English
Related papers

Related papers: A2Perf: Real-World Autonomous Agents Benchmark

200 papers

We introduce Agent2 RL-Bench, a compact diagnostic benchmark for evaluating agentic RL post-training, which tests whether LLM agents can autonomously design, implement, debug, and execute post-training pipelines that improve foundation…

Artificial Intelligence · Computer Science 2026-05-14 Wanyi Chen , Xiao Yang , Xu Yang , Tianming Sha , Qizheng Li , Zhuo Wang , Bowen Xian , Fang Kong , Weiqing Liu , Jiang Bian

Web agents, like OpenAI's Operator and Google's Project Mariner, are powerful agentic systems pushing the boundaries of Large Language Models (LLM). They can autonomously interact with the internet at the user's behest, such as navigating…

Artificial Intelligence · Computer Science 2025-11-07 Lars Krupp , Daniel Geißler , Vishal Banwari , Paul Lukowicz , Jakob Karolus

Handling heterogeneity and unpredictability are two core problems in pervasive computing. The challenge is to seamlessly integrate devices with varying computational resources in a dynamic environment to form a cohesive system that can…

Existing research on autonomous driving primarily focuses on urban driving, which is insufficient for characterising the complex driving behaviour underlying high-speed racing. At the same time, existing racing simulation frameworks…

LLMs have made significant progress in complex but easy-to-verify problems, yet they still struggle with discovering the unknown. In this paper, we present \textbf{AlphaResearch}, an autonomous research agent designed to discover new…

Computation and Language · Computer Science 2026-04-02 Zhaojian Yu , Kaiyue Feng , Yilun Zhao , Shilin He , Xiao-Ping Zhang , Arman Cohan

Agentic AI workflows (systems that autonomously plan and act) are becoming widespread, yet their task success rate on complex tasks remains low. A promising solution is inference-time alignment, which uses extra compute at test time to…

Obtaining standardized crowdsourced benchmark of computational methods is a major issue in data science communities. Dedicated frameworks enabling fair benchmarking in a unified environment are yet to be developed. Here we introduce…

Machine Learning · Computer Science 2022-06-28 Zhen Xu , Sergio Escalera , Isabelle Guyon , Adrien Pavão , Magali Richard , Wei-Wei Tu , Quanming Yao , Huan Zhao

Embodied AI requires agents that perceive, act, and anticipate how actions reshape future world states. World models serve as internal simulators that capture environment dynamics, enabling forward and counterfactual rollouts to support…

Computer Vision and Pattern Recognition · Computer Science 2025-12-02 Xinqing Li , Xin He , Le Zhang , Min Wu , Xiaoli Li , Yun Liu

Deep research -- producing comprehensive, citation-grounded reports by searching and synthesizing information from hundreds of live web sources -- marks an important frontier for agentic systems. To rigorously evaluate this ability, four…

Artificial Intelligence · Computer Science 2026-04-21 Jiayu Wang , Yifei Ming , Riya Dulepet , Qinglin Chen , Austin Xu , Zixuan Ke , Frederic Sala , Aws Albarghouthi , Caiming Xiong , Shafiq Joty

Self-driving laboratories (SDLs) close the loop between experiment design, automated execution, and data-driven decision making, and they provide a demanding testbed for agentic AI under expensive actions, noisy and delayed feedback, strict…

Artificial Intelligence · Computer Science 2026-01-27 Xuanzhou Chen , Audrey Wang , Stanley Yin , Hanyang Jiang , Dong Zhang

Modern coding scaffolds turn LLMs into capable software agents, but their ability to follow scaffold-specified instructions remains under-examined, especially when constraints are heterogeneous and persist across interactions. To fill this…

Generative AI agents in life sciences face a critical challenge: determining the optimal approach for diverse queries ranging from simple factoid questions to complex mechanistic reasoning. Traditional methods rely on fixed rules or…

Machine Learning · Computer Science 2025-12-04 Nihir Chadderwala

From professional research to everyday planning, many tasks are bottlenecked by wide-scale information seeking, which is more repetitive than cognitively complex. With the rapid development of Large Language Models (LLMs), automated search…

Computation and Language · Computer Science 2025-08-29 Ryan Wong , Jiawei Wang , Junjie Zhao , Li Chen , Yan Gao , Long Zhang , Xuan Zhou , Zuo Wang , Kai Xiang , Ge Zhang , Wenhao Huang , Yang Wang , Ke Wang

An increasing number of emerging applications, e.g., internet of things, vehicular communications, augmented reality, and the growing complexity due to the interoperability requirements of these systems, lead to the need to change the tools…

Multiagent Systems · Computer Science 2019-01-16 Merim Dzaferagic , M. Majid Butt , Maria Murphy , Nicholas Kaminski , Nicola Marchetti

Environment perception is a fundamental part of the dynamic driving task executed by Autonomous Driving Systems (ADS). Artificial Intelligence (AI)-based approaches have prevailed over classical techniques for realizing the environment…

Robotics · Computer Science 2024-12-24 Iqra Aslam , Abhishek Buragohain , Daniel Bamal , Adina Aniculaesei , Meng Zhang , Andreas Rausch

With the rapid advancement of autonomous driving technology, vehicle-to-everything (V2X) communication has emerged as a key enabler for extending perception range and enhancing driving safety by providing visibility beyond the line of…

This paper documents a case study in agent-driven autonomous reinforcement learning research for quadruped locomotion. The setting was not a fully self-starting research system. A human provided high-level directives through an agentic…

Robotics · Computer Science 2026-03-31 Nimesh Khandelwal , Shakti S. Gupta

From social networks to traffic routing, artificial learning agents are playing a central role in modern institutions. We must therefore understand how to leverage these systems to foster outcomes and behaviors that align with our own…

Multiagent Systems · Computer Science 2022-02-22 Jan Balaguer , Raphael Koster , Christopher Summerfield , Andrea Tacchetti

We introduce xbench, a dynamic, profession-aligned evaluation suite designed to bridge the gap between AI agent capabilities and real-world productivity. While existing benchmarks often focus on isolated technical skills, they may not…

As AI systems move from generating text to accomplishing goals through sustained interaction, the ability to model environment dynamics becomes a central bottleneck. Agents that manipulate objects, navigate software, coordinate with others,…