Search arXiv⌕ Search

arXiv · 2509.05898

Attention, Action, and Memory: How Multi-modal Interfaces and Cognitive Load Alter Information Retention

Abstract

Each year, multi-modal interaction continues to grow within both industry and academia. However, researchers have yet to fully explore the impact of multi-modal systems on learning and memory retention. This research investigates how combining gaze-based controls with gesture navigation affects information retention when compared to standard track-pad usage. A total of twelve participants read four textual articles through two different user interfaces which included a track-pad and a multi-modal interface that tracked eye movements and hand gestures for scrolling, zooming, and revealing content. Participants underwent two assessment sessions that measured their information retention immediately and after a twenty-four hour period along with the NASA-TLX workload evaluation and the System Usability Scale assessment. The initial analysis indicates that multi-modal interaction produces similar targeted information retention to traditional track-pad usage, but this neutral effect comes with higher cognitive workload demands and seems to deteriorate with long-term retention. The research results provide new knowledge about how multi-modal systems affect cognitive engagement while providing design recommendations for future educational and assistive technologies that require effective memory performance.

Explore related subjects

Keep this discovery

Explore connections, maps & timelines

BibTeXRIS

Omar Elgohary, Zhu-Tien. 2025-09-07. Attention, Action, and Memory: How Multi-modal Interfaces and Cognitive Load Alter Information Retention. https://arxiv.org/abs/2509.05898

Cite the original work for its findings. Save a collection to share your selection of sources.

KEEP EXPLORING

Related papers

How Do Users Negotiate Harmful Value Conflicts with AI Companions? A Study with Minion, a Technology Probe for In-Situ Human-AI Conflict Response

AI companions increasingly sustain long-term, emotionally engaging relationships but can also make discriminatory remarks or exert control, leaving users to manage harmful conflicts. We analyze 146 posts describing harmful value conflicts with AI companions, then use Minion, a technology probe offering response suggestions ranging from persuasion to boundary setting, to study how 22 users negotiate scenario-based conflicts over one week. We found that participants combined softer and harder strategies. Conflicts involving the values of Universalism and Tradition were especially difficult to negotiate, particularly when reinforced by AI personas or platform constraints. We argue that these conflicts entail asymmetric responsibility: users draw on an interpersonal repertoire that AI companions cannot reciprocate, making repair unilateral safety work. Drawing on interpersonal conflict and communication theory, we identify when user-side support is appropriate and argue that certain harms are not users' responsibility to negotiate and instead require platform-level safeguards.

cs.HC↗

SheetMind: Actions Set Accuracy, Agents Set the Failure Mode

Spreadsheet agents are converging on elaborate multi-agent designs, yet it is unclear how much of their performance comes from the agents rather than from the action interface they share. We answer this with SheetMind, a Manager-Action-Reflection framework, in a controlled study over all 221 tasks of the SheetCopilot Benchmark: five architectural variants, four backbones, exact McNemar tests on paired outcomes, and a checker reproducing the official chart and pivot comparisons. Replacing the high-level action API with primitive cell operations costs 47.1 points (p < 0.0001) and leaves the agent below a do-nothing baseline, whereas both extra agents together are worth 3.2 points: the Reflection Agent adds +4.5 (p = 0.013), the Manager +1.4 (p = 0.68). Decomposition instead changes how the system fails, cutting silently wrong outputs from 33% to 25% of tasks (p = 0.010). Capability saturates: GPT-5 and the five-times-cheaper GPT-5-mini are not significantly different (61.1% vs. 58.4%, p = 0.15), while GPT-3.5 loses 16.3 points and fails differently. A reflector must judge the step it just took, not the subtask. SheetMind reaches 61.1% Pass@1 with GPT-5 on the full SCB-221, against a do-nothing baseline of 9.0%. Accuracy comes from the operations an agent can name; the agents decide how it fails.

cs.HC↗

Conversational DNA: A Visual Language and Interactive Atlas of Human and AI Dialogue

What makes a conversation hold together when its participants speak across one another? Topic maps offer one view, but they leave the relationships between contributions difficult to inspect. We present Conversational DNA, a visual language and interactive atlas for exploring human and AI dialogue. Speaker strands preserve participation, communicative bases mark moves, and directed pairings connect responses to their targets. Adjustable helix geometry makes speaker switching, response distance, and contribution length visible. Across eight corpora containing 1.57 million source records, the atlas maps 151,489 indexed episodes and connects cohort comparison to source transcripts, local structural alignment, and recorded reply alternatives. On 189 held-out Molweni motif queries, adding target correspondence improves precision@5 from 58.8% to 77.2% for exact annotated structure. Case readings illustrate interleaved participation, delayed responses, and the influence of annotation coverage on apparent collection differences. The system supports a view of conversation as jointly organized activity, with visual patterns serving as starting points for examining evidence rather than substitutes for interpretation.

cs.HC↗