English
Related papers

Related papers: Grounding Open-Domain Instructions to Automate Web…

200 papers

Autonomous web agents powered by large language models (LLMs) have shown promise in completing complex browser tasks, yet they still struggle with long-horizon workflows. A key bottleneck is the grounding gap in existing skill formulations:…

AI-powered web agents have the potential to automate repetitive tasks, such as form filling, information retrieval, and scheduling, but they struggle to reliably execute these tasks without human intervention, requiring users to provide…

Human-Computer Interaction · Computer Science 2026-01-27 Yimeng Liu , Misha Sra , Jeevana Priya Inala , Chenglong Wang

Grounding language to the visual observations of a navigating agent can be performed using off-the-shelf visual-language models pretrained on Internet-scale data (e.g., image captions). While this is useful for matching images to natural…

Robotics · Computer Science 2023-03-09 Chenguang Huang , Oier Mees , Andy Zeng , Wolfram Burgard

Command-line bioinformatics tools remain essential for genomic analysis, yet their diversity in syntax and parameterization presents a persistent barrier to productive research. We present oxo-call, a Rust-based command-line assistant that…

Genomics · Quantitative Biology 2026-04-15 Yun Peng , Yujun Sun , Jia Ding , Bin Yan , Zhangyu Wang , Chunyang Wang , Chenyang Shu , Jian-Guo Zhou , Shixiang Wang

For a long time, different recommendation tasks typically require designing task-specific architectures and training objectives. As a result, it is hard to transfer the learned knowledge and representations from one task to another, thus…

Information Retrieval · Computer Science 2023-01-04 Shijie Geng , Shuchang Liu , Zuohui Fu , Yingqiang Ge , Yongfeng Zhang

To make robots accessible to a broad audience, it is critical to endow them with the ability to take universal modes of communication, like commands given in natural language, and extract a concrete desired task specification, defined using…

Computation and Language · Computer Science 2023-03-22 Jiayi Pan , Glen Chou , Dmitry Berenson

In the realm of dialogue systems, user simulation techniques have emerged as a game-changer, redefining the evaluation and enhancement of task-oriented dialogue (TOD) systems. These methods are crucial for replicating real user…

Conversational tutoring systems (CTSs) offer learning experiences driven by natural language interaction. They are known to promote high levels of cognitive engagement and benefit learning outcomes, particularly in reasoning tasks.…

Computation and Language · Computer Science 2023-11-15 Robin Schmucker , Meng Xia , Amos Azaria , Tom Mitchell

A robot as a coworker or a cohabitant is becoming mainstream day-by-day with the development of low-cost sophisticated hardware. However, an accompanying software stack that can aid the usability of the robotic hardware remains the…

Can advanced multi-modal models effectively tackle complex web-based tasks? Such tasks are often found on crowdsourcing platforms, where crowdworkers engage in challenging micro-tasks within web-based environments. Building on this idea, we…

Artificial Intelligence · Computer Science 2025-02-25 Kevin Xu , Yeganeh Kordi , Tanay Nayak , Adi Asija , Yizhong Wang , Kate Sanders , Adam Byerly , Jingyu Zhang , Benjamin Van Durme , Daniel Khashabi

Large "instruction-tuned" language models (i.e., finetuned to respond to instructions) have demonstrated a remarkable ability to generalize zero-shot to new tasks. Nevertheless, they depend heavily on human-written instruction data that is…

Computation and Language · Computer Science 2023-05-29 Yizhong Wang , Yeganeh Kordi , Swaroop Mishra , Alisa Liu , Noah A. Smith , Daniel Khashabi , Hannaneh Hajishirzi

This paper aims to efficiently enable large language models (LLMs) to use external knowledge and goal guidance in conversational recommender system (CRS) tasks. Advanced LLMs (e.g., ChatGPT) are limited in domain-specific CRS tasks for 1)…

Computation and Language · Computer Science 2024-05-06 Chuang Li , Yang Deng , Hengchang Hu , Min-Yen Kan , Haizhou Li

Dialogue policy optimisation via reinforcement learning requires a large number of training interactions, which makes learning with real users time consuming and expensive. Many set-ups therefore rely on a user simulator instead of humans.…

Computation and Language · Computer Science 2021-06-17 Hsien-chin Lin , Nurul Lubis , Songbo Hu , Carel van Niekerk , Christian Geishauser , Michael Heck , Shutong Feng , Milica Gašić

Following navigation instructions in natural language requires a composition of language, action, and knowledge of the environment. Knowledge of the environment may be provided via visual sensors or as a symbolic world representation…

Computation and Language · Computer Science 2019-09-20 Tzuf Paz-Argaman , Reut Tsarfaty

Autonomous reinforcement learning agents, like children, do not have access to predefined goals and reward functions. They must discover potential goals, learn their own reward functions and engage in their own learning trajectory.…

Machine Learning · Computer Science 2019-11-11 Nicolas Lair , Cédric Colas , Rémy Portelas , Jean-Michel Dussoux , Peter Ford Dominey , Pierre-Yves Oudeyer

While language models (LMs) have shown potential across a range of decision-making tasks, their reliance on simple acting processes limits their broad deployment as autonomous agents. In this paper, we introduce Language Agent Tree Search…

Artificial Intelligence · Computer Science 2024-06-07 Andy Zhou , Kai Yan , Michal Shlapentokh-Rothman , Haohan Wang , Yu-Xiong Wang

Humans naturally employ linguistic instructions to convey knowledge, a process that proves significantly more complex for machines, especially within the context of multitask robotic manipulation environments. Natural language, moreover,…

Robotics · Computer Science 2024-05-28 Boyuan Zheng , Jianlong Zhou , Fang Chen

To perform household tasks, assistive robots receive commands in the form of user language instructions for tool manipulation. The initial stage involves selecting the intended tool (i.e., object grounding) and grasping it in a…

Robotics · Computer Science 2023-03-01 Chao Tang , Dehao Huang , Lingxiao Meng , Weiyu Liu , Hong Zhang

With the growing capabilities of intelligent systems, the integration of artificial intelligence (AI) and robots in everyday life is increasing. However, when interacting in such complex human environments, the failure of intelligent…

Artificial Intelligence · Computer Science 2020-11-20 Devleena Das , Siddhartha Banerjee , Sonia Chernova

Although deep reinforcement learning has recently been very successful at learning complex behaviors, it requires a tremendous amount of data to learn a task. One of the fundamental reasons causing this limitation lies in the nature of the…

Robotics · Computer Science 2022-09-19 Zhenshan Bing , Alexander Koch , Xiangtong Yao , Kai Huang , Alois Knoll