English
Related papers

Related papers: STEVE: A Step Verification Pipeline for Computer-u…

200 papers

Training AI agents to proactively assist humans in daily activities, from routine household tasks to urgent safety situations, requires large-scale visual data. However, capturing such scenarios in the real world is often difficult, costly,…

Computation and Language · Computer Science 2026-05-12 Yu-Hsiang Liu , Yu-Chien Tang , An-Zi Yen

Formal verification offers a path to provably correct software, but writing verified code remains expensive enough that the technique is rarely used in production. Recent large language models can accelerate this work, and recent benchmarks…

Logic in Computer Science · Computer Science 2026-05-28 Leo Yao

Recent advances in Vision-Language-Action (VLA) models, powered by large language models and reinforcement learning-based fine-tuning, have shown remarkable progress in robotic manipulation. Existing methods often treat long-horizon actions…

Robotics · Computer Science 2025-12-25 Feng Xu , Guangyao Zhai , Xin Kong , Tingzhong Fu , Daniel F. N. Gordon , Xueli An , Benjamin Busam

The predominant approach for training web navigation agents is to gather human demonstrations for a set of popular websites and hand-written tasks, but it is becoming clear that human data is an inefficient resource. We develop a pipeline…

Machine Learning · Computer Science 2025-05-23 Brandon Trabucco , Gunnar Sigurdsson , Robinson Piramuthu , Ruslan Salakhutdinov

AI agents are increasingly used to solve complex, multi-step tasks, but existing multi-agent frameworks remain brittle as workflows grow in scale and depth. Small errors at intermediate stages can propagate through agent interactions, while…

Artificial Intelligence · Computer Science 2026-05-26 Andy Xu , Yu-Wing Tai

Self-evolving agents should not train on examples they cannot justify. Data-free self-evolving search agents offer a scalable route to systems that generate their own questions, answer them, and improve from their own feedback without human…

Artificial Intelligence · Computer Science 2026-05-25 Yamato Arai , Yuma Ichikawa

Evaluating and improving the security capabilities of code agents requires high-quality, executable vulnerability tasks. However, existing works rely on costly, unscalable manual reproduction and suffer from outdated data distributions. To…

Cryptography and Security · Computer Science 2026-05-19 Xianzhen Luo , Jingyuan Zhang , Shiqi Zhou , Rain Huang , Chuan Xiao , Qingfu Zhu , Zhiyuan Ma , Xing Yue , Yang Yue , Wencong Zeng , Wanxiang Che

Existing benchmarks for AI coding agents focus on isolated, single-issue tasks such as fixing a bug or adding a small feature. However, real-world software engineering is a long-horizon endeavor: developers interpret high-level…

Software Engineering · Computer Science 2026-05-25 Tue Le , Minh V. T. Thai , Dung Nguyen Manh , Huy Phan Nhat , Nghi D. Q. Bui

Behavior prediction remains one of the most challenging tasks in the autonomous vehicle (AV) software stack. Forecasting the future trajectories of nearby agents plays a critical role in ensuring road safety, as it equips AVs with the…

Artificial Intelligence · Computer Science 2021-11-16 Francis Indaheng , Edward Kim , Kesav Viswanadha , Jay Shenoy , Jinkyu Kim , Daniel J. Fremont , Sanjit A. Seshia

Computer use agents (CUAs) have shown strong potential for automating complex digital workflows, yet their training remains constrained by costly live environment interaction and limited high-quality supervision. Existing filtered behavior…

Artificial Intelligence · Computer Science 2026-05-29 Yifei He , Rui Yang , Hao Bai , Tong Zhang , Han Zhao

Software testing framework can be stated as the process of verifying and validating that a computer program/application works as expected and meets the requirements of the user. Usually testing can be done manually or using tools. Manual…

Software Engineering · Computer Science 2013-07-15 K. Karnavel , V. Divya , Gnanakeerthika , P. Karthika

Large language model agents have exhibited exceptional performance across a range of complex interactive tasks. Recent approaches have utilized tuning with expert trajectories to enhance agent performance, yet they primarily concentrate on…

Computation and Language · Computer Science 2024-09-26 Weimin Xiong , Yifan Song , Xiutian Zhao , Wenhao Wu , Xun Wang , Ke Wang , Cheng Li , Wei Peng , Sujian Li

Large Language Model (LLM)-based agents are increasingly applied to tasks requiring structured reasoning, tool use, and environmental adaptation, such as data manipulation, multistep planning, and computer-use automation. However, despite…

Artificial Intelligence · Computer Science 2025-11-26 Shashank Kirtania , Param Biyani , Priyanshu Gupta , Yasharth Bajpai , Roshni Iyer , Sumit Gulwani , Gustavo Soares

Tool-calling agents are increasingly deployed in real-world customer-facing workflows. Yet most studies on tool-calling agents focus on idealized settings with general, fixed, and well-specified tasks. In real-world applications, user…

Computation and Language · Computer Science 2026-04-23 Ziyi Wang , Yuxuan Lu , Yimeng Zhang , Pei Chen , Ziwei Dong , Jing Huang , Jiri Gesi , Xianfeng Tang , Chen Luo , Qun Liu , Yisi Sang , Hanqing Lu , Manling Li , Jin Lai , Dakuo Wang

Constructing AI models that respond to text instructions is challenging, especially for sequential decision-making tasks. This work introduces a methodology, inspired by unCLIP, for instruction-tuning generative models of behavior without…

Artificial Intelligence · Computer Science 2024-02-06 Shalev Lifshitz , Keiran Paster , Harris Chan , Jimmy Ba , Sheila McIlraith

Vision-and-language navigation requires an agent to navigate through a real 3D environment following natural language instructions. Despite significant advances, few previous works are able to fully utilize the strong correspondence between…

Computer Vision and Pattern Recognition · Computer Science 2020-10-06 Yicong Hong , Cristian Rodriguez-Opazo , Qi Wu , Stephen Gould

Simulation agents are essential for designing and testing systems that interact with humans, such as autonomous vehicles (AVs). These agents serve various purposes, from benchmarking AV performance to stress-testing system limits, but all…

Artificial Intelligence · Computer Science 2025-05-21 Daphne Cornelisse , Aarav Pandya , Kevin Joseph , Joseph Suárez , Eugene Vinitsky

Achieving mastery in real world software engineering tasks is fundamentally bottlenecked by the scarcity of large scale, high quality training data. Scaling such data has been limited by the complexity of environment setup, unit test…

Developing high-performance software is a complex task that requires specialized expertise. We introduce GSO, a benchmark for evaluating language models' capabilities in developing high-performance software. We develop an automated pipeline…

Software Engineering · Computer Science 2025-10-28 Manish Shetty , Naman Jain , Jinjian Liu , Vijay Kethanaboyina , Koushik Sen , Ion Stoica

Recent advances in large language models (LLMs) have enabled a new generation of autonomous agents that operate over sustained periods and manage sensitive resources on behalf of users. Trusted for their ability to act without direct…

Cryptography and Security · Computer Science 2025-12-19 Artem Grigor , Christian Schroeder de Witt , Simon Birnbach , Ivan Martinovic