Related papers: WebShop: Towards Scalable Real-World Web Interacti…
Large language model (LLM)-based agents are increasingly deployed in e-commerce shopping. To perform thorough, user-tailored product searches, agents should interpret personal preferences, engage in multi-turn dialogues, and ultimately…
AI agents today are mostly siloed - they either retrieve and reason over vast amount of digital information and knowledge obtained online; or interact with the physical world through embodied perception, planning and action - but rarely…
Recently, large language model (LLM)-based agents have achieved significant success in interactive environments, attracting significant academic and industrial attention. Despite these advancements, current research predominantly focuses on…
We present ScienceWorld, a benchmark to test agents' scientific reasoning abilities in a new interactive text environment at the level of a standard elementary school science curriculum. Despite the transformer-based progress seen in…
Embodied agents designed to assist users with tasks must engage in natural language interactions, interpret instructions, execute actions, and communicate effectively to resolve issues. However, collecting large-scale, diverse datasets of…
LLM-based user simulation is the primary mechanism for end-to-end agent evaluation, yet simulated users are poor proxies for real humans: unconstrained LLM defaults produce a Formalism Ceiling (style match rates of 6-8% against real users),…
Despite the potential of language model-based agents to solve real-world tasks such as web navigation, current methods still struggle with long-horizon tasks with complex action trajectories. In contrast, humans can flexibly solve complex…
Despite rapid progress in autonomous web agents, human involvement remains essential for shaping preferences and correcting agent behavior as tasks unfold. However, current agentic systems lack a principled understanding of when and why…
Building embodied AI systems that can follow arbitrary language instructions in any 3D environment is a key challenge for creating general AI. Accomplishing this goal requires learning to ground language in perception and embodied actions,…
Grounding natural language instructions on the web to perform previously unseen tasks enables accessibility and automation. We introduce a task and dataset to train AI agents from open-domain, step-by-step instructions originally written…
Building reliable computer-use agents requires grounding: accurately connecting natural language instructions to the correct on-screen elements. While large datasets exist for web and mobile interactions, high-quality resources for desktop…
Even in our increasingly text-intensive times, the primary site of language use is situated, co-present interaction. It is primary ontogenetically and phylogenetically, and it is arguably also still primary in negotiating everyday social…
Recent advances in language model (LM) agents and function calling have enabled autonomous, feedback-driven systems to solve problems across various digital domains. To better understand the unique limitations of LM agents, we introduce…
Multi-Agent Reinforcement Learning (MARL) methods have shown promise in enabling agents to learn a shared communication protocol from scratch and accomplish challenging team tasks. However, the learned language is usually not interpretable…
Instruction-following agents must ground language into their observation and action spaces. Learning to ground language is challenging, typically requiring domain-specific engineering or large quantities of human interaction data. To…
The advancement of Large Language Models (LLMs) has led to significant improvements in various service domains, including search, recommendation, and chatbot applications. However, applying state-of-the-art (SOTA) research to industrial…
Large language models (LLMs) have been successfully adapted for interactive decision-making tasks like web navigation. While achieving decent performance, previous methods implicitly assume a forward-only execution mode for the model, where…
Allowing humans to interactively train artificial agents to understand language instructions is desirable for both practical and scientific reasons, but given the poor data efficiency of the current learning methods, this goal may require…
Evaluating recommender systems remains challenging due to the gap between offline metrics and real user behavior, as well as the scarcity of interaction data. Recent work explores large language model (LLM) agents as synthetic users, yet…
Language agents based on large language models (LLMs) have demonstrated great promise in automating web-based tasks. Recent work has shown that incorporating advanced planning algorithms, e.g., tree search, is advantageous over reactive…