Large language model-brained gui agents: A survey
GUIs have long been central to human-computer interaction, providing an intuitive and
visually-driven way to access and interact with digital systems. The advent of LLMs …
visually-driven way to access and interact with digital systems. The advent of LLMs …
Memento No More: Coaching AI Agents to Master Multiple Tasks via Hints Internalization
M Alakuijala, Y Gao, G Ananov, S Kaski… - arxiv preprint arxiv …, 2025 - arxiv.org
As the general capabilities of artificial intelligence (AI) agents continue to evolve, their ability
to learn to master multiple complex tasks through experience remains a key challenge …
to learn to master multiple complex tasks through experience remains a key challenge …
Disentangling Exploration of Large Language Models by Optimal Exploitation
Exploration is a crucial skill for self-improvement and open-ended problem-solving.
However, it remains uncertain whether large language models can effectively explore the …
However, it remains uncertain whether large language models can effectively explore the …