Notice: This website is continuously updated as new conference proceedings and journal volumes are published. Consequently, the figures presented here may differ from those reported in our publications.
A brief overview of our methodology is provided on the Methods page, along with references to publications documenting our approach and links to the code and data used in each study.
The reproducibility variables underlying each score are classified using an automated LLM-based pipeline, validated against a manually labeled dataset. LLM-based classification introduces uncertainty and potential bias; scores should be interpreted as estimates.
Position: Truly Self-Improving Agents Require Intrinsic Metacognitive Learning
Authors: Tennison Liu, Mihaela Van Der Schaar
ICML 2025 | Venue PDF | LLM Run Details | Input Tokens: 21,546 Total number of tokens sent to the LLM as input for this paper's analysis. | Output Tokens: 2,412 Total number of tokens produced by the LLM (including reasoning/thinking tokens) for this paper's analysis.
| 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. |