Newest papers

PACT: Plan-Augmented Coordination via Trace-Graphs for Dynamic Multi-Agent Combinatorial Optimization

Xiao Zhou, Alex Schutz, Victor-Alexandru Darvariu, Nick Hawes · 2026 · arXiv (Cornell University)

DOI: 10.48550/arxiv.2610.26671 · cited by 0 works (OpenAlex) · open-access PDF

Portuguese

Métodos existentes assumem que todas as informações de instância de problema são conhecidas antecipadamente. No entanto, os problemas do mundo real são frequentemente dinâmicos: as informações relevantes são progressivamente reveladas à medida que os agentes tomam ações (por exemplo, chegando a uma borda em um problema de roteamento apenas para descobrir que é impenetrável). Em tais casos, os métodos existentes não coordenam os agentes para explorar e explorar as informações progressivamente reveladas. Para resolver o desafio de coordenação emergente, introduzimos o PACT (Plan-Augmented Coordination via Trace-graphs). O PACT aumenta o ambiente com nódulos auxiliares que representam os planos de agentes, que estão conectados aos nódulos de recursos para indicar dependências futuras. O esquema de acesso proposto instina

Machine translation (Meta M2M100); the English original follows.

Abstract

Multi-agent approaches have been investigated recently as a means of improving the scalability of reinforcement learning for neural combinatorial optimization. Existing methods assume that all problem instance information is known upfront. However, real-world problems are often dynamic: relevant information is progressively revealed as the agents take actions (e.g., arriving at an edge in a routing problem only to discover it is untraversable). In such cases, existing methods fail to coordinate agents to explore and exploit the progressively revealed information. To address the arising coordination challenge, we introduce PACT (Plan-Augmented Coordination via Trace-graphs). PACT augments the environment graph with auxiliary nodes representing the plans of agents, which are connected to the resource nodes to indicate future dependencies. The proposed message-passing scheme over the augmented graph grounds inter-agent coordination in the environment and enables proactive, rather than reactive, conflict resolution. We show that PACT improves solution quality in dynamic problems relative to baselines and exhibits the best transfer to larger instances on which, remarkably, it outperforms centralized oracles with privileged access to instance uncertainty.

Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese

Topics: Computer science, Scalability, Exploit, Graph, Reinforcement learning, Distributed computing

Sources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange