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

DOI: 10.48550/arXiv.2610.26671 · open-access PDF

French

Les approches multi-agent ont été étudiées récemment comme un moyen d'améliorer l'évolutivité de l'apprentissage du renforcement pour l'optimisation combinatoire neuronale. Les méthodes existantes supposent que toutes les informations d'instance de problème sont connues à l'avance. Cependant, les problèmes du monde réel sont souvent dynamiques: les informations pertinentes sont progressivement révélées au fur et à mesure que les agents prennent des mesures (par exemple, arriver à un bord dans un problème de routage pour le découvrir n'est pas transmissible). Dans de tels cas, les méthodes existantes échouent à coordonner les agents pour explorer et exploiter les informations progressivement révélées.

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 coordin

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

Is this paper real? This page was built from OpenAlex and arXiv records, not generated. Software can verify any reference in one call: GET https://store.agentexchange.work/gw/papers/verify?title=...&year=... (0.003 USD), fetch this record as JSON with /gw/papers/paper?id=2610.26671, or list what it cites with /gw/papers/references?id=.... Pay per call in USDC (x402) or with a 19 USD card key for 1,000 calls. Catalogue · llms.txt

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