AI Co-Mathematician: Accelerating Mathematicians with Agentic AI
This paper introduces the AI co-mathematician as a tool for mathematicians to use AI agents for open-ended research, achieving state-of-the-art results in problem-solving.
Predictive and Prescriptive AI toward Optimizing Wildfire Suppression
This study develops a model to optimize wildfire suppression resource allocation, enhancing decision-making in critical wildfire management.
AI Cap-and-Trade: Efficiency Incentives for Accessibility and Sustainability
The paper proposes a cap-and-trade system focused on increasing AI efficiency to reduce emissions and enhance accessibility for smaller companies.
Automated Clinical Report Generation for Remote Cognitive Remediation
This research compares template systems and LLMs for generating clinical reports in cognitive therapy, revealing trade-offs between reliability and quality.
Characterizing Faults in Agentic AI: A Taxonomy of Types, Symptoms, and Root Causes
This empirical study develops a comprehensive taxonomy of faults in agentic AI systems, contributing to better diagnostics and reliability.
When Should Users Check? Modeling Confirmation Frequency in Multi-Step Agentic AI Tasks
The paper presents a model that optimizes user confirmation points during multi-step tasks, improving AI task execution and user experience.
Beyond Task Success: Measuring Workflow Fidelity in LLM-Based Agentic Payment Systems
This research introduces the Agentic Success Rate metric to evaluate the fidelity of agent workflows in payment systems, improving regulation compliance.
Generative AI Meets 6G and Beyond: Diffusion Models for Semantic Communications
The article reviews diffusion models as foundational components in generative semantic communications, crucial for the development of next-generation wireless networks.
LAMP: Look-Ahead Mixed-Precision Inference of Large Language Models
This paper proposes a mixed-precision strategy for transformers that optimizes computational resources while maintaining accuracy.
Agentic AIs Are the Missing Paradigm for Out-of-Distribution Generalization in Foundation Models
The authors argue that agentic systems are essential for addressing out-of-distribution challenges in foundation models, advocating for a shift in research focus.