Related papers: Can Current Agents Close the Discovery-to-Applicat…

The development of general-purpose agents requires a shift from executing simple instructions to completing complex, real-world productivity workflows. However, current tool-use benchmarks remain misaligned with real-world requirements,…

Computer-using agents have shown strong potential to boost human productivity and enable new application forms across platforms. While recent advances have led to usable applications, existing benchmarks fail to account for the internal…

Agent benchmarks have become the de facto measure of frontier AI competence, guiding model selection, investment, and deployment. However, reward hacking, where agents maximize a score without performing the intended task, emerges…

Artificial intelligence systems for scientific discovery have demonstrated remarkable potential, yet existing approaches remain largely proprietary and operate in batch-processing modes requiring hours per research cycle, precluding…

We study building multi-task agents in open-world environments. Without human demonstrations, learning to accomplish long-horizon tasks in a large open-world environment with reinforcement learning (RL) is extremely inefficient. To tackle…

The process of scientific discovery relies on an interplay of observations, analysis, and hypothesis generation. Machine learning is increasingly being adopted to address individual aspects of this process. However, it remains an open…

Significant focus has been placed on integrating large language models (LLMs) with various tools in developing general-purpose agents. This poses a challenge to LLMs' tool-use capabilities. However, there are evident gaps between existing…

In long-horizon open-world multi-agent systems, existing methods often treat local anomalies as automatic triggers for communication. This default design introduces coordination noise, interrupts local execution, and overuses public…

Large Language Models (LLMs) have shown great promise in tool-making, yet existing frameworks often struggle to efficiently construct reliable toolsets and are limited to single-task settings. To address these challenges, we propose GATE…

General-purpose agents perform tasks in unfamiliar environments without domain-specific manual customization. Yet no study has systematically measured how agent architecture shapes performance across heterogeneous protocols and diverse…

Collaborative tasks are ubiquitous activities where a form of communication is required in order to reach a joint goal. Collaborative building is one of such tasks. We wish to develop an intelligent builder agent in a simulated building…

Sample inefficiency of deep reinforcement learning methods is a major obstacle for their use in real-world applications. In this work, we show how human demonstrations can improve final performance of agents on the Minecraft minigame…

In order for artificial agents to successfully perform tasks in changing environments, they must be able to both detect and adapt to novelty. However, visual novelty detection research often only evaluates on repurposed datasets such as…

Recent studies have delved into constructing generalist agents for open-world environments like Minecraft. Despite the encouraging results, existing efforts mainly focus on solving basic programmatic tasks, e.g., material collection and…

Production agentic systems make many model calls per user request, and most of those calls are short, structured, and routine. This raises a practical routing question that existing evaluations do not directly answer: which parts of an…

Developing generalist agents capable of solving open-ended tasks in visually rich, dynamic environments remains a core pursuit of embodied AI. While Minecraft has emerged as a compelling benchmark, existing agents often suffer from…

The rapid advancement of artificial intelligence, particularly autonomous agentic systems based on Large Language Models (LLMs), presents new opportunities to accelerate drug discovery by improving in-silico modeling and reducing dependence…

Reinforcement learning agents must generalize beyond their training experience. Prior work has focused mostly on identical training and evaluation environments. Starting from the recently introduced Crafter benchmark, a 2D open world…

Learning agents that are not only capable of taking tests, but also innovating is becoming a hot topic in AI. One of the most promising paths towards this vision is multi-agent learning, where agents act as the environment for each other,…

Constructing general knowledge by learning task-independent models of the world can help agents solve challenging problems. However, both constructing and evaluating such models remains an open challenge. The most common approaches to…