Related papers: WebWorld: A Large-Scale World Model for Web Agent …
World models are central to building AI agents capable of flexible reasoning and planning. Yet current evaluations (i) test only properties measurable from observed interactions, such as next-frame prediction or task return, and (ii) do not…
World models for interactive video generation have largely focused on single-agent settings, where future observations are generated from a single control signal. However, many generated environments require multi-agent interaction:…
Large Language Models (LLMs) have achieved remarkable success through imitation learning on vast text corpora, but this paradigm creates a training-generation gap and limits robust reasoning. Reinforcement learning (RL) offers a more…
When assessing the quality of coding agents, predominant benchmarks focus on solving single issues on GitHub, such as SWE-Bench. In contrast, in real use, these agents solve more various and complex tasks that involve other skills such as…
The Dreamer algorithm has recently obtained remarkable performance across diverse environment domains by training powerful agents with simulated trajectories. However, the compressed nature of its world model's latent space can result in…
The BrowserGym ecosystem addresses the growing need for efficient evaluation and benchmarking of web agents, particularly those leveraging automation and Large Language Models (LLMs). Many existing benchmarks suffer from fragmentation and…
Multimodal agents are making rapid progress on general computer-use tasks, yet existing benchmarks remain largely confined to browsers and basic desktop applications, falling short in professional software workflows that dominate real-world…
Legged locomotion over various terrains is challenging and requires precise perception of the robot and its surroundings from both proprioception and vision. However, learning directly from high-dimensional visual input is often…
Large Language Model (LLM) agents are rapidly improving to handle increasingly complex web-based tasks. Most of these agents rely on general-purpose, proprietary models like GPT-4 and focus on designing better prompts to improve their…
We introduce LLM-Wikirace, a benchmark for evaluating planning, reasoning, and world knowledge in large language models (LLMs). In LLM-Wikirace, models must efficiently navigate Wikipedia hyperlinks step by step to reach a target page from…
The rise of powerful multimodal LLMs has enhanced the viability of building web agents which can, with increasing levels of autonomy, assist users to retrieve information and complete tasks on various human-computer interfaces. It is hence…
World models are progressively being employed across diverse fields, extending from basic environment simulation to complex scenario construction. However, existing models are mainly trained on domain-specific states and actions, and…
Recently, video-based world models that learn to simulate the dynamics have gained increasing attention in robot learning. However, current approaches primarily emphasize visual generative quality while overlooking physical fidelity,…
Search agents have emerged as a pivotal paradigm for solving open-ended, knowledge-intensive reasoning tasks. However, training these agents via Reinforcement Learning (RL) faces a critical dilemma: interacting with live commercial Web APIs…
World models are a powerful paradigm in AI and robotics, enabling agents to reason about the future by predicting visual observations or compact latent states. The 1X World Model Challenge introduces an open-source benchmark of real-world…
State-of-the-art multimodal web agents, powered by Multimodal Large Language Models (MLLMs), can autonomously execute many web tasks by processing user instructions and interacting with graphical user interfaces (GUIs). Current strategies…
The integration of Vision-Language-Action (VLA) models with World Models has gained increasing attention. One representative approach treats learned World Models as generative simulators, enabling policy optimization entirely within…
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:…
Recent advances have showcased the extraordinary capabilities of Large Language Model (LLM) agents in tackling web-based information-seeking tasks. However, existing efforts mainly focus on single-fact retrieval and rely on outcome-only…
Agent systems powered by large language models (LLMs) have demonstrated impressive performance on repository-level code-generation tasks. However, for tasks such as website codebase generation, which depend heavily on visual effects and…