arXiv AI
Designing Proactive Thought Partners for Writing
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
Hugging Face Trending Papers
Sep 1
Designing Proactive Thought Partners for Writing
Writing involves diverse cognitive activities, from ideation to revision, and writers' needs vary across individuals and moments. Proactive AI promises to provide the right support at the right time,...
arXiv AI
Sep 1
Towards Cognitive Process-Aware Proactive Writing Support
The paper proposes a proactive writing support system that infers users’ needs from their writing interactions, using Flower and Hayes’ cognitive process theory as a framework. By mapping six cognitive processes to 14 specific support types and associated interaction behaviors, the authors develop AToM CoWriter, which offers context-aware suggestions without requiring explicit prompts. Two within-subjects studies with 21 participants show that this approach improves expressiveness, idea exploration, and engagement with proactive suggestions.
arXiv AI
Jun 11
Designing AI-Supported Focus Groups: A Role x Modality Playbook
arXiv:2606. 11835v1 Announce Type: cross Abstract: Collecting participants' lived experiences is central to design research.
Hugging Face Trending Papers
Jul 4
ProACT: Towards Breakdown-Aware Proactive Agent in Multi-User Collaboration
Conversational agents are increasingly embedded in human collaborative work, yet they remain fundamentally passive and reactive: they respond to explicit user requests rather than proactively recognizing moments when a team would benefit from timely intervention as human collaborators often do. This reactive design substantially limits the use of agents as active participants in multi-user collaboration, where disagreements, ambiguous goals, forgotten constraints, underspecified plans, discussion loops, and imbalanced participation can gradually undermine group progress.
arXiv AI
5d ago
PeerPen: AI-Assisted Writing for Online Mental Health Peer Support
arXiv:2609.14886v1 Announce Type: cross Abstract: Online mental health communities thrive on peer support, yet those who volunteer to help often lack formal training and may struggle to articulate su...
arXiv AI
Jun 11
Nonslop: A Gamified Experiment in Human-AI Collaborative Writing
arXiv:2606. 12350v1 Announce Type: new Abstract: The rapid proliferation of large language models (LLMs) raises critical questions about human creativity and individual expression in an era of AI-assisted creation.