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

German

Multi-Agent-Ansätze wurden in letzter Zeit als Mittel zur Verbesserung der Skalierbarkeit des Verstärkungslernens für neuronale kombinatorische Optimierung untersucht. Bestehende Methoden gehen davon aus, dass alle Probleminstanzinformationen im Voraus bekannt sind. Allerdings sind reale Probleme oft dynamisch: relevante Informationen werden allmählich offenbart, während die Agenten Aktionen ergreifen (z. B. an einem Rand in einem Routing-Problem ankommen, um es nur zu entdecken, ist unüberwindbar). In solchen Fällen scheitern bestehende Methoden daran, Agenten zu koordinieren, um die progressiv offenbarten Informationen zu erforschen und zu nutzen.

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