Related papers: Self-Evolving Coordination Protocol in Multi-Agent…
Current LLM agents are proficient at calling isolated APIs but struggle with the "last mile" of commercial software automation. In real-world scenarios, tools are not independent; they are atomic, interdependent, and prone to environmental…
We study information design in multi-agent systems (MAS) with binary actions and strategic complementarities, where an external designer influences behavior only through signals. Agents play the smallest-equilibrium of the induced Bayesian…
Sequential Convex Programming (SCP) has recently gained significant popularity as an effective method for solving optimal control problems and has been successfully applied in several different domains. However, the theoretical analysis of…
An agent must try new behaviors to explore and improve. In high-stakes environments, an agent that violates safety constraints may cause harm and must be taken offline, curtailing any future interaction. Imitating old behavior is safe, but…
Coordination in multi-agent system is very essential, in order to perform complex tasks and lead MAS towards its goal. Also, the member agents of multi-agent system should be autonomous as well as collaborative to accomplish the complex…
Controlling the behavioral diversity is a pivotal challenge in multi-agent reinforcement learning (MARL), particularly in complex collaborative scenarios. While existing methods attempt to regulate behavioral diversity by directly…
Agentic AI systems - capable of goal interpretation, world modeling, planning, tool use, long-horizon operation, and autonomous coordination - introduce distinct control failures not addressed by existing safety frameworks. We identify six…
How can we determine whether an AI system preserves itself as a deeply held objective or merely as an instrumental strategy? Autonomous agents with memory, persistent context, and multi-step planning create a measurement problem: terminal…
Autonomous cooperative planning (ACP) is a promising technique to improve the efficiency and safety of multi-vehicle interactions for future intelligent transportation systems. However, realizing robust ACP is a challenge due to the…
In multi-agent systems, agents possess only local observations of the environment. Communication between teammates becomes crucial for enhancing coordination. Past research has primarily focused on encoding local information into embedding…
Autonomous systems often have logical constraints arising, for example, from safety, operational, or regulatory requirements. Such constraints can be expressed using temporal logic specifications. The system state is often partially…
Modern AI agents can exchange messages using protocols such as A2A and ACP, yet these mechanisms emphasize communication over coordination. As agent populations grow, this limitation produces brittle collective behavior, where individually…
Modern distributed software systems often operate in dynamic environments in which operation conditions change continuously and subsystems may come and go at will, e.g. intelligent traffic management and multi-robot systems. To manage these…
Self-evolving memory systems are unprecedentedly reshaping the evolutionary paradigm of large language model (LLM)-based agents. Prior work has predominantly relied on manually engineered memory architectures to store trajectories, distill…
Autonomous robots may be able to adapt their behavior in response to changes in the environment. This is useful, for example, to efficiently handle limited resources or to respond appropriately to unexpected events such as faults. The…
Multi-agent systems have extended the capability of agentic AI. Instead of single inference passes, multiple agents perform collective reasoning to derive high quality answers. However, existing multi-agent orchestration relies on static…
Multiagent AI systems require consistent communication, but we lack methods to verify that agents share the same understanding of the terms used. Natural language is interpretable but vulnerable to semantic drift, while learned protocols…
Large Language Models (LLMs) have demonstrated remarkable capabilities across diverse tasks but remain fundamentally static, unable to adapt their internal parameters to novel tasks, evolving knowledge domains, or dynamic interaction…
Multi-agent large language model (LLM) systems often rely on a controller to coordinate a pool of heterogeneous models, yet existing controllers are typically limited to one-shot routing: they select a model once and return its output…
As multi-agent systems evolve to encompass increasingly diverse and specialized agents, the challenge of enabling effective collaboration between heterogeneous agents has become paramount, with traditional agent communication protocols…