English
Related papers

Related papers: HATS: Hardness-Aware Trajectory Synthesis for GUI …

200 papers

Enabling Large Language Models (LLMs) to effectively utilize tools in multi-turn interactions is essential for building capable autonomous agents. However, acquiring diverse and realistic multi-turn tool-use data remains a significant…

Computation and Language · Computer Science 2026-01-16 Zhihao Xu , Rumei Li , Jiahuan Li , Rongxiang Weng , Jingang Wang , Xunliang Cai , Xiting Wang

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

The dominant paradigm of monolithic scaling in Vision-Language Models (VLMs) is failing for understanding and reasoning in documents, yielding diminishing returns as it struggles with the inherent need of this domain for document-based…

Computer Vision and Pattern Recognition · Computer Science 2025-11-17 Xinlei Yu , Chengming Xu , Zhangquan Chen , Yudong Zhang , Shilin Lu , Cheng Yang , Jiangning Zhang , Shuicheng Yan , Xiaobin Hu

Simultaneous trajectory prediction for multiple heterogeneous traffic participants is essential for the safe and efficient operation of connected automated vehicles under complex driving situations in the real world. The multi-agent…

Robotics · Computer Science 2021-06-15 Xiaoyu Mo , Yang Xing , Chen Lv

High-level synthesis (HLS) is a powerful tool for developing efficient hardware accelerators that rely on specialized memory systems to achieve sufficient on-chip data reuse and off-chip bandwidth utilization. However, even with HLS,…

Programming Languages · Computer Science 2026-01-26 Izumi Tanaka , Ken Sakayori , Shinya Takamaeda-Yamazaki , Naoki Kobayashi

Large Language Models (LLMs) promise to accelerate discovery by reasoning across the expanding scientific landscape. Yet, the challenge is no longer access to information but connecting it in meaningful, domain-spanning ways. In materials…

Artificial Intelligence · Computer Science 2026-02-10 Isabella A. Stewart , Tarjei Paule Hage , Yu-Chuan Hsu , Markus J. Buehler

The acquisition of agentic capabilities has transformed LLMs from "knowledge providers" to "action executors", a trend that while expanding LLMs' capability boundaries, significantly increases their susceptibility to malicious use. Previous…

Cryptography and Security · Computer Science 2025-05-30 Jinchuan Zhang , Lu Yin , Yan Zhou , Songlin Hu

Large language models (LLMs) are proven to benefit a lot from retrieval-augmented generation (RAG) in alleviating hallucinations confronted with knowledge-intensive questions. RAG adopts information retrieval techniques to inject external…

Computation and Language · Computer Science 2024-10-10 Junda Zhu , Lingyong Yan , Haibo Shi , Dawei Yin , Lei Sha

Sensemaking on a large collection of documents (corpus) is a challenging task often found in fields such as market research, legal studies, intelligence analysis, political science, computational linguistics, etc. Previous works approach…

Human-Computer Interaction · Computer Science 2025-08-13 Sam Yu-Te Lee , Kwan-Liu Ma

Recent studies in Vision-and-Language Navigation (VLN) train RL agents to execute natural-language navigation instructions in photorealistic environments, as a step towards robots that can follow human instructions. However, given the…

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

In today's rapidly evolving field of electronic design automation (EDA), the complexity of hardware designs is increasing, necessitating more sophisticated automation solutions. High-level synthesis (HLS), as a pivotal solution, automates…

Programming Languages · Computer Science 2025-08-06 M Zafir Sadik Khan , Nowfel Mashnoor , Mohammad Akyash , Kimia Azar , Hadi Kamali

The rise of large language models has sparked interest in AI-driven hardware design, raising the question: does high-level synthesis (HLS) still matter in the agentic era? We argue that HLS remains essential. While we expect mature agentic…

Computation and Language · Computer Science 2026-02-10 Niansong Zhang , Sunwoo Kim , Shreesha Srinath , Zhiru Zhang

Graphical User Interface (GUI) agents aim to automate a wide spectrum of human tasks by emulating user interaction. Despite rapid advancements, current approaches are hindered by several critical challenges: data bottleneck in end-to-end…

Artificial Intelligence · Computer Science 2026-01-08 Hongze Mi , Yibo Feng , Wenjie Lu , Yuqi Wang , Jinyuan Li , Song Cao , He Cui , Tengfei Tian , Xuelin Zhang , Haotian Luo , Di Sun , Jun Fang , Hua Chai , Naiqiang Tan , Gang Pan

High-definition (HD) mapping tasks, which perform lane detections and predictions, are extremely challenging due to non-ideal conditions such as view occlusions, distant lane visibility, and adverse weather conditions. Those conditions…

Computer Vision and Pattern Recognition · Computer Science 2026-04-14 Mingyang Li , Brian Lee , Rui Zuo , Brent Bacchus , Priyantha Mudalige , Qinru Qiu

Test-time scaling has become an effective paradigm for improving the reasoning ability of large language models by allocating additional computation during inference. Recent structured approaches have further advanced this paradigm by…

Artificial Intelligence · Computer Science 2026-05-20 George Wu , Nan Jing , Qing Yi , Chuan Hao , Ming Yang , Feng Chang , Yuan Wei , Jian Yang , Ran Tao , Bryan Dai

We propose MADS (Multi-Agent Dialogue Simulation), a scalable framework for generating persuasive multi-turn dialogues via agent self-play. MADS employs three coordinated agents: User Agents designed to simulate diverse persona-driven…

Computation and Language · Computer Science 2025-10-14 Mingjin Li , Yu Liu , Huayi Liu , Xiang Ye , Chao Jiang , Hongguang Zhang , Yu Ruan

The evaluation of Deep Research Agents is a critical challenge, as conventional outcome-based metrics fail to capture the nuances of their complex reasoning. Current evaluation faces two primary challenges: 1) a reliance on singular metrics…

Computation and Language · Computer Science 2026-02-26 Yanyu Chen , Jiyue Jiang , Jiahong Liu , Yifei Zhang , Xiao Guo , Irwin King

The emergence of Large Language Models (LLMs) like ChatGPT has inspired the development of LLM-based agents capable of addressing complex, real-world tasks. However, these agents often struggle during task execution due to methodological…

Computation and Language · Computer Science 2025-01-22 Yaoxiang Wang , Zhiyong Wu , Junfeng Yao , Jinsong Su

Business documents often contain substantial tabular and textual information with numerical values, requiring mathematical reasoning for effective document understanding. While Small Language Models (SLMs) still struggle at this task,…

Machine Learning · Computer Science 2025-08-22 Vishnou Vinayagame , Gregory Senay , Luis Martí