Related papers: IntentCUA: Learning Intent-level Representations f…
Recent advances in large language models (LLMs) have increased the demand for comprehensive benchmarks to evaluate their capabilities as human-like agents. Existing benchmarks, while useful, often focus on specific application scenarios,…
The recent development of Agentic AI systems, empowered by autonomous large language models (LLMs) agents with planning and tool-usage capabilities, enables new possibilities for the evolution of industrial automation and reduces the…
Effective planning of long-horizon deformable object manipulation requires suitable abstractions at both the spatial and temporal levels. Previous methods typically either focus on short-horizon tasks or make strong assumptions that…
Computational metacognition represents a cognitive systems perspective on high-order reasoning in integrated artificial systems that seeks to leverage ideas from human metacognition and from metareasoning approaches in artificial…
Complex, long-horizon planning and its combinatorial nature pose steep challenges for learning-based agents. Difficulties in such settings are exacerbated in low data regimes where over-fitting stifles generalization and compounding errors…
LLM-based agents have made significant advancements in interactive environments, such as mobile operations and web browsing, and other domains beyond computer using. Current multi-agent systems universally excel in performance, compared to…
Neural cellular automata represent an evolution of the traditional cellular automata model, enhanced by the integration of a deep learning-based transition function. This shift from a manual to a data-driven approach significantly increases…
GUI task automation streamlines repetitive tasks, but existing LLM or VLM-based planner-executor agents suffer from brittle generalization, high latency, and limited long-horizon coherence. Their reliance on single-shot reasoning or static…
Improving the effectiveness of human-robot interaction requires social robots to accurately infer human goals through robust intention understanding. This challenge is particularly critical in multimodal settings, where agents must…
Long-horizon planning for robot manipulation is a challenging problem that requires reasoning about the effects of a sequence of actions on a physical 3D scene. While traditional task planning methods are shown to be effective for…
Large Language Models have demonstrated remarkable capabilities across diverse domains, yet significant challenges persist when deploying them as AI agents for real-world long-horizon tasks. Existing LLM agents suffer from a critical…
Existing Reinforcement Learning (RL) systems encounter significant challenges when applied to real-world scenarios, primarily due to poor generalization across environments that differ from their training conditions. This thesis explores…
Current Graphical User Interface (GUI) agents operate primarily under a reactive paradigm: a user must provide an explicit instruction for the agent to execute a task. However, an intelligent AI assistant should be proactive, which is…
Large language models (LLMs) show remarkable potential to act as computer agents, enhancing human productivity and software accessibility in multi-modal tasks that require planning and reasoning. However, measuring agent performance in…
The rise of personal assistant agents, e.g., OpenClaw, highlights the growing potential of large language models to support users across everyday life and work. A core challenge in these settings is proactive assistance, since users often…
Decision-making in complex, continuous multi-task environments is often hindered by the difficulty of obtaining accurate models for planning and the inefficiency of learning purely from trial and error. While precise environment dynamics…
Assistive teleoperation enhances efficiency via shared control, yet inter-operator variability, stemming from diverse habits and expertise, induces highly heterogeneous trajectory distributions that undermine intent recognition stability.…
Intent, a critical cognitive notion and mental state, is ubiquitous in human communication and problem-solving. Accurately understanding the underlying intent behind questions is imperative to reasoning towards correct answers. However,…
Effective human-robot collaboration in open-world environments requires joint planning under uncertain conditions. However, existing approaches often treat humans as passive supervisors, preventing autonomous agents from becoming human-like…
AI agents are increasingly deployed to automate complex enterprise workflows, yet evidence of their effectiveness in identity governance is limited. We report results from the first randomized controlled trial (RCT) evaluating an AI agent…