Position: Truly Self-Improving Agents Require Intrinsic Metacognitive Learning

Authors: Tennison Liu, Mihaela Van Der Schaar

ICML 2025 | Venue PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Theoretical In this position paper, we argue that sustainable, generalized self-improvement requires agents to develop intrinsic metacognitive learning abilities. ... Through case studies, we explore diverse forms of intrinsic and extrinsic metacognitive learning, observing that selfimprovement potential increases when metacognitive functions are more intrinsic yet thoughtfully shared between humans and agents.
Researcher Affiliation Academia 1DAMTP, University of Cambridge, Cambridge, UK. Correspondence to: Tennison Liu <EMAIL>.
Pseudocode No The paper does not contain any explicit pseudocode or algorithm blocks. It describes concepts and frameworks textually.
Open Source Code No The paper does not provide any statements or links indicating that source code for its methodology is made available.
Open Datasets No The paper is a position paper that discusses concepts and existing works; it does not present new experimental results based on a dataset for which public access information would be provided.
Dataset Splits No The paper is a position paper and does not involve conducting experiments or using specific datasets that would require detailing dataset splits.
Hardware Specification No The paper is a position paper and does not describe running its own experiments, therefore no hardware specifications are provided.
Software Dependencies No The paper is a position paper and does not describe implementing or running a specific system, therefore no software dependencies with version numbers are provided.
Experiment Setup No The paper is a position paper and does not describe running its own experiments, therefore no specific experimental setup details such as hyperparameters or training configurations are provided.