Related papers: OS-Symphony: A Holistic Framework for Robust and G…
Despite rapid developments and widespread applications of MLLM agents, they still struggle with long-form video understanding (LVU) tasks, which are characterized by high information density and extended temporal spans. Recent research on…
Recently, large language models (LLMs) have demonstrated remarkable problem-solving capabilities by autonomously integrating with external tools for collaborative reasoning. However, due to the inherently complex and diverse nature of…
The evolution of Multimodal Large Language Models (MLLMs) has shifted the focus from text generation to active behavioral execution, particularly via OS agents navigating complex GUIs. However, the transition of these agents into…
Long-horizon tasks that require sustained reasoning and multiple tool interactions remain challenging for LLM agents: small errors compound across steps, and even state-of-the-art models often hallucinate or lose coherence. We identify…
Existing efforts in building GUI agents heavily rely on the availability of robust commercial Vision-Language Models (VLMs) such as GPT-4o and GeminiProVision. Practitioners are often reluctant to use open-source VLMs due to their…
Computer-using agents powered by Vision-Language Models (VLMs) have demonstrated human-like capabilities in operating digital environments like mobile platforms. While these agents hold great promise for advancing digital automation, their…
As agent systems powered by large language models (LLMs) advance, improving performance in context understanding, tool usage, and long-horizon execution has become critical. However, existing agent frameworks and benchmarks provide limited…
Long-horizon, repetitive workflows are common in professional settings, such as processing expense reports from receipts and entering student grades from exam papers. These tasks are often tedious for humans since they can extend to extreme…
Despite significant advancements in Large Language Models (LLMs) and Large Vision-Language Models (LVLMs), current models still face substantial challenges in handling complex, multi-turn, and visually-grounded tasks that demand deep…
Computer-Use Agents (CUAs) are emerging as a new paradigm in human-computer interaction, enabling autonomous execution of tasks in desktop environment by perceiving high-level natural-language instructions. As such agents become…
With VLM-powered computer-using agents (CUAs) becoming increasingly capable at graphical user interface (GUI) navigation and manipulation, reliable step-level decision-making has emerged as a key bottleneck for real-world deployment. In…
Most existing Large Language Model (LLM)-based agent frameworks rely on centralized orchestration, incurring high deployment costs, rigid communication topologies, and limited adaptability. To address these challenges, we introduce…
Computer-using agents have shown strong potential to boost human productivity and enable new application forms across platforms. While recent advances have led to usable applications, existing benchmarks fail to account for the internal…
Visual reasoning is dominated by end-to-end neural networks scaled to billions of model parameters and training examples. However, even the largest models struggle with compositional reasoning, generalization, fine-grained spatial and…
Story visualization is the transformation of narrative elements into image sequences. While existing research has primarily focused on visual contextual coherence, the deeper narrative essence of stories often remains overlooked. This…
With the rapid advancements in Large Language Models (LLMs), an increasing number of studies have leveraged LLMs as the cognitive core of agents to address complex task decision-making challenges. Specially, recent research has demonstrated…
The dream to create AI assistants as capable and versatile as the fictional J.A.R.V.I.S from Iron Man has long captivated imaginations. With the evolution of (multi-modal) large language models ((M)LLMs), this dream is closer to reality, as…
Graphical User Interface (GUI) agents powered by Vision-Language Models (VLMs) have demonstrated human-like computer control capability. Despite their utility in advancing digital automation, a critical bottleneck persists: collecting…
Complex, non-linear tasks challenge LLM-enhanced multi-agent systems (MAS) due to partial observability and suboptimal coordination. We propose Orchestrator, a novel MAS framework that leverages attention-inspired self-emergent coordination…
Multimodal large language models (MLLMs) have shown strong capabilities but remain limited to fixed modality pairs and require costly fine-tuning with large aligned datasets. Building fully omni-capable models that can integrate text,…