscience, psychology, generative models, and agent-based systems.<n>We analyze the architectural and cognitive foundations of general intelligence, highlighting the role of modular reasoning, persistent memory, and multi-agent coordination.<n>We identify key scientific, technical, and ethical challenges on the path to Artificial General Intelligence.
  arXiv  Detail & Related papers  (2025-07-01T16:52:25Z)
• Metacognitive Retrieval-Augmented Large Language Models [43.57020180706832]
  This paper introduces MetaRAG, an approach that combines the retrieval-augmented generation process with metacognition. By integrating this, MetaRAG enables the model to monitor, evaluate, and plan its response strategies. Empirical evaluations show that MetaRAG significantly outperforms existing methods.
  arXiv  Detail & Related papers  (2024-02-18T15:41:31Z)
• Learning Generalizable Representations for Reinforcement Learning via Adaptive Meta-learner of Behavioral Similarities [43.327357653393015]
  We propose a novel meta-learner-based framework for representation learning regarding behavioral similarities for reinforcement learning. We empirically demonstrate that our proposed framework outperforms state-of-the-art baselines on several benchmarks.
  arXiv  Detail & Related papers  (2022-12-26T11:11:23Z)
• Anti-Retroactive Interference for Lifelong Learning [65.50683752919089]
  We design a paradigm for lifelong learning based on meta-learning and associative mechanism of the brain. It tackles the problem from two aspects: extracting knowledge and memorizing knowledge. It is theoretically analyzed that the proposed learning paradigm can make the models of different tasks converge to the same optimum.
  arXiv  Detail & Related papers  (2022-08-27T09:27:36Z)
• On Fast Adversarial Robustness Adaptation in Model-Agnostic Meta-Learning [100.14809391594109]
  Model-agnostic meta-learning (MAML) has emerged as one of the most successful meta-learning techniques in few-shot learning. Despite the generalization power of the meta-model, it remains elusive that how adversarial robustness can be maintained by MAML in few-shot learning. We propose a general but easily-optimized robustness-regularized meta-learning framework, which allows the use of unlabeled data augmentation, fast adversarial attack generation, and computationally-light fine-tuning.
  arXiv  Detail & Related papers  (2021-02-20T22:03:04Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.