Related papers: MobiFlow: Real-World Mobile Agent Benchmarking thr…
Exploratory GUI testing is a particularly demanding setting for MLLM agents: without predefined test scripts, an agent must autonomously navigate an application and discover defects through its own interaction. However, current evaluation…
Recent advancements in Large Language Models (LLMs) have shown significant progress in understanding complex natural language. One important application of LLM is LLM-based AI Agent, which leverages the ability of LLM as well as external…
With the growing adoption of agent-based models in policy evaluation, a pressing question arises: Can such systems effectively simulate and analyze complex social scenarios to inform policy decisions? Addressing this challenge could…
Graphical user interface (GUI)-based mobile agents automate digital tasks on mobile devices by interpreting natural-language instructions and interacting with the screen. While recent methods apply reinforcement learning (RL) to train…
Embodied artificial intelligence emphasizes the role of an agent's body in generating human-like behaviors. The recent efforts on EmbodiedAI pay a lot of attention to building up machine learning models to possess perceiving, planning, and…
With the advancement of multimodal large language models (MLLMs), building GUI agent systems has become an increasingly promising direction--especially for mobile platforms, given their rich app ecosystems and intuitive touch interactions.…
This paper presents the first industry-standard open-source machine learning (ML) benchmark to allow perfor mance and accuracy evaluation of mobile devices with different AI chips and software stacks. The benchmark draws from the expertise…
As multimodal large language models (MLLMs) advance, MLLM-based virtual agents have demonstrated remarkable performance. However, existing benchmarks face significant limitations, including uncontrollable task complexity, extensive manual…
Building Graphical User Interface (GUI) agents is a promising research direction, which simulates human interaction with computers or mobile phones to perform diverse GUI tasks. However, a major challenge in developing generalized GUI…
High-quality dialogue is crucial for e-commerce customer service, yet traditional intent-based systems struggle with dynamic, multi-turn interactions. We present MindFlow+, a self-evolving dialogue agent that learns domain-specific behavior…
Mobile GUI agents exhibit substantial potential to facilitate and automate the execution of user tasks on mobile phones. However, exist mobile GUI agents predominantly privilege autonomous operation and neglect the necessity of active user…
Large language model (LLM) agents have shown increasing promise for collaborative task completion. However, existing multi-agent frameworks often rely on static workflows, fixed roles, and limited inter-agent communication, reducing their…
The development of LLM-based autonomous agents for end-to-end software development represents a significant paradigm shift in software engineering. However, the scientific evaluation of these systems is hampered by significant challenges,…
During last ten years, the number of smartphones and mobile applications has been constantly growing. Android, iOS and Windows Mobile are three mobile platforms that cover almost all smartphones in the world in 2017. Developing a mobile app…
Autonomous mobile GUI agents have attracted increasing attention along with the advancement of Multimodal Large Language Models (MLLMs). However, existing methods still suffer from inefficient learning from failed trajectories and ambiguous…
Mobile application performance is a vital factor for user experience. Yet, performance issues are notoriously difficult to detect in development environments, where they often manifest less conspicuously, making their diagnosis more…
The rise of mobile devices equipped with numerous sensors, such as LiDAR and cameras, has spurred the adoption of multi-modal deep intelligence for distributed sensing tasks, such as smart cabins and driving assistance. However, the arrival…
With the rapid advancement of Large Language Models (LLMs) in code generation, human-AI interaction is evolving from static text responses to dynamic, interactive HTML-based applications, which we term MiniApps. These applications require…
Large language models (LLMs) have shown strong performance on automated software engineering tasks, yet existing benchmarks focus primarily on library-style repositories, leaving mobile application development largely unexplored despite its…
The rise of agentic AI systems, where agents collaborate to perform diverse tasks, poses new challenges with observing, analyzing and optimizing their behavior. Traditional evaluation and benchmarking approaches struggle to handle the…