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

Korean

다중 에이전트 접근법은 최근 신경 조합 최적화에 대한 강화 학습의 확장성을 향상시키는 방법으로 조사되었습니다. 기존 방법은 모든 문제 인스턴스 정보가 사전에 알려져 있다고 가정합니다. 그러나 실제 문제는 종종 역동적입니다 : 에이전트가 행동을 수행함에 따라 관련 정보가 점진적으로 공개됩니다 (예를 들어, 라우팅 문제의 가장자리에 도착하여 그것을 발견 할 수 없습니다). 그러한 경우에, 기존 방법은 에이전트를 조정하여 점진적으로 공개 된 정보를 탐구하고 활용하지 못합니다. 발생하는 조정 도전을 해결하기 위해, 우리는 PACT (계획 증가 조정 Trace-graphs를 통해). PACT는 에이전트의 계획을 나타내는 보조 노드와 함께 환경을 증가시킵니다, 이는

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