Related papers: MineNPC-Task: Task Suite for Memory-Aware Minecraf…

Existing benchmarks for multimodal memory reasoning largely evaluate systems within pre-assembled contexts, but under-evaluate whether agents can use evidence distributed across independently originated sources. We argue that…

Applications in labor market intelligence demand specialized NLP systems for a wide range of tasks, characterized by extreme multi-label target spaces, strict latency constraints, and multiple text modalities such as skills and job titles.…

Leveraging large language models (LLMs), autonomous agents have significantly improved, gaining the ability to handle a variety of tasks. In open-ended settings, optimizing collaboration for efficiency and effectiveness demands flexible…

Recently, large language model based (LLM-based) agents have been widely applied across various fields. As a critical part, their memory capabilities have captured significant interest from both industrial and academic communities. Despite…

Long-term memory is essential for large language model (LLM) agents operating in complex environments, yet existing memory designs are either task-specific and non-transferable, or task-agnostic but less effective due to low task-relevance…

Recent benchmarks for Large Language Model (LLM) agents primarily focus on evaluating reasoning, planning, and execution capabilities, while another critical component-memory, encompassing how agents memorize, update, and retrieve long-term…

Large language model (LLM)-powered multi-agent systems (MAS) demonstrate remarkable collective intelligence, wherein multi-agent memory serves as a pivotal mechanism for continual adaptation. However, existing multi-agent memory designs…

Stateful tool-using LLM agents treat the context window as working memory, yet today's agent harnesses manage residency and durability as best-effort, causing recurring failures: lost state after compaction, bypassed flushes on reset, and…

This study examines how large language model-driven non-player characters (LLM-NPCs) affect players' cognitive load and gaming experience, with a particular focus on the underlying psychological mechanisms, differences across task…

Playing video games requires perception, memory, and planning, exactly the faculties modern large language model (LLM) agents are expected to master. We study the major challenges in using popular video games to evaluate modern LLMs and…

Current interactive LLM agents rely on goal-conditioned stepwise planning, where environmental understanding is acquired reactively during execution rather than established beforehand. This temporal inversion leads to Delayed Environmental…

Large language model (LLM) agents have exhibited strong problem-solving competence across domains like research and coding. Yet, it remains underexplored whether LLM agents can tackle compounding real-world problems that require a diverse…

Procedural content generation for games is a growing trend in both research and industry, even though there is no consensus of how good content looks, nor how to automatically evaluate it. A number of metrics have been developed in the…

Large language models (LLMs) are increasingly deployed as interactive agents, yet their capacity for social and strategic reasoning over extended interaction remains poorly understood. Existing evaluations rely on static vignettes or…

While advancements in NLP have significantly improved the performance of Large Language Models (LLMs) on tasks requiring vertical thinking, their lateral thinking capabilities remain under-explored and challenging to measure due to the…

Although deep reinforcement learning has led to breakthroughs in many difficult domains, these successes have required an ever-increasing number of samples, affording only a shrinking segment of the AI community access to their development.…

World models learn general knowledge from videos and simulate experience for training behaviors in imagination, offering a path towards intelligent agents. However, previous world models have been unable to accurately predict object…

Integrating LLM and reinforcement learning (RL) agent effectively to achieve complementary performance is critical in high stake tasks like cybersecurity operations. In this study, we introduce SecurityBot, a LLM agent mentored by…

Memory is a fundamental component for enabling long-context LLM agents, supporting persistent state across interactions through a continuous serve-and-update lifecycle. Despite substantial prior work, existing systems suffer from…

Optimizing CUDA code across multiple generations of GPU architectures is challenging, as achieving peak performance requires an extensive exploration of an increasingly complex, hardware-specific optimization space. Traditional compilers…