Related papers: HATS: Hardness-Aware Trajectory Synthesis for GUI …

While GUI agents have advanced rapidly, they often lack the robustness to recover from their own errors, hindering real-world deployment. To bridge this gap at both the evaluation and data levels, we introduce GUI-RobustEval and propose…

Beyond hallucinations, another problem in program synthesis using LLMs is ambiguity in user intent. We illustrate the ambiguity problem in a networking context for LLM-based incremental configuration synthesis of route-maps and ACLs. These…

Using Large Language Models to produce intermediate thoughts, a.k.a. Chain-of-thought (CoT), before providing an answer has been a successful recipe for solving complex language tasks. In robotics, similar embodied CoT strategies,…

The rapid advancements in artificial intelligence (AI) have led to a growing trend of human-AI teaming (HAT) in various fields. As machines continue to evolve from mere automation to a state of autonomy, they are increasingly exhibiting…

Sensemaking report writing often requires multiple refinements in the iterative process. While Large Language Models (LLMs) have shown promise in generating initial reports based on human visual workspace representations, they struggle to…

Vision-language model (VLM) based GUI agents show promise for automating complex desktop and mobile tasks, but face significant challenges in applying reinforcement learning (RL): (1) slow multi-turn interactions with GUI environments for…

Bridging the gap between algorithm development and hardware realization remains a persistent challenge, particularly in latency- and resource-constrained domains such as wireless communication. While MATLAB provides a mature environment for…

Recent vision-language models have strong perceptual ability but their implicit reasoning is hard to explain and easily generates hallucinations on complex queries. Compositional methods improve interpretability, but most rely on a single…

We introduce a new approach to take into account the memory architecture and the memory mapping in the High- Level Synthesis of Real-Time embedded systems. We formalize the memory mapping as a set of constraints used in the scheduling step.…

Recent advances in large language models have prompted researchers to examine their abilities across a variety of linguistic tasks, but little has been done to investigate how models handle the interactions in meaning across words and…

Large-scale, high-quality interaction trajectories are essential for advancing mobile Graphical User Interface (GUI) agents. While existing methods typically rely on labor-intensive human demonstrations or automated model exploration to…

Operational safety at mission-critical work sites is a top priority given the complex and hazardous nature of daily tasks. This paper presents the Human-Agent Risk Navigation and Event Safety System (HARNESS), a modular AI framework…

Harness engineering has emerged as an important inference-time technique for large language model (LLM) agents, aiming to improve long-term performance through task decomposition and guided execution. However, more elaborate harnesses are…

Web-based 'deep research' agents aim to solve complex question - answering tasks through long-horizon interactions with online tools. These tasks remain challenging, as the underlying language models are often not optimized for long-horizon…

Autonomous agents operating on the graphical user interfaces (GUIs) of various applications hold immense practical value. Unlike the large language model (LLM)-based methods which rely on structured texts and customized backends, the…

Continuous path keyboard input has higher inherent ambiguity than standard tapping, because the path trace may exhibit not only local overshoots/undershoots (as in tapping) but also, depending on the user, substantial mid-path excursions.…

Large Language Models (LLMs) have demonstrated impressive capabilities, yet their deployment in high-stakes domains is hindered by inherent limitations in trustworthiness, including hallucinations, instability, and a lack of transparency.…

Real-world multimodal applications often require any-to-any capabilities, enabling both understanding and generation across modalities including text, image, audio, and video. However, integrating the strengths of autoregressive language…

As intelligent systems and multi-agent coordination become increasingly central to real-world applications, there is a growing need for simulation tools that are both scalable and accessible. Existing high-fidelity simulators, while…

Agentic search enables LLMs to solve complex multi-hop questions through iterative reasoning and external search. Despite the effectiveness, these systems often suffer from a critical limitation in practice: agents fail to recognize their…