多智能体系统

Multi-agent LLM systems routinely generate multiple candidate responses that are aggregated by an LLM judge. To reduce the dominant prefill cost in such pipelines, recent work advocates KV cache reuse across partially shared contexts and…

Vision-based formation control systems are attractive because they can use inexpensive sensors and can work in GPS-denied environments. The safety assurance for such systems is challenging: the vision component's accuracy depends on the…

While Vision-Language Models (VLMs) have significantly advanced Computer-Using Agents (CUAs), current frameworks struggle with robustness in long-horizon workflows and generalization in novel domains. These limitations stem from a lack of…

Random walk (RW)-based algorithms have long been popular in distributed systems due to low overheads and scalability, with recent growing applications in decentralized learning. However, their reliance on local interactions makes them…

Numerical simulation is one of the mainstream methods in scientific research, typically performed by professional engineers. With the advancement of multi-agent technology, using collaborating agents to replicate human behavior shows…

Generating high-quality structured data such as JSON records, remains a fundamental challenge for large language models (LLMs), particularly when semantic richness must coexist with strict schema adherence. While autoregressive LLMs offer…

The advent of 6G networks is accelerating autonomy and intelligence in large-scale, decentralized multi-agent systems (MAS). While this evolution enables adaptive behavior, it also heightens vulnerability to stressors such as environmental…

Multi-agent systems face a fundamental coordination problem: agents must coordinate despite heterogeneous preferences, asymmetric stakes, and imperfect information. When coordination fails, friction emerges: measurable resistance…

Constructing memory from users' long-term conversations overcomes LLMs' contextual limitations and enables personalized interactions. Recent studies focus on hierarchical memory to model users' multi-granular behavioral patterns via…

Peer incentivization (PI) is a popular multi-agent reinforcement learning approach where all agents can reward or penalize each other to achieve cooperation in social dilemmas. Despite their potential for scalable cooperation, current PI…

Simulating dementia patients with large language models (LLMs) is challenging due to the need to jointly model cognitive impairment, emotional dynamics, and nonverbal behaviors over long conversations. We present DemMA, an expert-guided…

This paper introduces a novel framework for simulating and analyzing how uncooperative behaviors can destabilize or collapse LLM-based multi-agent systems. Our framework includes two key components: (1) a game theory-based taxonomy of…

A law in a multiagent system is a set of constraints imposed on agents' behaviours to avoid undesirable outcomes. The paper considers two types of laws: useful laws that, if followed, completely eliminate the undesirable outcomes and…

We propose a two-level information-theoretic framework for characterizing the informational organization of Agent-Based Model (ABM) dynamics within the broader paradigm of Complex Adaptive Systems (CAS). At the macro level, a pooled…

We present LegalSim, a modular multi-agent simulation of adversarial legal proceedings that explores how AI systems can exploit procedural weaknesses in codified rules. Plaintiff and defendant agents choose from a constrained action space…

This paper investigates the convergence time of log-linear learning to an $\epsilon$-efficient Nash equilibrium in potential games, where an efficient Nash equilibrium is defined as the maximizer of the potential function. Previous…

Large Language Models (LLMs) are increasingly instantiated as interacting agents in multi-agent systems (MAS), where collective decisions emerge through social interaction rather than independent reasoning. A fundamental yet underexplored…

Multi-agent reinforcement learning in dynamic social dilemmas commonly relies on parameter sharing to enable scalability. We show that in shared-policy Deep Q-Network learning, standard exploration can induce a robust and systematic…

Finding a free parking space in a city has become a challenging task over the past decades. A recently proposed auction-based parking assignment can alleviate cruising for parking and also set a market-driven, demand-responsive parking…

Policy Space Response Oracles (PSRO) combines game-theoretic equilibrium computation with learning and is effective in approximating Nash Equilibrium in zero-sum games. However, the computational cost of PSRO has become a significant…