English
Related papers

Related papers: ScaleEnv: Scaling Environment Synthesis from Scrat…

200 papers

Recent advances in large language models have enabled LLM-based agents to achieve strong performance on a variety of benchmarks. However, their performance in real-world deployments often that observed on benchmark settings, especially in…

Artificial Intelligence · Computer Science 2026-02-19 Ruipeng Wang , Yuxin Chen , Yukai Wang , Chang Wu , Junfeng Fang , Xiaodong Cai , Qi Gu , Hui Su , An Zhang , Xiang Wang , Xunliang Cai , Tat-Seng Chua

We introduce AgentSynth, a scalable and cost-efficient pipeline for automatically synthesizing high-quality tasks and trajectory datasets for generalist computer-use agents. Leveraging information asymmetry, AgentSynth constructs subtasks…

Computation and Language · Computer Science 2026-03-03 Jingxu Xie , Dylan Xu , Xuandong Zhao , Dawn Song

Today's AI models learn primarily through mimicry and refining, so it is not surprising that they struggle to solve problems beyond the limits set by existing data. To solve novel problems, agents should acquire skills for exploring and…

Artificial Intelligence · Computer Science 2026-03-25 Raj Ghugare , Roger Creus Castanyer , Catherine Ji , Kathryn Wantlin , Jin Schofield , Karthik Narasimhan , Benjamin Eysenbach

The capability of a reinforcement learning (RL) agent heavily depends on the diversity of the learning scenarios generated by the environment. Generation of diverse realistic scenarios is challenging for real-time strategy (RTS)…

Machine Learning · Computer Science 2023-03-30 Abdus Salam Azad , Edward Kim , Qiancheng Wu , Kimin Lee , Ion Stoica , Pieter Abbeel , Sanjit A. Seshia

In Vision-and-Language Navigation (VLN), an agent needs to navigate through the environment based on natural language instructions. Due to limited available data for agent training and finite diversity in navigation environments, it is…

Computer Vision and Pattern Recognition · Computer Science 2022-03-30 Jialu Li , Hao Tan , Mohit Bansal

Large Language Model (LLM) agents are increasingly improved through interaction, yet most self-evolution methods adapt either the policy or the learning environment in isolation. We identify this structural gap as \emph{Agent-Environment…

Computation and Language · Computer Science 2026-05-26 Yihao Hu , Zhihao Wen , Xiujin Liu , Pan Wang , Xin Zhang , Wei Wu

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…

Tool-calling is essential for Large Language Model (LLM) agents to complete real-world tasks. While most existing benchmarks assume simple, perfectly documented tools, real-world tools (e.g., general "search" APIs) are often opaque, lacking…

Computation and Language · Computer Science 2026-02-18 Skyler Hallinan , Thejas Venkatesh , Xiang Ren , Sai Praneeth Karimireddy , Ashwin Paranjape , Yuhao Zhang , Jack Hessel

Progress in software-engineering agents is increasingly constrained by the scarcity of executable, scalable, and realistic data for training and evaluation. This scarcity stems from three fundamental challenges in existing pipelines:…

Artificial Intelligence · Computer Science 2026-03-03 Yucheng Zeng , Shupeng Li , Daxiang Dong , Ruijie Xu , Zimo Chen , Liwei Zheng , Yuxuan Li , Zhe Zhou , Haotian Zhao , Lun Tian , Heng Xiao , Tianshu Zhu , Longkun Hao , Jianmin Wu

Automated GUI agents aims to facilitate user interaction by automatically performing complex tasks in digital environments, such as web, mobile, desktop devices. It receives textual task instruction and GUI description to generate…

Artificial Intelligence · Computer Science 2025-05-02 Jing Huang , Zhixiong Zeng , Wenkang Han , Yufeng Zhong , Liming Zheng , Shuai Fu , Jingyuan Chen , Lin Ma

Real-world data visualization (DV) requires native environmental grounding, cross-platform evolution, and proactive intent alignment. Yet, existing benchmarks often suffer from code-sandbox confinement, single-language creation-only tasks,…

Intelligent agents gather information and perceive semantics within the environments before taking on given tasks. The agents store the collected information in the form of environment models that compactly represent the surrounding…

Computer Vision and Pattern Recognition · Computer Science 2019-08-15 Ue-Hwan Kim , Jin-Man Park , Taek-Jin Song , Jong-Hwan Kim

Vehicle-to-Everything (V2X) collaborative perception extends sensing beyond single vehicle limits through transmission. However, as more agents participate, existing frameworks face two key challenges: (1) the participating agents are…

Computer Vision and Pattern Recognition · Computer Science 2025-11-14 Yueran Zhao , Zhang Zhang , Chao Sun , Tianze Wang , Chao Yue , Nuoran Li

Many challenges remain before AI agents can be deployed in real-world environments. However, one virtue of such environments is that they are inherently multi-agent and contain human experts. Using advanced social intelligence in such an…

Machine Learning · Computer Science 2025-08-22 Eric Ye , Ren Tao , Natasha Jaques

Open-ended image generation is no longer a simple prompt-to-image problem. High-quality generation often requires an agent to combine a model's internal generative ability with external resources. As requests become more diverse and…

Computer Vision and Pattern Recognition · Computer Science 2026-05-25 Sixiang Chen , Zhaohu Xing , Tian Ye , Xinyu Geng , Yunlong Lin , Jianyu Lai , Xuanhua He , Fuxiang Zhai , Jialin Gao , Lei Zhu

Improving open-source models on real-world SWE tasks (solving GITHUB issues) faces two key challenges: 1) scalable curation of execution environments to train these models, and, 2) optimal scaling of test-time compute. We introduce…

Software Engineering · Computer Science 2025-04-11 Naman Jain , Jaskirat Singh , Manish Shetty , Liang Zheng , Koushik Sen , Ion Stoica

The question of whether deep neural networks are good at generalising beyond their immediate training experience is of critical importance for learning-based approaches to AI. Here, we consider tests of out-of-sample generalisation that…

Artificial Intelligence · Computer Science 2020-02-20 Felix Hill , Andrew Lampinen , Rosalia Schneider , Stephen Clark , Matthew Botvinick , James L. McClelland , Adam Santoro

Building human-like agent, which aims to learn and think like human intelligence, has long been an important research topic in AI. To train and test human-like agents, we need an environment that imposes the agent to rich multimodal…

Artificial Intelligence · Computer Science 2021-05-04 Kwanyoung Park , Hyunseok Oh , Youngki Lee

Tool learning enables large language models (LLMs) to interact with external tools and APIs, greatly expanding the application scope of LLMs. However, due to the dynamic nature of external environments, these tools and APIs may become…

Computation and Language · Computer Science 2025-03-03 Guoxin Chen , Zhong Zhang , Xin Cong , Fangda Guo , Yesai Wu , Yankai Lin , Wenzheng Feng , Yasheng Wang

Auto-scaling is an automated approach that dynamically provisions resources for microservices to accommodate fluctuating workloads. Despite the introduction of many sophisticated auto-scaling algorithms, evaluating auto-scalers remains…

Software Engineering · Computer Science 2025-04-14 Shuaiyu Xie , Jian Wang , Yang Luo , Yunqing Yong , Yuzhen Tan , Bing Li
‹ Prev 1 3 4 5 6 7 10 Next ›