English
Related papers

Related papers: The Stochastic Gap: A Markovian Framework for Pre-…

200 papers

Modern AI benchmarks operate at a complexity that outpaces traditional verification methods. Tasks authored by domain experts often contain implicit assumptions, incomplete environment specifications, and brittle evaluation logic that human…

Computation and Language · Computer Science 2026-05-27 Junlin Wang , Federico Bianchi , Shang Zhu , Fan Nie , Yongchan Kwon , Bhuwan Dhingra , James Zou

Blind-spot mass is a Good-Turing framework for quantifying deployment coverage risk in machine learning. In modern ML systems, operational state distributions are often heavy-tailed, implying that a long tail of valid but rare states is…

Machine Learning · Computer Science 2026-04-08 Biplab Pal , Santanu Bhattacharya , Madanjit Singh

This paper extends the Acemoglu-Restrepo task exposure framework to address the labor market effects of agentic artificial intelligence systems: autonomous AI agents capable of completing entire occupational workflows rather than discrete…

Systems and Control · Electrical Eng. & Systems 2026-04-02 Ravish Gupta , Saket Kumar

We present CAIA, a benchmark exposing a critical blind spot in AI evaluation: the inability of state-of-the-art models to operate in adversarial, high-stakes environments where misinformation is weaponized and errors are irreversible. While…

Artificial Intelligence · Computer Science 2026-01-21 Zeshi Dai , Zimo Peng , Zerui Cheng , Ryan Yihe Li

Reinforcement learning algorithms typically rely on the assumption that the environment dynamics and value function can be expressed in terms of a Markovian state representation. However, when state information is only partially observable,…

Agentic AI prototypes are being deployed across domains with increasing speed, yet no methodology for their structured design, governance, and prospective evaluation has been established. Existing AI documentation practices and guidelines…

Software Engineering · Computer Science 2026-03-02 Sebastian Lobentanzer

Benchmarks are the primary tool for assessing progress in artificial intelligence (AI), yet current practice evaluates models on isolated test suites and provides little guidance for reasoning about generality or autonomous…

Artificial Intelligence · Computer Science 2025-12-05 Przemyslaw Chojecki

Large language model (LLM)-based agents are increasingly used to perform complex, multi-step workflows in regulated settings such as compliance and due diligence. However, many agentic architectures rely primarily on prompt engineering of a…

Artificial Intelligence · Computer Science 2026-02-03 Ananya Joshi , Michael Rudow

Retail supply chain operations in supermarket chains involve continuous, high-volume manual workflows spanning demand forecasting, procurement, supplier coordination, and inventory replenishment, processes that are repetitive,…

The rapid rise of compound AI systems (a.k.a., AI agents) is reshaping the labor market, raising concerns about job displacement, diminished human agency, and overreliance on automation. Yet, we lack a systematic understanding of the…

Computers and Society · Computer Science 2026-02-03 Yijia Shao , Humishka Zope , Yucheng Jiang , Jiaxin Pei , David Nguyen , Erik Brynjolfsson , Diyi Yang

This paper finds that the introduction of agentic AI systems intensifies existing challenges to traditional public sector oversight mechanisms -- which rely on siloed compliance units and episodic approvals rather than continuous,…

Computers and Society · Computer Science 2025-09-03 Chris Schmitz , Jonathan Rystrøm , Jan Batzner

Deep Research Agents (DRAs) are promising agentic systems that gather and synthesize information to support research across domains such as financial decision-making, medical analysis, and scientific discovery. Despite recent improvements…

Artificial Intelligence · Computer Science 2026-02-27 Haotian Zhai , Elias Stengel-Eskin , Pratik Patil , Liu Leqi

This paper studies the performative prediction problem which optimizes a stochastic loss function with data distribution that depends on the decision variable. We consider a setting where the agent(s) provides samples adapted to the…

Optimization and Control · Mathematics 2021-10-05 Qiang Li , Hoi-To Wai

Generative and agentic artificial intelligence is entering financial markets faster than existing governance can adapt. Current model-risk frameworks assume static, well-specified algorithms and one-time validations; large language models…

Computers and Society · Computer Science 2025-12-16 Eren Kurshan , Tucker Balch , David Byrd

Evaluating AI agents on comprehensive benchmarks is expensive because each evaluation requires interactive rollouts with tool use and multi-step reasoning. We study whether small task subsets can preserve agent rankings at substantially…

Artificial Intelligence · Computer Science 2026-03-26 Franck Ndzomga

Large language models are increasingly being used to support network operations (NetOps) and artificial intelligence for IT operations (AIOps), including incident investigation, root-cause analysis, configuration synthesis, and limited…

Networking and Internet Architecture · Computer Science 2026-05-14 Muhammad Bilal , Jon Crowcroft , Ruizhi Wang , Xiaolong Xu , Schahram Dustdar

Earth Observation (EO) is moving beyond static prediction toward multi-step analytical workflows that require coordinated reasoning over data, tools, and geospatial state. While foundation models and vision-language models have advanced…

Computer Vision and Pattern Recognition · Computer Science 2026-05-14 Muhammad Akhtar Munir , Muhammad Umer Sheikh , Akashah Shabbir , Muhammad Haris Khan , Fahad Khan , Xiao Xiang Zhu , Begum Demir , Salman Khan

Artificial intelligence models have shown strong potential in acute ischemic stroke imaging, particularly for lesion detection and segmentation using computed tomography and magnetic resonance imaging. However, most existing approaches…

Image and Video Processing · Electrical Eng. & Systems 2026-01-06 Md Rashadul Islam

Machine-learned systems are in widespread use for making decisions about humans, and it is important that they are fair, i.e., not biased against individuals based on sensitive attributes. We present a general framework of runtime…

Machine Learning · Computer Science 2025-07-08 Thomas A. Henzinger , Mahyar Karimi , Konstantin Kueffner , Kaushik Mallik

Outpatient departments (OPDs) in Indian public hospitals face severe overcrowding, with daily volumes reaching 200--8,000 patients~\cite{aiims2020annual}. The prevailing First-Come-First-Served (FCFS) token system treats all patients…

Systems and Control · Electrical Eng. & Systems 2026-04-02 Ravish Gupta , Saket Kumar , Maulik Dang