paper-with-me

홈 › Papers

The Real Barrier to LLM Agent Usability is Agentic ROI

2025-05-23 · Weiwen Liu, Jiarui Qin, Xu Huang, Xingshan Zeng, Yunjia Xi, Jianghao Lin, Chuhan Wu, Yasheng Wang, Lifeng Shang, Ruiming Tang, Defu Lian, Yong Yu, Weinan Zhang

Large Language Model (LLM) agents represent a promising shift in human-AI interaction, moving beyond passive prompt-response systems to autonomous agents capable of reasoning, planning, and goal-directed action. Despite the widespread application in specialized, high-effort tasks like coding and scientific research, we highlight a critical usability gap in high-demand, mass-market applications. This position paper argues that the limited real-world adoption of LLM agents stems not only from gaps in model capabilities, but also from a fundamental tradeoff between the value an agent can provide and the costs incurred during real-world use. Hence, we call for a shift from solely optimizing model performance to a broader, utility-driven perspective: evaluating agents through the lens of the overall agentic return on investment (Agent ROI). By identifying key factors that determine Agentic ROI--information quality, agent time, and cost--we posit a zigzag development trajectory in optimizing agentic ROI: first scaling up to improve the information quality, then scaling down to minimize the time and cost. We outline the roadmap across different development stages to bridge the current usability gaps, aiming to make LLM agents truly scalable, accessible, and effective in real-world contexts.

📄 PDF Abstract BibTeX arXiv:2505.17767

Code (0)

등록된 구현이 없습니다.

Tasks

Large Language Model

Similar Papers 제목 키워드 기반

From Barriers to Tactics: A Behavioral Science-Informed Agentic Workflow for Personalized Nutrition Coaching

2024-10-17 · Eric Yang, Tomas Garcia, Hannah Williams, Bhawesh Kumar 외

Effective management of cardiometabolic conditions requires sustained positive nutrition habits, often hindered by complex and individualized barriers. Direct human management is simply not scalable, while previous attem…

ManagementNutrition

ReusStdFlow: A Standardized Reusability Framework for Dynamic Workflow Construction in Agentic AI

2026-02-16 · Gaoyang Zhang, Shanghong Zou, Yafang Wang, He Zhang 외 arxiv

To address the ``reusability dilemma'' and structural hallucinations in enterprise Agentic AI,this paper proposes ReusStdFlow, a framework centered on a novel ``Extraction-Storage-Construction'' paradigm. The framework d…

AgenticRL: Self-Refining Agentic Reinforcement Learning for Vision-Conditioned UAV Navigation

2026-06-02 · Roohan Ahmed Khan, Yasheerah Yaqoot, Amir Atef Habel, Muhammad Ahsan Mustafa 외 arxiv

Deep reinforcement learning has shown strong potential for enabling autonomous robots to learn complex navigational tasks. However, its practical use still depends heavily on human designed reward functions and repeated …

Reinforcement Learning

Can AI Lower the Barrier to Cybersecurity? A Human-Centered Mixed-Methods Study of Novice CTF Learning

2026-02-20 · Cathrin Schachner, Jasmin Wachter arxiv

Capture-the-Flag (CTF) competitions serve as gateways into offensive cybersecurity, yet they often present steep barriers for novices due to complex toolchains and opaque workflows. Recently, agentic AI frameworks for cy…

From Queries to Insights: Agentic LLM Pipelines for Spatio-Temporal Text-to-SQL

2025-10-29 · Manu Redd, Tao Zhe, Dongjie Wang arxiv

Natural-language-to-SQL (NL-to-SQL) systems hold promise for democratizing access to structured data, allowing users to query databases without learning SQL. Yet existing systems struggle with realistic spatio-temporal q…