相关论文: PEAR: Planner-Executor Agent Robustness Benchmark

The widespread adoption of Large Language Models (LLMs) and LLM-powered agents in multi-user settings underscores the need for reliable, usable methods to accommodate diverse preferences and resolve conflicting directives. Drawing on…

In cooperative Multi-Agent Reinforcement Learning (MARL), it is a common practice to tune hyperparameters in ideal simulated environments to maximize cooperative performance. However, policies tuned for cooperation often fail to maintain…

Model ensemble is a useful approach in reinforcement learning (RL) for training effective agents. Despite wide success of RL, training effective agents remains difficult due to the multitude of factors requiring careful tuning, such as…

Large language model-based multi-agent systems (LLM-MAS) effectively accomplish complex and dynamic tasks through inter-agent communication, but this reliance introduces substantial safety vulnerabilities. Existing attack methods targeting…

When combining Large Language Models (LLMs) with autonomous agents, used in network monitoring and decision-making systems, this will create serious security issues. In this research, the MAESTRO framework consisting of the seven layers…

As the complexity of Software Engineering (SE) tasks continues to escalate, Multi-Agent Systems (MASs) have emerged as a focal point of research and practice due to their autonomy and scalability. Furthermore, through leveraging the…

Multi-agent systems (MASs) have pushed the boundaries of large language model (LLM) agents in domains such as web research and software engineering. However, long-horizon, multi-constraint planning tasks involve conditioning on detailed…

In decentralized multiagent trajectory planners, agents need to communicate and exchange their positions to generate collision-free trajectories. However, due to localization errors/uncertainties, trajectory deconfliction can fail even if…

The security of LLM-based multi-agent systems (MAS) is critically threatened by propagation vulnerability, where malicious agents can distort collective decision-making through inter-agent message interactions. While existing supervised…

The integration of large language models (LLMs) into robotic task planning has unlocked better reasoning capabilities for complex, long-horizon workflows. However, ensuring safety in LLM-driven plans remains a critical challenge, as these…

Large Language Models (LLMs) based agents excel at diverse tasks, yet they suffer from brittle procedural memory that is manually engineered or entangled in static parameters. In this work, we investigate strategies to endow agents with a…

Although Multi-Agent Reinforcement Learning (MARL) is effective for complex multi-robot tasks, it suffers from low sample efficiency and requires iterative manual reward tuning. Large Language Models (LLMs) have shown promise in…

Multi-agent systems (MAS) built on large language models (LLMs) offer a promising path toward solving complex, real-world tasks that single-agent systems often struggle to manage. While recent advancements in test-time scaling (TTS) have…

The evolution of Multimodal Large Language Models (MLLMs) has shifted the focus from text generation to active behavioral execution, particularly via OS agents navigating complex GUIs. However, the transition of these agents into…

This benchmark suite provides a comprehensive evaluation framework for assessing both individual LLMs and multi-agent systems in Real-world planning and scheduling scenarios. The suite encompasses 14 designed planning and scheduling…

Algorithmic problem solving serves as a rigorous testbed for evaluating structured reasoning in AI coding systems, as it directly reflects a model's ability to perform structured reasoning in complex scenarios. Existing approaches…

Recent interest in Multi-Agent Systems of Large Language Models (MAS LLMs) has led to an increase in frameworks leveraging multiple LLMs to tackle complex tasks. However, much of this literature appropriates the terminology of MAS without…

Reinforcement Learning (RL) has emerged as a crucial method for training or fine-tuning large language models (LLMs), enabling adaptive, task-specific optimizations through interactive feedback. Multi-Agent Reinforcement Learning (MARL), in…

Large Language Models (LLMs) exhibit substantial promise in enhancing task-planning capabilities within embodied agents due to their advanced reasoning and comprehension. However, the systemic safety of these agents remains an underexplored…

The rapid advancement of large language models (LLMs) has empowered intelligent agents to leverage diverse external tools for solving complex real-world problems. However, this reliance introduces new challenges, as extended contexts and…