Related papers: PillagerBench: Benchmarking LLM-Based Agents in Co…

LLM-based reasoning models have enabled the development of agentic systems that act as co-scientists, assisting in multi-step scientific analysis. However, evaluating these systems is challenging, as it requires realistic, end-to-end…

The balancing process for game levels in a competitive two-player context involves a lot of manual work and testing, particularly in non-symmetrical game levels. In this paper, we propose an architecture for automated balancing of…

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…

Multi-agent deep reinforcement learning (MARL) suffers from a lack of commonly-used evaluation tasks and criteria, making comparisons between approaches difficult. In this work, we provide a systematic evaluation and comparison of three…

With large language models (LLMs) on the rise, in-game interactions are shifting from rigid commands to natural conversations. However, the impacts of LLMs on player performance and game experience remain underexplored. This work explores…

Agents based on large language models leverage tools to modify environments, revolutionizing how AI interacts with the physical world. Unlike traditional NLP tasks that rely solely on historical dialogue for responses, these agents must…

Reinforcement Learning (RL) agents often struggle with efficiency and performance in complex environments. We propose a novel framework that uses a Large Language Model (LLM) to dynamically generate a curriculum over available actions,…

Leveraging multiple large language model (LLM) agents has shown to be a promising approach for tackling complex tasks, while the effective design of multiple agents for a particular application remains an art. It is thus intriguing to…

Existing benchmarks for LLM agents' social behavior typically focus on a single capability dimension and evaluate only behavioral outcomes, overlooking process signals from reasoning and communication. We present M3-BENCH, a benchmark of 24…

Multi-agent reinforcement learning (MARL) models multiple agents that interact and learn within a shared environment. This paradigm is applicable to various industrial scenarios such as autonomous driving, quantitative trading, and…

As foundation models are increasingly deployed as interacting agents in multi-agent systems, their collective behavior raises new challenges for trustworthiness, transparency, and accountability. Traditional coordination mechanisms, such as…

Autonomous agents empowered by Large Language Models (LLMs) have undergone significant improvements, enabling them to generalize across a broad spectrum of tasks. However, in real-world scenarios, cooperation among individuals is often…

Cooperative Multi-Agent Reinforcement Learning (MARL) solves complex tasks that require coordination from multiple agents, but is often limited to either local (independent learning) or global (centralized learning) perspectives. In this…

We address the long-horizon gap in large language model (LLM) agents by enabling them to sustain coherent strategies in adversarial, stochastic environments. Settlers of Catan provides a challenging benchmark: success depends on balancing…

In the Minecraft Collaborative Building Task, two players collaborate: an Architect (A) provides instructions to a Builder (B) to assemble a specified structure using 3D blocks. In this work, we investigate the use of large language models…

Multi-agent systems, which consist of multiple AI models interacting within a shared environment, are increasingly used for persona-based interactions. However, if not carefully designed, these systems can reinforce implicit biases in large…

An important challenge in reinforcement learning is training agents that can solve a wide variety of tasks. If tasks depend on each other (e.g. needing to learn to walk before learning to run), curriculum learning can speed up learning by…

The growing adoption of large language models (LLMs) presents potential for deeper understanding of human behaviours within game theory frameworks. Addressing research gap on multi-player competitive games, this paper examines the strategic…

Competitive Self-Play (CSP) based Multi-Agent Reinforcement Learning (MARL) has shown phenomenal breakthroughs recently. Strong AIs are achieved for several benchmarks, including Dota 2, Glory of Kings, Quake III, StarCraft II, to name a…

Although LLM-based agents have attracted significant attention in domains such as software engineering and machine learning research, their role in advancing combinatorial optimization (CO) remains relatively underexplored. This gap…