A reinforcement learning agent for timing GenAI access improved post-test performance and metacognitive accuracy over unrestricted or fully restricted conditions in a lab study with 105 students.
Thematic analysis
10 Pith papers cite this work. Polarity classification is still indexing.
10
Pith papers citing it
citation-role summary
background 1
method 1
citation-polarity summary
representative citing papers
Summary reasoning traces from LLMs maintain task performance and increase trust and appeal relative to answer-only or full-trace conditions, but none of the formats improve users' metacognitive calibration on reasoning tasks.
Oversight strategy in computer-use agents shapes exposure to problematic actions more reliably than correction success, with plan-based approaches reducing occurrences but not uniformly improving interventions.
A qualitative study with 22 creative writers finds that the reflective value of AI refusals depends on alignment with users' situational thinking phases, cognitive beliefs, and views of AI roles.
PRISM-XR adds edge-based sensitive-data filtering and quick registration to MLLM-driven XR collaboration, reporting 90% request accuracy, sub-0.3s registration, and over 90% sensitive-object filtering in a 28-person study.
A taxonomy and design space for chart annotations synthesized from qualitative coding of 1,800 static real-world examples.
Robo-Blocks is an LLM-augmented block-based tool that supplies generative scaffolding via structured narratives; a deployment study with novices surfaced user personas, usage patterns, and design insights for integrating such scaffolding into social-robot programming practice.
Developers anticipate code review staying central with more automation and broader scope, while highlighting tensions around understanding, accountability, and trust in AI-mediated processes.
Literature on system prompts for AI shows fragmented and contradictory claims that complicate policy efforts to use them as reliable governance mechanisms.