English
Related papers

Related papers: OS-Marathon: Benchmarking Computer-Use Agents on L…

200 papers

Contemporary multi-agent systems encounter persistent challenges in cross-platform interoperability, dynamic task scheduling, and efficient resource sharing. Agents with heterogeneous implementations often lack standardized interfaces;…

Artificial Intelligence · Computer Science 2025-07-08 Yuyang Cheng , Yumiao Xu , Chaojia Yu , Yong Zhao

Current agentic frameworks underperform on long-horizon tasks. As reasoning depth increases, sequential orchestration becomes brittle, context windows impose hard limits that degrade performance, and opaque execution traces make failures…

Artificial Intelligence · Computer Science 2026-02-17 Salaheddin Alzu'bi , Baran Nama , Arda Kaz , Anushri Eswaran , Weiyuan Chen , Sarvesh Khetan , Rishab Bala , Tu Vu , Sewoong Oh

Recent advances in coding agents suggest rapid progress toward autonomous software development, yet existing benchmarks fail to rigorously evaluate the long-horizon capabilities required to build complete software systems. Most prior…

Large language model (LLM) agents are fundamentally constrained by context length on long-horizon tasks. We introduce Context-Folding, a framework that empowers agents to actively manage their working context. An agent can procedurally…

Computation and Language · Computer Science 2025-10-15 Weiwei Sun , Miao Lu , Zhan Ling , Kang Liu , Xuesong Yao , Yiming Yang , Jiecao Chen

Evaluating mathematical capabilities is critical for assessing the overall performance of large language models (LLMs). However, existing evaluation methods often focus solely on final answers, resulting in highly inaccurate and…

Artificial Intelligence · Computer Science 2025-03-14 Shu-Xun Yang , Cunxiang Wang , Yidong Wang , Xiaotao Gu , Minlie Huang , Jie Tang

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

Multi-agent reinforcement learning (MARL) is a powerful paradigm for solving cooperative and competitive decision-making problems. While many MARL benchmarks have been proposed, few combine continuous state and action spaces with…

Artificial Intelligence · Computer Science 2025-11-18 Artem Pshenitsyn , Aleksandr Panov , Alexey Skrynnik

With VLM-powered computer-using agents (CUAs) becoming increasingly capable at graphical user interface (GUI) navigation and manipulation, reliable step-level decision-making has emerged as a key bottleneck for real-world deployment. In…

Artificial Intelligence · Computer Science 2025-12-19 Zhenyu Wu , Jingjing Xie , Zehao Li , Bowen Yang , Qiushi Sun , Zhaoyang Liu , Zhoumianze Liu , Yu Qiao , Xiangyu Yue , Zun Wang , Zichen Ding

With the advancement of large language models (LLMs) and the expansion of their context windows, existing long-context benchmarks fall short in effectively evaluating the models' comprehension and reasoning abilities in extended texts.…

Computation and Language · Computer Science 2024-06-27 Lei Zhang , Yunshui Li , Ziqiang Liu , Jiaxi yang , Junhao Liu , Longze Chen , Run Luo , Min Yang

A critical limitation in large-scale multi-agent systems is the cascading of errors. And without intermediate verification, downstream agents exacerbate upstream inaccuracies, resulting in significant quality degradation. To bridge this…

Multiagent Systems · Computer Science 2026-03-18 Churong Liang , Jinling Gan , Kairan Hong , Qiushi Tian , Zongze Wu , Runnan Li

Recent Computer-Using Agents (CUAs), powered by multimodal large language models (LLMs), offer a promising direction for automating complex desktop workflows through natural language. However, most existing CUAs remain conceptual…

Human computation refers to the outsourcing of computation tasks to human workers. It offers a new direction for solving a variety of problems and calls for innovative ways of managing human computation processes. The majority of human…

Human-Computer Interaction · Computer Science 2012-04-17 Lu Xiao

AI agents hold growing promise for accelerating scientific discovery; yet, a lack of frontier evaluations hinders adoption into real workflows. Expert-written benchmarks have proven effective at measuring AI reasoning, but most at this…

Heterogeneous hardware and dynamic workloads worsen long-standing OS bottlenecks in scalability, adaptability, and manageability. At the same time, advances in machine learning (ML), large language models (LLMs), and agent-based methods…

Operating Systems · Computer Science 2025-11-12 Yifan Zhang , Xinkui Zhao , Ziying Li , Guanjie Cheng , Jianwei Yin , Lufei Zhang , Zuoning Chen

Controlling desktop applications via software remains a fundamental yet under-served problem. Existing multi-modal large language models (MLLMs) ingest screenshots and task instructions to generate keystrokes and mouse events, but they…

Artificial Intelligence · Computer Science 2025-09-24 Zihan Dong , Xinyu Fan , Zixiang Tang , Yunqing Li

As concerns surrounding AI-driven labor displacement intensify in knowledge-intensive sectors, existing benchmarks fail to measure performance on tasks that define practical professional expertise. Finance, in particular, has been…

Large Language Models (LLMs) have shown remarkable capabilities in solving diverse tasks. However, their proficiency in iteratively optimizing complex solutions through learning from previous feedback remains insufficiently explored. To…

Artificial Intelligence · Computer Science 2025-06-13 Xiaozhe Li , Jixuan Chen , Xinyu Fang , Shengyuan Ding , Haodong Duan , Qingwen Liu , Kai Chen

Autonomous agents operating in domains such as robotics or video game simulations must adapt to changing tasks without forgetting about the previous ones. This process called Continual Reinforcement Learning poses non-trivial difficulties,…

Machine Learning · Computer Science 2026-02-02 Anthony Kobanda , Odalric-Ambrym Maillard , Rémy Portelas

Complex, non-linear tasks challenge LLM-enhanced multi-agent systems (MAS) due to partial observability and suboptimal coordination. We propose Orchestrator, a novel MAS framework that leverages attention-inspired self-emergent coordination…

Multiagent Systems · Computer Science 2025-09-09 Lukas Beckenbauer , Johannes-Lucas Loewe , Ge Zheng , Alexandra Brintrup