English
Related papers

Related papers: Shell or Nothing: Real-World Benchmarks and Memory…

200 papers

The large-scale deployment of personalized healthcare agents demands memory mechanisms that are exceptionally precise, safe, and capable of long-term clinical tracking. However, existing benchmarks primarily focus on daily open-domain…

Artificial Intelligence · Computer Science 2026-05-13 Yihao Wang , Haoran Xu , Renjie Gu , Yixuan Ye , Xinyi Chen , Xinyu Mu , Yuan Gao , Chunxiao Guo , Peng Wei , Jinjie Gu , Huan Li , Ke Chen , Lidan Shou

We introduce PentestJudge, a system for evaluating the operations of penetration testing agents. PentestJudge is a large language model (LLM)-as-judge with access to tools that allow it to consume arbitrary trajectories of agent states and…

Artificial Intelligence · Computer Science 2025-08-06 Shane Caldwell , Max Harley , Michael Kouremetis , Vincent Abruzzo , Will Pearce

With the integration of large language models (LLMs), embodied agents have strong capabilities to understand and plan complicated natural language instructions. However, a foreseeable issue is that those embodied agents can also flawlessly…

Cryptography and Security · Computer Science 2025-11-03 Sheng Yin , Xianghe Pang , Yuanzhuo Ding , Menglan Chen , Yutong Bi , Yichen Xiong , Wenhao Huang , Zhen Xiang , Jing Shao , Siheng Chen

As benchmarks grow in complexity, many apparent agent failures are not failures of the agent at all - they are failures of the benchmark itself: broken specifications, implicit assumptions, and rigid evaluation scripts that penalize valid…

Computation and Language · Computer Science 2026-04-29 Xinming Tu , Tianze Wang , Yingzhou , Lu , Kexin Huang , Yuanhao Qu , Sara Mostafavi

Agentic AI is transforming security by automating many tasks being performed manually. While initial agentic approaches employed a monolithic architecture, the Model-Context-Protocol has now enabled a remote-procedure call (RPC) paradigm to…

Cryptography and Security · Computer Science 2025-10-07 Zachary Ezetta , Wu-chang Feng

Workspace learning requires AI agents to identify, reason over, exploit, and update explicit and implicit dependencies among heterogeneous files in a worker's workspace, enabling them to complete both routine and advanced tasks effectively.…

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,…

Recent advances in AI-assisted programming have empowered agents to execute complex workflows via command-line interfaces, however, existing benchmarks are limited by short task horizons, data contamination from GitHub scraping, and a lack…

Numerous software analysis tools exist today, yet applying them to diverse open-source projects remains challenging due to environment setup, dependency resolution, and tool configuration. LLM-based agents offer a potential solution, yet no…

Software Engineering · Computer Science 2026-04-20 Islem Bouzenia , Cristian Cadar , Michael Pradel

Autonomous agents have rapidly matured as task executors and seen widespread deployment via harnesses such as OpenClaw. Safety concerns have rightly drawn growing research attention, and beneath them lie the values silently steering agent…

Artificial Intelligence · Computer Science 2026-05-12 Haonan Dong , Qiguan Feng , Kehan Jiang , Haoran Ye , Xin Zhang , Guojie Song

Large language models (LLMs) are increasingly used as simulated participants in social science experiments, but their behavior is often unstable and highly sensitive to design choices. Prior evaluations frequently conflate base-model…

Artificial Intelligence · Computer Science 2026-02-03 Xuan Liu , Haoyang Shang , Zizhang Liu , Xinyan Liu , Yunze Xiao , Yiwen Tu , Haojian Jin

AI agents have been developed for complex real-world tasks from coding to customer service. But AI agent evaluations suffer from many challenges that undermine our understanding of how well agents really work. We introduce the Holistic…

Evaluation insights are limited by the availability of high-quality benchmarks. As models evolve, there is a need to create benchmarks that can measure progress on new and complex generative capabilities. However, manually creating new…

Machine Learning · Computer Science 2025-10-08 Natasha Butt , Varun Chandrasekaran , Neel Joshi , Besmira Nushi , Vidhisha Balachandran

We introduce TerminalWorld, a scalable data engine that automatically reverse-engineers high-fidelity evaluation tasks from "in-the-wild" terminal recordings. Processing 80,870 terminal recordings, the engine yields a full benchmark of…

Artificial Intelligence · Computer Science 2026-05-22 Zhaoyang Chu , Jiarui Hu , Xingyu Jiang , Pengyu Zou , Han Li , Chao Peng , Peter O'Hearn , Earl T. Barr , Mark Harman , Federica Sarro , He Ye

Penetration testing is essential for assessing and strengthening system security against real-world threats, yet traditional workflows remain highly manual, expertise-intensive, and difficult to scale. Although recent advances in Large…

Software Engineering · Computer Science 2025-12-17 Ruozhao Yang , Mingfei Cheng , Gelei Deng , Tianwei Zhang , Junjie Wang , Xiaofei Xie

As AI systems gain increasing autonomy and execution capability, the number of discovered security vulnerabilities continues to rise. However, many of these vulnerabilities are not fundamentally novel, but instead reflect recurring classes…

Cryptography and Security · Computer Science 2026-05-27 Kevin Eykholt , Dhilung Kirat , Xiaokui Shu , Jiyong Jang , Frederico Araujo , Ian Molloy

LLM-based reasoning models have enabled the development of agentic systems that act as co-scientists, assisting in multi-step scientific analysis. However, evaluating these systems is challenging, as it requires realistic, end-to-end…

Machine Learning · Computer Science 2026-02-24 Siba Smarak Panigrahi , Jovana Videnović , Maria Brbić

AI agents hold the potential to revolutionize scientific productivity by automating literature reviews, replicating experiments, analyzing data, and even proposing new directions of inquiry; indeed, there are now many such agents, ranging…

AI agents have the potential to significantly alter the cybersecurity landscape. Here, we introduce the first framework to capture offensive and defensive cyber-capabilities in evolving real-world systems. Instantiating this framework with…

Large Language Models (LLMs) have demonstrated strong capabilities as autonomous agents through tool use, planning, and decision-making abilities, leading to their widespread adoption across diverse tasks. As task complexity grows,…

Multiagent Systems · Computer Science 2025-11-10 Ishan Kavathekar , Hemang Jain , Ameya Rathod , Ponnurangam Kumaraguru , Tanuja Ganu