Related papers: UI-Genie: A Self-Improving Approach for Iterativel…

Existing online benchmarks for mobile GUI agents remain largely app-centric and task-homogeneous, failing to reflect the diversity and instability of real-world mobile usage. To this end, we introduce VenusBench-Mobile, a challenging online…

With the rapid development of Large Vision Language Models, the focus of Graphical User Interface (GUI) agent tasks shifts from single-screen tasks to complex screen navigation challenges. However, real-world GUI environments, such as PC…

Graphical user interface (GUI) agents have advanced rapidly but still struggle with complex tasks involving novel UI elements, long-horizon actions, and personalized trajectories. In this work, we introduce Instruction Agent, a GUI agent…

Generative Reward Models (GRMs) provide greater flexibility than scalar reward models in capturing human preferences, but their effectiveness is limited by poor reasoning capabilities. This often results in incomplete or overly speculative…

The rapid development of large vision-language model (VLM) has greatly promoted the research of GUI agent. However, GUI agents still face significant challenges in handling long-horizon tasks. First, single-agent models struggle to balance…

Scaling generalist GUI agents is hindered by the data scalability bottleneck of expensive human demonstrations and the "distillation ceiling" of synthetic teacher supervision. To transcend these limitations, we propose UI-Oceanus, a…

The development of GUI agents could revolutionize the next generation of human-computer interaction. Motivated by this vision, we present MAI-UI, a family of foundation GUI agents spanning the full spectrum of sizes, including 2B, 8B, 32B,…

In classical Reinforcement Learning from Human Feedback (RLHF), Reward Models (RMs) serve as the fundamental signal provider for model alignment. As Large Language Models evolve into agentic systems capable of autonomous tool invocation and…

Building autonomous agents that perceive and operate graphical user interfaces (GUIs) like humans has long been a vision in the field of artificial intelligence. Central to these agents is the capability for GUI interaction, which involves…

We study how to endow GUI agents with scalable memory that help generalize across unfamiliar interfaces and long-horizon tasks. Prior GUI agents compress past trajectories into text tokens, which balloons context length and misses decisive…

This paper introduces the design and development of a framework that integrates a large language model (LLM) with a retrieval-augmented generation (RAG) approach leveraging both a knowledge graph and user interaction history. The framework…

AI research agents accelerate ML research by automating hypothesis generation, experimentation, and empirical refinement. Existing agent strategies range from greedy hill-climbing to tree search and evolutionary optimization, yet which…

With the rapid advancement of Vision-Language Models (VLMs), GUI-based mobile agents have emerged as a key development direction for intelligent mobile systems. However, existing agent models continue to face significant challenges in…

In recent years, significant progress has been made in both image generation and generated image detection. Despite their rapid, yet largely independent, development, these two fields have evolved distinct architectural paradigms: the…

The lack of high-quality data for content-grounded generation tasks has been identified as a major obstacle to advancing these tasks. To address this gap, we propose Genie, a novel method for automatically generating high-quality…

MLLM-based GUI agents have demonstrated strong capabilities in complex user interface interaction tasks. However, long-horizon scenarios remain challenging, as these agents are burdened with tasks beyond their intrinsic capabilities,…

We introduce GAIN (Goal-Aligned Decision-Making under Imperfect Norms), a benchmark designed to evaluate how large language models (LLMs) balance adherence to norms against business goals. Existing benchmarks typically focus on abstract…

Designing reward functions for efficiently guiding reinforcement learning (RL) agents toward specific behaviors is a complex task. This is challenging since it requires the identification of reward structures that are not sparse and that…

This study aims to develop an adaptive learning platform that leverages generative AI to automate assessment creation and feedback delivery. The platform provides self-correcting tests and personalised feedback that adapts to each learners…

Automatic evaluation is crucial yet challenging for open-ended natural language generation, especially when rule-based metrics are infeasible. Compared with traditional methods, the recent LLM-as-a-Judge paradigms enable better and more…