English
Related papers

Related papers: On Randomness in Agentic Evals

200 papers

Large Language Models (LLMs) based autonomous agents demonstrate multifaceted capabilities to contribute substantially to economic production. However, existing benchmarks remain focused on single agentic capability, failing to capture…

Artificial Intelligence · Computer Science 2026-04-24 Keyu Li , Junhao Shi , Yang Xiao , Mohan Jiang , Jie Sun , Yunze Wu , Dayuan Fu , Shijie Xia , Xiaojie Cai , Tianze Xu , Weiye Si , Wenjie Li , Dequan Wang , Pengfei Liu

Recent advances in agentic frameworks have enabled AI agents to perform complex reasoning and decision-making. However, evidence comparing their reasoning performance, efficiency, and practical suitability remains limited. To address this…

Artificial Intelligence · Computer Science 2026-04-21 Zeeshan Rasheed , Abdul Malik Sami , Muhammad Waseem , Kai-Kristian Kemell , Mika Saari , Pekka Abrahamsson

Agent benchmarks typically report only final outcomes: pass or fail. This threatens evaluation credibility in three ways. First, scores may be inflated or deflated by shortcuts and benchmark artifacts, misrepresenting capability. Second,…

Can AI agents predict whether they will succeed at a task? We study agentic uncertainty by eliciting success probability estimates before, during, and after task execution. All results exhibit agentic overconfidence: some agents that…

Artificial Intelligence · Computer Science 2026-02-09 Jean Kaddour , Srijan Patel , Gbètondji Dovonon , Leo Richter , Pasquale Minervini , Matt J. Kusner

Reliable evaluation is essential for developing and deploying large language models, yet in practice it often requires substantial manual effort: practitioners must identify appropriate benchmarks, reproduce heterogeneous evaluation…

Computation and Language · Computer Science 2026-03-11 Chengyu Shen , Yanheng Hou , Minghui Pan , Runming He , Zhen Hao Wong , Meiyi Qiang , Zhou Liu , Hao Liang , Peichao Lai , Zeang Sheng , Wentao Zhang

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

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

Enterprise agents increasingly operate inside scoped retrieval systems, delegated workflows, and policy-constrained evidence environments. In these settings, access control can be enforced correctly while the system still produces an answer…

Artificial Intelligence · Computer Science 2026-05-08 Krti Tallam

The rapid growth of AI agent ecosystems is transforming how complex tasks are delegated and executed, creating a new challenge of identifying suitable agents for a given task. Unlike traditional tools, agent capabilities are often…

Artificial Intelligence · Computer Science 2026-04-27 Bin Wu , Arastun Mammadli , Xiaoyu Zhang , Emine Yilmaz

As intelligent agents become more generally-capable, i.e. able to master a wide variety of tasks, the complexity and cost of properly evaluating them rises significantly. Tasks that assess specific capabilities of the agents can be…

Artificial Intelligence · Computer Science 2026-02-12 Marc Lanctot , Kate Larson , Ian Gemp , Michael Kaisers

Agentic artificial intelligence (AI) is a natural fit for Internet of Things (IoT) and edge systems, but edge deployments are often constrained to models around 8 billion parameters or smaller. An important question is: How much…

Artificial Intelligence · Computer Science 2026-05-12 Shiqiang Wang , Herbert Woisetschläger

While individual components of agentic architectures have been studied in isolation, there remains limited empirical understanding of how different design dimensions interact within complex multi-agent systems. This study aims to address…

Artificial Intelligence · Computer Science 2026-01-07 Tara Bogavelli , Roshnee Sharma , Hari Subramani

Computer-use agents have rapidly improved on real-world tasks such as web navigation, desktop automation, and software interaction, in some cases surpassing human performance. Yet even when the task and model are unchanged, an agent that…

Artificial Intelligence · Computer Science 2026-04-21 Gonzalo Gonzalez-Pumariega , Saaket Agashe , Jiachen Yang , Ang Li , Xin Eric Wang

AI agents are increasingly embedded in real software systems, where they execute multi-step workflows through multi-turn dialogue, tool invocations, and intermediate decisions. These long execution histories, called agentic traces, make…

Software Engineering · Computer Science 2026-05-12 Reshabh K Sharma , Shraddha Barke , Benjamin Zorn

Agentic systems are modern software systems: they consist of orchestrated modules, expose interfaces, and are deployed in software pipelines. Unlike conventional programs, their execution, i.e., trajectories, is inherently stochastic and…

Software Engineering · Computer Science 2026-04-14 Shuyang Liu , Yang Chen , Rahul Krishna , Saurabh Sinha , Jatin Ganhotra , Reyhan Jabbarvand

We study the selection of agents based on mutual nominations, a theoretical problem with many applications from committee selection to AI alignment. As agents both select and are selected, they may be incentivized to misrepresent their true…

Computer Science and Game Theory · Computer Science 2025-10-23 Javier Cembrano , Felix Fischer , Max Klimm

LLM agents are rapidly evolving from coding assistants into autonomous software engineering systems. However, existing evaluation methodologies remain largely centered on static, isolated, and short-horizon benchmarks that fail to capture…

Software Engineering · Computer Science 2026-05-28 Yipeng Ouyang , Xin Huang , Bingjie Liu , Zhongchun Zheng , Yuhao Gu , Xianwei Zhang

Agentic AI systems are increasingly capable of autonomous data science workflows, yet clinical prediction tasks demand domain expertise that purely automated approaches struggle to provide. We investigate how human guidance of agentic AI…

The rapid rise of autonomous AI systems and advancements in agent capabilities are introducing new risks due to reduced oversight of real-world interactions. Yet agent testing remains nascent and is still a developing science. As AI agents…