English
Related papers

Related papers: Anchor: Mitigating Artifact Drift in Agent Benchma…

200 papers

Current agentic AI benchmarks predominantly evaluate task completion accuracy, while overlooking critical enterprise requirements such as cost-efficiency, reliability, and operational stability. Through systematic analysis of 12 main…

Artificial Intelligence · Computer Science 2025-11-19 Sushant Mehta

GraphFlow is a visual workflow system designed to improve the reliability of agentic AI automation in multi-step, mission-critical processes. In these workflows, small errors compound rapidly: under an idealized model of independent steps,…

Artificial Intelligence · Computer Science 2026-05-15 Drewry H. Morris , Luis Valles , Reza Hosseini Ghomi

Recent advances in frontier large language models have enabled code review agents that operate in open-ended, reasoning-intensive settings. However, the lack of standardized benchmarks and granular evaluation protocols makes it difficult to…

Software Engineering · Computer Science 2026-03-13 Kristen Pereira , Neelabh Sinha , Rajat Ghosh , Debojyoti Dutta

Autonomous driving systems require comprehensive evaluation in safety-critical scenarios to ensure safety and robustness. However, such scenarios are rare and difficult to collect from real-world driving data, necessitating simulation-based…

Artificial Intelligence · Computer Science 2026-03-04 Zhulin Jiang , Zetao Li , Cheng Wang , Ziwen Wang , Chen Xiong

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

We introduce ARC-AGI-3, an interactive benchmark for studying agentic intelligence through novel, abstract, turn-based environments in which agents must explore, infer goals, build internal models of environment dynamics, and plan effective…

Artificial Intelligence · Computer Science 2026-04-20 ARC Prize Foundation

The rapid deployment of AI agents in commercial settings has outpaced the development of evaluation methodologies that reflect production realities. Existing benchmarks measure agent capabilities through retrospectively curated tasks with…

Terminal-agent benchmarks have become a primary signal for measuring the coding and system-administration capabilities of large language models. As the market for evaluation environments grows, so does the pressure to ship tasks quickly,…

Artificial Intelligence · Computer Science 2026-05-01 Ivan Bercovich

Large language models are shifting from passive information providers to active agents intended for complex workflows. However, their deployment as reliable AI workers in enterprise is stalled by benchmarks that fail to capture the…

AI agents have the potential to aid users on a variety of consequential tasks, including conducting scientific research. To spur the development of useful agents, we need benchmarks that are challenging, but more crucially, directly…

Computation and Language · Computer Science 2024-09-18 Zachary S. Siegel , Sayash Kapoor , Nitya Nagdir , Benedikt Stroebl , Arvind Narayanan

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

We introduce Adaptive Procedural Task Generation (APT-Gen), an approach to progressively generate a sequence of tasks as curricula to facilitate reinforcement learning in hard-exploration problems. At the heart of our approach, a task…

Machine Learning · Computer Science 2021-03-19 Kuan Fang , Yuke Zhu , Silvio Savarese , Li Fei-Fei

The growing deployment of decision-making agents in dynamic environments increases the demand for safety verification. While critical testing scenario generation has emerged as an appealing verification methodology, effectively balancing…

Machine Learning · Computer Science 2025-08-18 Qitong Chu , Yufeng Yue , Danya Yao , Huaxin Pei

Training web agents to navigate complex, real-world websites requires them to master $\textit{subtasks}$ - short-horizon interactions on multiple UI components (e.g., choosing the correct date in a date picker, or scrolling in a container…

Evaluating the general abilities of intelligent agents requires complex simulation environments. Existing benchmarks typically evaluate only one narrow task per environment, requiring researchers to perform expensive training runs on many…

Artificial Intelligence · Computer Science 2022-02-15 Danijar Hafner

Enterprise environments contain a heterogeneous, rapidly growing collection of internal artifacts related to code, data, and many different tools. Critical information for assessing privacy risk and ensuring regulatory compliance is often…

Cryptography and Security · Computer Science 2025-07-30 Chenhao Fang , Yanqing Peng , Rajeev Rao , Matt Sarmiento , Wendy Summer , Arya Pudota , Alex Goncalves , Jordi Mola , Hervé Robert

Post-training via Supervised Fine-Tuning (SFT) and Reinforcement Learning (RL) is crucial for enhancing reasoning in Multimodal Large Language Models (MLLMs), yet existing paradigms often reach a performance bottleneck due to the…

Computer Vision and Pattern Recognition · Computer Science 2026-05-26 Zehao Wang , Yihan Zeng , Zidong Gong , Yuanfan Guo , Feng Zhu , Hongzhi Zhang , Wei Zhang , Wangmeng Zuo

Generative AI agents, software systems powered by Large Language Models (LLMs), are emerging as a promising approach to automate cybersecurity tasks. Among the others, penetration testing is a challenging field due to the task complexity…

Cryptography and Security · Computer Science 2024-10-29 Luca Gioacchini , Marco Mellia , Idilio Drago , Alexander Delsanto , Giuseppe Siracusano , Roberto Bifulco

Next-generation AI must manage vast personal data, diverse tools, and multi-step reasoning, yet most benchmarks remain context-free and single-turn. We present ASTRA-bench (Assistant Skills in Tool-use, Reasoning \& Action-planning), a…

Artificial Intelligence · Computer Science 2026-03-03 Zidi Xiu , David Q. Sun , Kevin Cheng , Maitrik Patel , Josh Date , Yizhe Zhang , Jiarui Lu , Omar Attia , Raviteja Vemulapalli , Oncel Tuzel , Meng Cao , Samy Bengio

Autonomous agents have recently achieved remarkable progress across diverse domains, yet most evaluations focus on short-horizon, fully observable tasks. In contrast, many critical real-world tasks, such as large-scale software development,…