Related papers: Taming "Zombie'' Agents: A Markov State-Aware Fram…

The rise of powerful large language models (LLMs) has spurred a new trend in building LLM-based autonomous agents for solving complex tasks, especially multi-agent systems. Despite the remarkable progress, we notice that existing works are…

Multi-agent navigation in dynamic environments is of great industrial value when deploying a large scale fleet of robot to real-world applications. This paper proposes a decentralized partially observable multi-agent path planning with…

The booming success of LLMs initiates rapid development in LLM agents. Though the foundation of an LLM agent is the generative model, it is critical to devise the optimal reasoning strategies and agent architectures. Accordingly, LLM agent…

Nowadays, cooperative multi-agent systems are used to learn how to achieve goals in large-scale dynamic environments. However, learning in these environments is challenging: from the effect of search space size on learning time to…

Multi-agent systems address issues of accessibility and scalability of artificial intelligence (AI) foundation models, which are often represented by large language models. We develop a framework - the "Society of HiveMind" (SOHM) - that…

This work proposes a neural network architecture that learns policies for multiple agent classes in a heterogeneous multi-agent reinforcement setting. The proposed network uses directed labeled graph representations for states, encodes…

We present Agent Lightning, a flexible and extensible framework that enables Reinforcement Learning (RL)-based training of Large Language Models (LLMs) for any AI agent. Unlike existing methods that tightly couple RL training with agent or…

The effectiveness of LLM-based agents is often limited not by model capacity alone, but by how efficiently contextual information is utilized at runtime. Existing agent frameworks rely on rigid, syntax-heavy state representations such as…

As Large Language Models (LLMs) continue to scale, post-training pruning has emerged as a promising approach to reduce computational costs while preserving performance. Existing methods such as SparseGPT and Wanda achieve high sparsity…

Large language model (LLM)-based agents that reason, plan, and act through tools, memory, and structured interaction are emerging as a promising paradigm for automating complex workflows. Recent systems such as OpenClaw and Claude Code…

This work considers the problem of learning cooperative policies in multi-agent settings with partially observable and non-stationary environments without a communication channel. We focus on improving information sharing between agents and…

We introduce Kimi K2.5, an open-source multimodal agentic model designed to advance general agentic intelligence. K2.5 emphasizes the joint optimization of text and vision so that two modalities enhance each other. This includes a series of…

In this paper, we propose a new mutual information framework for multi-agent reinforcement learning to enable multiple agents to learn coordinated behaviors by regularizing the accumulated return with the simultaneous mutual information…

Ransomware has become one of the most serious cybersecurity threats causing major financial losses and operational disruptions worldwide.Traditional detection methods such as static analysis, heuristic scanning and behavioral analysis often…

Existing multi-agent coordination techniques are often fragile and vulnerable to anomalies such as agent attrition and communication disturbances, which are quite common in the real-world deployment of systems like field robotics. To better…

In artificial multi-agent systems, the ability to learn collaborative policies is predicated upon the agents' communication skills: they must be able to encode the information received from the environment and learn how to share it with…

Metasurface inverse design has become central to realizing complex optical functionality, yet translating target responses into executable, solver-compatible workflows still demands specialized expertise in computational electromagnetics…

A multimodal large language model (MLLM) agent can receive instructions, capture images, retrieve histories from memory, and decide which tools to use. Nonetheless, red-teaming efforts have revealed that adversarial images/prompts can…

As increasingly capable agents are deployed, a central safety challenge is how to retain meaningful human control without modifying the underlying system. We study a minimal control interface in which an agent chooses whether to act…

Machine learning algorithms have been applied to predict agent behaviors in real-world dynamic systems, such as advertiser behaviors in sponsored search and worker behaviors in crowdsourcing. The behavior data in these systems are generated…