The paper proves an information-theoretically optimal gap-majority lemma in the two-player randomized communication model, achieving the correct linear scaling and constant-constant tradeoff.

This paper investigates the convergence and stability of equilibria in bimatrix two-player games using the optimistic exponential weights method, allowing step sizes to differ.

This paper demonstrates that using a communication algorithm (CommFormer) with heterogeneous agents significantly improves the speed and performance of multi-agent reinforcement learning for autonomou…

This paper proposes MUTE, a framework for reducing communication in Multi-Agent Reinforcement Learning under bandwidth constraints by unlearning irrelevant messages.

The paper develops a novel attack method for multi-agent discussions under continuous monitoring, demonstrating that monitoring alone is insufficient to secure these systems.

A paper on dynamic strategic communication problem where a sender controls the timing of truthful updates from binary Markov sources and aims to persuade the receiver to estimate the state as 1, while…

This paper provides an information bottleneck perspective on the differences between single-agent and multi-agent systems, showing that the advantage of MAS arises under bounded relays and introducing…

This paper characterizes Pure Nash Equilibria and presents a polynomial-time algorithm for finding them in the Intermittent Strategic Cooperation-Based Two-Agent Path Planning game.

The paper proposes Multi-Order Communication (MOC) to overcome the limitations of standard first-order message passing in LLM-based multi-agent systems, significantly improving performance by capturin…

The paper introduces FootsiesGym, an open-source environment for learning in a two-player, zero-sum, imperfect-information game, providing a vectorized simulator for efficient analysis.

The paper proposes DySCo, a dynamic trust-aware sparse consensus mechanism, to efficiently manage communication in multi-agent LLM systems by selectively connecting agents based on real-time value, th…

The paper proves XNLP-hardness of Directed Edge Geography and Undirected Edge Geography when parameterized by pathwidth, and shows their fixed-parameter tractability when parameterized by treewidth an…

This paper proposes a framework for compositional semantic communication (CSC) in physical AI systems, enabling heterogeneous devices to transmit semantic representations that compose meaningfully at…

This paper introduces a correction-aware network model to study the spread of erroneous claims in communication networks and characterizes the intersection of reliability and error control constraints…

The paper presents a complete, moderatorless protocol for playing Werewolf using only ordinary playing cards, eliminating the need for a trusted third party or digital devices.

The paper proposes TCP-MCP, a co-evolution framework that jointly optimizes agent prompts and communication topologies to design highly efficient and effective multi-agent systems.

This paper investigates if team-based interaction improves LLM performance on complex reasoning tasks (ChGK), finding that structured team strategies significantly boost accuracy by acting as error-fi…