English
Related papers

Related papers: Truly Self-Improving Agents Require Intrinsic Meta…

200 papers

In this work, we investigate how two factors, metacognitive skills and motivation, would impact student learning across domains. More specifically, our primary goal is to identify the critical, yet robust, interaction patterns of these two…

Human-Computer Interaction · Computer Science 2023-03-27 Mark Abdelshiheed , Guojing Zhou , Mehak Maniktala , Tiffany Barnes , Min Chi

Reinforcement learning has enabled agents to solve challenging tasks in unknown environments. However, manually crafting reward functions can be time consuming, expensive, and error prone to human error. Competing objectives have been…

Machine Learning · Computer Science 2021-02-11 Brendon Matusch , Jimmy Ba , Danijar Hafner

Multi-agent systems built on Large Language Models (LLMs) show exceptional promise for complex collaborative problem-solving, yet they face fundamental challenges stemming from context window limitations that impair memory consistency, role…

Artificial Intelligence · Computer Science 2026-01-13 Sizhe Yuen , Francisco Gomez Medina , Ting Su , Yali Du , Adam J. Sobey

We describe a framework of hybrid cognition by formulating a hybrid cognitive agent that performs hierarchical active inference across a human and a machine part. We suggest that, in addition to enhancing human cognitive functions with an…

Artificial Intelligence · Computer Science 2018-10-08 André Ofner , Sebastian Stober

Neural nets are powerful function approximators, but the behavior of a given neural net, once trained, cannot be easily modified. We wish, however, for people to be able to influence neural agents' actions despite the agents never training…

Machine Learning · Computer Science 2022-02-01 Mycal Tucker , William Kuhl , Khizer Shahid , Seth Karten , Katia Sycara , Julie Shah

A long-standing challenge in Reinforcement Learning is enabling agents to learn a model of their environment which can be transferred to solve other problems in a world with the same underlying rules. One reason this is difficult is the…

Machine Learning · Computer Science 2019-05-16 Kai Olav Ellefsen , Jim Torresen

Meta-learning, or "learning to learn", refers to techniques that infer an inductive bias from data corresponding to multiple related tasks with the goal of improving the sample efficiency for new, previously unobserved, tasks. A key…

Machine Learning · Computer Science 2021-02-24 Sharu Theresa Jose , Osvaldo Simeone

Self-improving AI systems aim to reduce reliance on human engineering by learning to improve their own learning and problem-solving processes. Existing approaches to self-improvement rely on fixed, handcrafted meta-level mechanisms,…

Artificial Intelligence · Computer Science 2026-03-23 Jenny Zhang , Bingchen Zhao , Wannan Yang , Jakob Foerster , Jeff Clune , Minqi Jiang , Sam Devlin , Tatiana Shavrina

Recently, there has been a great deal of research in emergent communication on artificial agents interacting in simulated environments. Recent studies have revealed that, in general, emergent languages do not follow the compositionality…

Computation and Language · Computer Science 2023-01-30 Rishi Hazra , Sonu Dixit , Sayambhu Sen

As more and more AI agents are used in practice, it is time to think about how to make these agents fully autonomous so that they can learn by themselves in a self-motivated and self-supervised manner rather than being retrained…

Artificial Intelligence · Computer Science 2024-03-01 Bing Liu , Eric Robertson , Scott Grigsby , Sahisnu Mazumder

A longstanding goal of artificial intelligence is to create artificial agents capable of learning to perform tasks that require sequential decision making. Importantly, while it is the artificial agent that learns and acts, it is still up…

Artificial Intelligence · Computer Science 2021-07-14 Ruohan Zhang , Faraz Torabi , Garrett Warnell , Peter Stone

Personalized AI agents are becoming central to modern information retrieval, yet most evaluation methodologies remain static, relying on fixed benchmarks and one-off metrics that fail to reflect how users' needs evolve over time. These…

Information Retrieval · Computer Science 2025-10-07 Kirandeep Kaur , Preetam Prabhu Srikar Dammu , Hideo Joho , Chirag Shah

One of the most basic lower bounds in machine learning is that in nearly any nontrivial setting, it takes $\textit{at least}$ $1/\epsilon$ samples to learn to error $\epsilon$ (and more, if the classifier being learned is complex). However,…

Machine Learning · Statistics 2025-06-04 Idan Attias , Avrim Blum , Keziah Naggita , Donya Saless , Dravyansh Sharma , Matthew Walter

The standard theory of model-free reinforcement learning assumes that the environment dynamics are stationary and that agents are decoupled from their environment, such that policies are treated as being separate from the world they…

In sequential machine teaching, a teacher's objective is to provide the optimal sequence of inputs to sequential learners in order to guide them towards the best model. In this paper we extend this setting from current static one-data-set…

Machine Learning · Computer Science 2020-09-15 Mustafa Mert Celikok , Pierre-Alexandre Murena , Samuel Kaski

Machine learning is usually defined in behaviourist terms, where external validation is the primary mechanism of learning. In this paper, I argue for a more holistic interpretation in which finding more probable, efficient and abstract…

Artificial Intelligence · Computer Science 2017-11-07 Johan Loeckx

Metacognition is an important aspect in creative problem solving (CPS) and through this chapter we analyse the meta-reasoning aspects applied in the different processes of monitoring the progress of learners' reasoning and CPS activities.…

Human-Computer Interaction · Computer Science 2025-08-08 Margarida Romero , George Kalmpourtzis

Most of the works on planning and learning, e.g., planning by (model based) reinforcement learning, are based on two main assumptions: (i) the set of states of the planning domain is fixed; (ii) the mapping between the observations from the…

Artificial Intelligence · Computer Science 2018-11-27 Luciano Serafini , Paolo Traverso

The statelessness of foundation models bottlenecks agentic systems' ability to continually learn, a core capability for long-horizon reasoning and adaptation. To address this limitation, agentic systems commonly incorporate memory modules…

Artificial Intelligence · Computer Science 2026-02-10 Yiming Xiong , Shengran Hu , Jeff Clune

Intelligent instruction-following robots capable of improving from autonomously collected experience have the potential to transform robot learning: instead of collecting costly teleoperated demonstration data, large-scale deployment of…

Robotics · Computer Science 2025-02-26 Zhiyuan Zhou , Pranav Atreya , Abraham Lee , Homer Walke , Oier Mees , Sergey Levine