Related papers: Go-Browse: Training Web Agents with Structured Exp…
Recent advances in deep-research systems have demonstrated the potential for AI agents to autonomously discover and synthesize knowledge from external sources. In this paper, we introduce WebResearcher, a novel framework for building such…
Information seeking is a fundamental requirement for humans. However, existing LLM agents rely heavily on open-web search, which exposes two fundamental weaknesses: online content is noisy and unreliable, and many real-world tasks require…
We introduce WebGames, a comprehensive benchmark suite designed to evaluate general-purpose web-browsing AI agents through a collection of 50+ interactive challenges. These challenges are specifically crafted to be straightforward for…
Recent research in language-guided visual navigation has demonstrated a significant demand for the diversity of traversable environments and the quantity of supervision for training generalizable agents. To tackle the common data scarcity…
Developing autonomous agents for web-based tasks is a core challenge in AI. While Large Language Model (LLM) agents can interpret complex user requests, they often operate as black boxes, making it difficult to diagnose why they fail or how…
Addressing intricate real-world problems necessitates in-depth information seeking and multi-step reasoning. Recent progress in agentic systems, exemplified by Deep Research, underscores the potential for autonomous multi-step research. In…
GUI agents hold significant potential to enhance the experience and efficiency of human-device interaction. However, current methods face challenges in generalizing across applications (apps) and tasks, primarily due to two fundamental…
The development of high-quality datasets is crucial for benchmarking and advancing research in Graphical User Interface (GUI) agents. Despite their importance, existing datasets are often constructed under idealized conditions, overlooking…
We describe WebSuite, the first diagnostic benchmark for generalist web agents, designed to systematically evaluate why agents fail. Advances in AI have led to the rise of numerous web agents that autonomously operate a browser to complete…
Developing high-performance software is a complex task that requires specialized expertise. We introduce GSO, a benchmark for evaluating language models' capabilities in developing high-performance software. We develop an automated pipeline…
Building agents that can explore their environments intelligently is a challenging open problem. In this paper, we make a step towards understanding how a hierarchical design of the agent's policy can affect its exploration capabilities.…
Search intelligence is evolving from Deep Research to Wide Research, a paradigm essential for retrieving and synthesizing comprehensive information under complex constraints in parallel. However, progress in this field is impeded by the…
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…
We develop a general problem setting for training and testing the ability of agents to gather information efficiently. Specifically, we present a collection of tasks in which success requires searching through a partially-observed…
Modern AAA video games feature huge game levels and maps which are increasingly hard for level testers to cover exhaustively. As a result, games often ship with catastrophic bugs such as the player falling through the floor or being stuck…
With recent advancements in large language models, web agents have been greatly improved. However, dealing with complex and dynamic web environments requires more advanced planning and search abilities. Previous studies usually adopt a…
This paper proposes a paradigm shift for affective computing by viewing the affect modeling task as a reinforcement learning process. According to our proposed framework the context (environment) and the actions of an agent define the…
Current approaches rely on zero-shot evaluation due to the absence of training data; while proprietary models such as GPT-4 exhibit strong reasoning capabilities, smaller open-source models remain ineffective at complex tool use. To address…
Graphical User Interface (GUI) agents can automate complex tasks across digital environments, but their development is hindered by the scarcity of high-quality trajectory data for training. Existing approaches rely on expensive human…
Web agents automate browser tasks, ranging from simple form completion to complex workflows like ordering groceries. While current benchmarks evaluate general-purpose performance~(e.g., WebArena) or safety against malicious actions~(e.g.,…