English
Related papers

Related papers: IntentScore: Intent-Conditioned Action Evaluation …

200 papers

We present Agent S, an open agentic framework that enables autonomous interaction with computers through a Graphical User Interface (GUI), aimed at transforming human-computer interaction by automating complex, multi-step tasks. Agent S…

Artificial Intelligence · Computer Science 2024-10-11 Saaket Agashe , Jiuzhou Han , Shuyu Gan , Jiachen Yang , Ang Li , Xin Eric Wang

Long-term action anticipation from egocentric video is critical for applications such as human-computer interaction and assistive technologies, where anticipating user intent enables proactive and context-aware AI assistance. However,…

Computer Vision and Pattern Recognition · Computer Science 2025-11-18 Qiaohui Chu , Haoyu Zhang , Meng Liu , Yisen Feng , Haoxiang Shi , Liqiang Nie

Personal assistant systems, such as Apple Siri, Google Assistant, Amazon Alexa, and Microsoft Cortana, are becoming ever more widely used. Understanding user intent such as clarification questions, potential answers and user feedback in…

Information Retrieval · Computer Science 2020-02-06 Liu Yang , Minghui Qiu , Chen Qu , Cen Chen , Jiafeng Guo , Yongfeng Zhang , W. Bruce Croft , Haiqing Chen

Agentic Reinforcement Learning (Agentic RL) has achieved notable success in enabling agents to perform complex reasoning and tool use. However, most methods still relies on sparse outcome-based reward for training. Such feedback fails to…

Artificial Intelligence · Computer Science 2026-04-29 Kaixuan Fan , Kaituo Feng , Manyuan Zhang , Tianshuo Peng , Zhixun Li , Yilei Jiang , Shuang Chen , Peng Pei , Xunliang Cai , Xiangyu Yue

Interactive driving scenarios, such as lane changes, merges and unprotected turns, are some of the most challenging situations for autonomous driving. Planning in interactive scenarios requires accurately modeling the reactions of other…

Reward is critical to the evaluation and training of large language models (LLMs). However, existing rule-based or model-based reward methods struggle to generalize to GUI agents, where access to ground-truth trajectories or application…

Artificial Intelligence · Computer Science 2026-04-16 Gaole Dai , Shiqi Jiang , Ting Cao , Yuqing Yang , Yuanchun Li , Rui Tan , Mo Li , Lili Qiu

Vision-language model based graphical user interface (GUI) agents have shown strong interaction capabilities. However, they often behave unfaithfully, relying on memorized shortcuts rather than grounding actions in displayed screen evidence…

Artificial Intelligence · Computer Science 2026-05-05 Haowen Hu , Pengzhou Cheng , Zheng Wu , Lingzhong Dong , Gongshen Liu , Zhuosheng Zhang

AI agents are commonly trained with large datasets of demonstrations of human behavior. However, not all behaviors are equally safe or desirable. Desired characteristics for an AI agent can be expressed by assigning desirability scores,…

Machine Learning · Computer Science 2024-05-08 Tim Franzmeyer , Edith Elkind , Philip Torr , Jakob Foerster , Joao Henriques

How to build AI that understands human intentions, and uses this knowledge to collaborate with people? We describe a computational framework for evaluating models of goal inference in the domain of 3D motor actions, which receives as input…

Artificial Intelligence · Computer Science 2021-12-03 Yingdong Qian , Marta Kryven , Tao Gao , Hanbyul Joo , Josh Tenenbaum

Accurately understanding the intent behind speech, conversation, and writing is crucial to the development of helpful Large Language Model (LLM) assistants. This paper introduces IntentGrasp, a comprehensive benchmark for evaluating the…

Computation and Language · Computer Science 2026-05-11 Yuwei Yin , Chuyuan Li , Giuseppe Carenini

Recently, mobile AI agents have gained increasing attention. Given a task, mobile AI agents can interact with mobile devices in multiple steps and finally form a GUI flow that solves the task. However, existing agents tend to focus on most…

Computation and Language · Computer Science 2025-02-06 Qinzhuo Wu , Wei Liu , Jian Luan , Bin Wang

Fine-tuning facilitates the adaptation of text-to-image generative models to novel concepts (e.g., styles and portraits), empowering users to forge creatively customized content. Recent efforts on fine-tuning focus on reducing training data…

Human-Computer Interaction · Computer Science 2024-01-30 Xingchen Zeng , Ziyao Gao , Yilin Ye , Wei Zeng

Programming languages assume programs directly execute effects. When autonomous systems generate behavior dynamically, this assumption becomes problematic: there is no structural mediation point between deciding to act and acting. We define…

Programming Languages · Computer Science 2026-05-26 Alan L. McCann

While GUI agents have shown impressive capabilities in common computer-use tasks such as OSWorld, current benchmarks mainly focus on isolated and single-application tasks. This overlooks a critical real-world requirement of coordinating…

Artificial Intelligence · Computer Science 2026-05-01 Jinchao Li , Yunxin Li , Chenrui Zhao , Zhenran Xu , Baotian Hu , Min Zhang

The ability to compute an accurate reward function is essential for optimising a dialogue policy via reinforcement learning. In real-world applications, using explicit user feedback as the reward signal is often unreliable and costly to…

Computation and Language · Computer Science 2016-06-03 Pei-Hao Su , Milica Gasic , Nikola Mrksic , Lina Rojas-Barahona , Stefan Ultes , David Vandyke , Tsung-Hsien Wen , Steve Young

Ranking ensemble is a critical component in real recommender systems. When a user visits a platform, the system will prepare several item lists, each of which is generally from a single behavior objective recommendation model. As multiple…

Information Retrieval · Computer Science 2023-04-18 Jiayu Li , Peijie Sun , Zhefan Wang , Weizhi Ma , Yangkun Li , Min Zhang , Zhoutian Feng , Daiyue Xue

Practical deployment of multi-agent systems (MAS) demands strong performance at test time, motivating methods that guide search during inference and selectively spend compute to improve quality. We present the Multi-Agent System Process…

Multiagent Systems · Computer Science 2026-02-16 Milad Yazdani , Mahdi Mostajabdaveh , Zirui Zhou , Ying Xiong

AI agents are vulnerable to prompt injection attacks, where malicious content hijacks agent behavior to steal credentials or cause financial loss. The only known robust defense is architectural isolation that strictly separates trusted task…

Computer vision algorithms performance are near or superior to humans in the visual problems including object recognition (especially those of fine-grained categories), segmentation, and 3D object reconstruction from 2D views. Humans are,…

Computer Vision and Pattern Recognition · Computer Science 2020-11-13 Stuart Synakowski , Qianli Feng , Aleix Martinez

With the development of deep learning, natural language processing technology has effectively improved the efficiency of various aspects of the traditional judicial industry. However, most current efforts focus on tasks within individual…

Computation and Language · Computer Science 2024-09-24 Zhitao He , Pengfei Cao , Chenhao Wang , Zhuoran Jin , Yubo Chen , Jiexin Xu , Huaijun Li , Xiaojian Jiang , Kang Liu , Jun Zhao