238 papers
This paper presents AutoUE, a novel multi-agent system that leverages retrieval-augmented generation and game design patterns to automatically generate, code, and test complete 3D games within Unreal Engine, effectively addressing the complexities of tool usage and workflow orchestration.
The paper proposes Multi-TAP, a multi-criteria target-adaptive persona framework that addresses data sparsity and intra-domain heterogeneity in cross-domain recommendation by explicitly modeling semantic personas and selectively transferring relevant source-domain signals, thereby outperforming state-of-the-art methods on real-world datasets.
This paper proposes and validates a novel approach using GPT-4-powered dialogue systems to facilitate user review creation through interview-based information gathering, demonstrating that the resulting system-generated reviews require less editing and are perceived as more helpful by readers than human-written ones, despite some fluency challenges.
This paper introduces GuideTWSI, a diverse dataset combining synthetic and real-world images to address the scarcity of Tactile Walking Surface Indicator (TWSI) data, specifically bridging the gap between East Asian directional bars and North American/European truncated domes to improve navigation safety for blind and low-vision individuals.
This paper investigates the potential of retrofitting to enhance sensor-powered smart car cabins by identifying limitations in built-in systems through interviews and defining user requirements via participatory design, ultimately offering design recommendations for future retrofit solutions.
This paper analyzes 377 YouTube videos to map the collective knowledge creators share about monetizing Generative AI, identifying ten common use cases and revenue strategies while highlighting structural tensions such as unverifiable income claims and shifting authorship norms in AI-mediated creative labor.
This paper introduces ADAS-TO, the first large-scale naturalistic multimodal dataset of 15,659 ADAS-to-manual takeover events from 327 drivers, which combines kinematic and vision-language analysis to characterize safety-critical scenarios and demonstrate that actionable visual cues often precede takeovers by over three seconds.
This report synthesizes developmental science and industry practice to establish non-negotiable design guardrails for anthropomorphic conversational AI, ensuring these systems prioritize adolescent safety, autonomy, and skill development.
MindfulAgents is a large language model-driven multi-agent system that personalizes mindfulness meditation through expert-aligned script generation and real-time adaptation, significantly improving user engagement, self-awareness, and stress reduction in both short-term and long-term studies.
This paper introduces "notational animating," an interactive animation authoring paradigm that enables users to sketch high-level notations over static drawings, which are then interpreted by AI into formalized animation keyframes through a structured representation and a closed feedback loop for resolving ambiguity.
A randomized experiment involving 400 participants reveals that while AI assistance can enhance both performance and pleasure in close reading poems, the benefits are optimized with a single interpretation rather than multiple, as heavy reliance on AI improves task performance but diminishes the enjoyment of the experience.
This paper presents a neurosymbolic collaboration between an LLM-powered agent, symbolic computation tools, and human researchers that successfully discovered and formally verified a new tight lower bound on the imbalance of Latin squares for the case , demonstrating the potential of AI-human partnerships in pure mathematical discovery.
This paper analyzes all 960 Chess960 starting positions using Stockfish evaluations and a novel information-based metric to reveal a universal White first-move advantage and a highly heterogeneous landscape of strategic complexity and decision asymmetry, demonstrating that the classical chess setup is merely one configuration among many rather than a unique extremum.
The paper introduces CompanionCast, a multi-agent framework that orchestrates specialized AI agents with multimodal detection, context caching, and spatial audio to enhance social presence and emotional sharing during shared media experiences, as validated by improved outcomes in pilot studies with soccer fans.
KrishokBondhu is a voice-enabled, call-center-integrated advisory system for Bengali farmers in Bangladesh that leverages a Retrieval-Augmented Generation (RAG) framework to deliver high-quality, real-time agricultural guidance, achieving a 44.7% performance improvement over existing benchmarks.
The paper introduces Sandpiper, a mixed-initiative system that integrates interactive researcher dashboards with agentic LLMs to enable scalable, privacy-preserving, and rigorous qualitative analysis of large-scale educational discourse while mitigating hallucinations and ensuring methodological consistency.
This prospective feasibility study demonstrates that a conversational AI system (AMIE) can safely and effectively conduct clinical history-taking and generate diagnostic suggestions in a real-world urgent care setting, achieving high patient satisfaction and diagnostic accuracy comparable to primary care providers while requiring no real-time human intervention.
This paper introduces IronEngine, a general AI assistant platform featuring a unified orchestration core and a three-phase pipeline that integrates diverse backends, adaptive memory, and extensive tooling to achieve high task completion rates while separating planning quality from execution capability.
This paper addresses the sub-wavelength sensing accuracy limitations in bistatic wireless systems caused by clock asynchronism by deriving a quantitative mapping between distorted channel ratios and ideal features, enabling a robust framework that leverages signal amplitude to reconstruct fine-grained displacement details with nearly an order-of-magnitude improvement.
This paper addresses the underexplored challenge of generalization in online reinforcement learning for mobile GUI agents by introducing the AndroidWorld-Generalization benchmark and a scalable GRPO-based training system, demonstrating that while RL significantly improves zero-shot performance on unseen task instances, generalization to new templates and applications remains difficult and benefits from test-time few-shot adaptation.