paper-with-me

홈 › Papers

DigitalCoach: Communication and Grounding Gaps in Human and Agentic Computer Use Coaching

2026-06-30 · Meng Chen, Anya Ji, Tsung-Han Wu, Tobias Maringgele, David M. Chan, Alane Suhr, Amy Pavel arxiv

Agents are increasingly capable of automating software tasks, but can they teach humans how to use software themselves? We introduce DigitalCoach, a multimodal dataset of 72 human expert-novice computer use coaching sessions consisting of 22,752 dialogue turns grounded in 28.1 hours of screen and input event recordings across five software applications. We use DigitalCoach to evaluate whether state-of-the-art models can teach humans how to use computers. Automated evaluation shows that models differ from humans in how they coach: models provide more direct instructions, but fewer explanations, error diagnoses, and knowledge-check questions. When we fix the coaching method, models produce utterances similar to human references yet poorly grounded in visual context. Interactive evaluation confirms that model coaches cause learners to passively follow instructions without deeper engagement and fall short in visual grounding. DigitalCoach lays a foundation for collaborative and proactive computer use coaching agents.

📄 PDF Abstract BibTeX arXiv:2606.31980

Code (0)

등록된 구현이 없습니다.

Tasks

Visual Grounding

Similar Papers 제목 키워드 기반

Disfluent but effective? A quantitative study of disfluencies and conversational moves in team discourse

2016-12-01 · COLING 2016 12 · Felix Gervits, Kathleen Eberhard, Matthias Scheutz

Situated dialogue systems that interact with humans as part of a team (e.g., robot teammates) need to be able to use information from communication channels to gauge the coordination level and effectiveness of the team. …

Decision MakingSpoken Dialogue Systems

AgenticAI-DialogGen: Topic-Guided Conversation Generation for Fine-Tuning and Evaluating Short- and Long-Term Memories of LLMs

2026-04-14 · Manoj Madushanka Perera, Adnan Mahmood, Kasun Eranda Wijethilake, Quan Z. Sheng arxiv

Recent advancements in Large Language Models (LLMs) have improved their ability to process extended conversational contexts, yet fine-tuning and evaluating short- and long-term memories remain difficult due to the absenc…

Knowledge Graphs

Challenges in Human-Agent Communication

2024-11-28 · Gagan Bansal, Jennifer Wortman Vaughan, Saleema Amershi, Eric Horvitz 외

Remarkable advancements in modern generative foundation models have enabled the development of sophisticated and highly capable autonomous agents that can observe their environment, invoke tools, and communicate with oth…

Agentic AI-assisted coding offers a unique opportunity to instill epistemic grounding during software development

2026-04-23 · Magnus Palmblad, Jared M. Ragland, Benjamin A. Neely arxiv

The capabilities of AI-assisted coding are progressing at breakneck speed. Chat-based vibe coding has evolved into fully fledged AI-assisted, agentic software development using agent scaffolds where the human developer c…

StarBench: A Turn-Based RPG Benchmark for Agentic Multimodal Decision-Making and Information Seeking

2025-10-21 · Haoran Zhang, Chenhao Zhu, Sicong Guo, Hanzhe Guo 외 arxiv

Human players do more than press buttons: they ground what they see on screen into precise keyboard-mouse actions and, when stuck, they seek information before trying again. We ask whether current vision-language models …