cs.MA
PulseAugur coverage of cs.MA — every cluster mentioning cs.MA across labs, papers, and developer communities, ranked by signal.
4 day(s) with sentiment data
-
New algorithm computes exact equilibria in two-player zero-sum games
Researchers have developed a deterministic polynomial-time algorithm for calculating exact extensive-form proper equilibria in two-player zero-sum games with perfect recall. The algorithm assigns each information set a …
-
New Soei System Enhances AI Agent Software Engineering Observability
Researchers have developed Soei, a new system designed to improve the observability of multi-agent AI software engineering processes. The system addresses challenges in tracking the actions, evidence, and intent behind …
-
Cake cutting research tackles proportional allocation complexity · 2 papers
Two new research papers explore the complexities of proportional cake cutting, a theoretical problem in multiagent systems. The first paper determines the exact worst-case number of cuts needed to guarantee an equal-len…
-
New framework uses statistical contracts for strategic multi-agent resource allocation
Researchers have introduced a novel framework for strategic multi-agent resource allocation using statistical contracts. This approach aims to optimize resource distribution by designing contracts that limit allocations…
-
New research explores intermediate coordination for decentralized multi-agent systems · 2 sources tracked
Two new research papers explore advanced coordination mechanisms for decentralized multi-agent systems, particularly those leveraging large language models (LLMs). The first paper introduces a Responsibility-Centered Co…
-
Akule framework accelerates multi-robot motion planning with sparse diffusion models
Researchers have developed Akule, a novel framework for multi-robot motion planning that utilizes sparse interaction diffusion models. This approach enhances scalability by coordinating individual robot motions without …
-
New algorithm optimizes UAV-UGV coordination for aerial monitoring
Researchers have developed a new algorithm for coordinating unmanned aerial vehicles (UAVs) and unmanned ground vehicles (UGVs) in aerial monitoring missions. This algorithm addresses energy constraints for UAVs, which …
-
New Poll algorithm offers efficient network intervention in strategic agent games
Researchers have developed a new algorithm called Poll for network intervention in multi-activity network games. This algorithm addresses challenges related to private information, potential misreporting by agents, and …
-
New theory shapes passive stiffness in aerial manipulation systems
Researchers have developed a new theory to understand and control the passive mechanical response of cable-suspended aerial manipulation systems. This theory interprets aerial vehicles as movable compliant anchors, enab…
-
New algorithms offer high-probability Nash regret bounds for decentralized learning
Researchers have developed new algorithms for decentralized learning of Nash equilibria in Markov $\alpha$-potential games. These algorithms, a KL-projected natural policy gradient (NPG), are designed for both episodic …
-
RideSkill algorithm uses LLMs for optimized ride-sharing
Researchers have developed RideSkill, a novel hierarchical algorithm designed to optimize generalized ride-sharing operations. This method addresses limitations in existing multi-agent reinforcement learning approaches,…
-
LiveSim framework uses LLMs to simulate evolving user behavior in live-streaming ecosystems
Researchers have developed LiveSim, a novel framework utilizing large language models (LLMs) to simulate user behavior in multi-agent live-streaming ecosystems. Unlike previous simulators that relied on static user prof…
-
Multi-agent LLM traffic patterns differ from human-driven workloads
A new research paper explores the traffic patterns generated by multi-agent Large Language Model (LLM) systems, which differ significantly from traditional human-driven workloads. The study found that the coordination t…
-
AI agents balance memory and communication, new paper suggests
Researchers have published a paper exploring the balance between an agent's internal memory and external communication for decision-making. The study introduces the concept of a "remembering-signaling frontier" to illus…
-
New framework models indirect geoeconomic influence via political economy restructuring
Researchers have developed a new framework using switching dynamical systems to analyze indirect geoeconomic influence. This model allows a sender to influence a target nation by restructuring its internal political eco…
-
Imprecise belief fusion enhances multi-agent social learning
Researchers have developed a new model for social learning where agents learn from each other by combining their beliefs, represented as formulas in a propositional language. The model incorporates a fusion operator tha…
-
AI research explores social reward and punishment dynamics
This research paper explores how a combination of peer and institutional incentives can shape cooperation and social welfare within social dilemmas. Using a four-strategy model in the context of a Prisoner's Dilemma, th…
-
Paper explores emergent behavior in financial markets using formal methods
A new paper explores emergent behavior in financial markets, drawing parallels between complex systems and the formal methods community. The research identifies and structures sources of complexity within electronic fin…
-
New paper introduces Equilibrium Causal Digital Twins for system prediction
A new paper introduces "Equilibrium Causal Digital Twins" to address the challenge of predicting system responses to interventions, particularly in systems with feedback loops. The research outlines conditions under whi…
-
New filtering method enhances safety for drones with degraded GPS signals · 2 sources tracked
Researchers have developed a new method for ensuring the safety of learned separation policies for small Unmanned Aircraft Systems (sUAS) when Global Navigation Satellite Systems (GNSS) signals are degraded. The study e…