112 papers
This paper proposes a novel three-level Stackelberg game framework that incorporates heterogeneous leaders and non-follower agents to accurately model congestion-coupled strategic interactions, demonstrating that ignoring non-participating agents leads to distorted equilibrium predictions in systems like EV charging markets.
This paper proposes Adaptive Memory Admission Control (A-MAC), a framework that decomposes memory value into five interpretable factors to enable transparent, efficient, and domain-adaptive long-term memory management for LLM agents, achieving superior precision-recall tradeoffs and reduced latency compared to state-of-the-art systems.
This paper proposes a propagation dynamics model and a non-intrusive genealogy-graph-based governance layer to identify, model, and effectively mitigate error cascades in LLM-based multi-agent systems, significantly improving defense success rates against error amplification without altering existing collaboration architectures.
SkillNet is an open infrastructure that addresses the lack of systematic skill accumulation in AI agents by providing a unified ontology, a repository of over 200,000 skills, and evaluation tools to create, connect, and assess skills, thereby significantly enhancing agent performance and efficiency across diverse tasks.
This paper proposes an auction-based framework for allocating shared reconfigurable intelligent surfaces (RISs) in multi-cell networks, where deep reinforcement learning agents optimize bidding strategies to dynamically balance spectral efficiency and cost constraints.
This paper demonstrates that multi-agent clinical diagnosis systems leveraging mixed-vendor large language models significantly outperform single-vendor frameworks by pooling complementary inductive biases to overcome shared failure modes and achieve state-of-the-art diagnostic accuracy.
This paper proposes a Dual-Interaction-Aware Cooperative Control (DIACC) strategy based on Multi-Agent Reinforcement Learning, which integrates decentralized decision-making, centralized value estimation, and a novel reward design to effectively alleviate mixed traffic congestion by distinguishing between cooperative and observational vehicle interactions.
This paper establishes a rigorous graph-theoretic framework that maps Transformer cross-entropy log-odds to signed Laplacians to analyze consensus stability in multi-agent LLM systems, demonstrating how structural balance theory identifies reasoning oscillations caused by unobservable latent states and proposing chordal graph topologies with spectral perturbations to deterministically resolve these deadlocks.
This paper introduces a simulation-based clinical red teaming framework that pairs AI psychotherapists with dynamic patient agents to evaluate mental health support systems, revealing critical safety gaps such as the validation of delusions and failure to de-escalate suicide risk in AI agents tested against Alcohol Use Disorder scenarios.
This study demonstrates that a neural network-based simulation inference framework effectively and efficiently estimates parameters in a large-scale labour market agent-based model, outperforming traditional Bayesian methods and summary statistics in recovering original parameters across various dataset scales.
EmboTeam is a novel framework that enhances embodied multi-robot collaboration by cascading LLM-based instruction parsing into formal PDDL planning and reactive behavior tree execution, achieving significantly higher task success rates on the new MACE-THOR benchmark compared to existing baselines.
The paper proposes GRAND, a hybrid hierarchical algorithm that combines reinforcement learning-based graph guidance with minimum-cost flow rebalancing and local assignment to achieve up to 10% higher throughput than state-of-the-art schedulers for large-scale, lifelong multi-agent pickup-and-delivery tasks while maintaining real-time execution.
This paper proposes a Conflict-Based Search (CBS) protocol that enables efficient, collision-free multi-agent motion planning for heterogeneous teams of robots with independent tasks by utilizing a central planner that coordinates diverse single-agent solvers—ranging from traditional algorithms to learning-based methods—through a standardized space-time constraint API.
The paper introduces Foam-Agent, a multi-agent framework leveraging large language models and retrieval-augmented generation to automate end-to-end computational fluid dynamics workflows from natural language prompts, achieving an 88.2% execution success rate on diverse simulation tasks without expert intervention.
This paper addresses the limitations of existing BDI agents in real-time environments by proposing a redefined control loop that explicitly manages temporal constraints and resources, which is then validated through an implementation in a resource-collection video game.
This paper demonstrates that while basic Axelrod models yield similar consensus outcomes regardless of topology, implementing a toroidal opinion space significantly enhances the potential for multi-group polarization and increases sensitivity to model extensions compared to a cubic space.
This paper introduces TritonDFT, a multi-agent framework that automates complex Density Functional Theory workflows through expert-curated designs and Pareto-aware optimization, accompanied by the DFTBench benchmark to evaluate multi-dimensional agent capabilities.
This paper introduces \SysName, a novel framework that enhances Multi-Agent System security by shifting from static input filtering to execution-aware analysis through the reconstruction of Cross-Agent Semantic Flows, effectively detecting complex attack vectors that bypass conventional guardrails.
VideoChat-M1 introduces a novel multi-agent system for video understanding that employs a learnable Collaborative Policy Planning paradigm, where multiple agents dynamically generate, execute, and refine tool invocation strategies through interaction and multi-agent reinforcement learning to achieve state-of-the-art performance across diverse video benchmarks.
The paper introduces -IPOMDP, a computational framework that equips model-based reinforcement learning agents with anomaly detection and out-of-belief policies to identify and deter deception from more sophisticated opponents, thereby mitigating exploitation in mixed-motive and zero-sum games.