相关论文: TimeWarp: Evaluating Web Agents by Revisiting the …
Mobile agents are essential for automating tasks in complex and dynamic mobile environments. As foundation models evolve, the demands for agents that can adapt in real-time and process multimodal data have grown. This survey provides a…
Analysis of aggregate Web traffic has shown that PageRank is a poor model of how people actually navigate the Web. Using the empirical traffic patterns generated by a thousand users over the course of two months, we characterize the…
Scenario testing is an important technique for detecting errors in web systems. Testers draft test scenarios and convert them into test scripts for execution. Early methods relied on testers to convert test scenarios into test scripts.…
GUI agents that interact with graphical interfaces on behalf of users represent a promising direction for practical AI assistants. However, training such agents is hindered by the scarcity of suitable environments. We present InfiniteWeb, a…
In this paper, we provide a general framework for studying multi-agent online learning problems in the presence of delays and asynchronicities. Specifically, we propose and analyze a class of adaptive dual averaging schemes in which agents…
Designing adaptive mechanisms to align individual and collective interests remains a central challenge in artificial social intelligence. Existing methods often struggle with modeling heterogeneous agents possessing persistent latent traits…
Mobile agents can autonomously complete user-assigned tasks through GUI interactions. However, existing mainstream evaluation benchmarks, such as AndroidWorld, operate by connecting to a system-level Android emulator and provide evaluation…
Deep Research systems based on web agents have shown strong potential in solving complex information-seeking tasks, yet their search efficiency remains underexplored. We observe that many state-of-the-art open-source web agents rely on long…
As language models (LMs) are used to build autonomous agents in real environments, ensuring their adversarial robustness becomes a critical challenge. Unlike chatbots, agents are compound systems with multiple components taking actions,…
Efficiently solving real-world problems with LLMs increasingly hinges on their ability to interact with dynamic web environments and autonomously acquire external information. While recent research like Search-R1 and WebDancer demonstrates…
Large language model (LLM) agents have shown increasing promise for collaborative task completion. However, existing multi-agent frameworks often rely on static workflows, fixed roles, and limited inter-agent communication, reducing their…
Recent advances in large language models (LLMs) have enabled the emergence of general-purpose agents for automating end-to-end machine learning (ML) workflows, including data analysis, feature engineering, model training, and competition…
We present WebGym, the largest-to-date open-source environment for training realistic visual web agents. Real websites are non-stationary and diverse, making artificial or small-scale task sets insufficient for robust policy learning.…
Developing autonomous agents that quickly explore an environment and adapt their behavior online is a canonical challenge in robotics and machine learning. While humans are able to achieve such fast online exploration and adaptation, often…
Collaborative multi-agent reinforcement learning has rapidly evolved, offering state-of-the-art algorithms for real-world applications, including sensitive domains. However, a key challenge to its widespread adoption is the lack of a…
LLM agents are increasingly expected to function as general-purpose systems capable of resolving open-ended user requests. While existing benchmarks focus on domain-aware environments for developing specialized agents, evaluating…
In this report, we explore the ability of language model agents to acquire resources, create copies of themselves, and adapt to novel challenges they encounter in the wild. We refer to this cluster of capabilities as "autonomous replication…
Large Language Models (LLMs) have opened transformative possibilities for human-robot collaboration. However, enabling real-time collaboration requires both low latency and robust reasoning, and most LLMs suffer from high latency. To…
We introduce PATHWAYS, a benchmark of 250 multi-step decision tasks that test whether web-based agents can discover and correctly use hidden contextual information. Across both closed and open models, agents typically navigate to relevant…
World models have been emerging as critical components for assessing the consequences of actions generated by interactive agents in online planning and offline evaluation. In text-based environments, world models are typically evaluated and…