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

Indonesian

Metode yang ada mengasumsikan bahwa semua informasi instansi masalah diketahui terlebih dahulu. Namun, masalah dunia nyata sering dinamis: informasi yang relevan diungkapkan secara progresif saat agen mengambil tindakan (misalnya, tiba di tepi dalam masalah routing hanya untuk menemukan bahwa itu tidak dapat dilalui). Dalam kasus seperti itu, metode yang ada gagal mengkoordinasikan agen untuk mengeksplorasi dan memanfaatkan informasi yang secara progresif diungkapkan. Untuk mengatasi tantangan koordinasi yang muncul, kami memperkenalkan PACT (Plan-Augmented Coordination via Trace-graphs). PACT meningkatkan lingkungan dengan nod grafis tambahan yang mewakili rencana agen, yang terhubung ke nod sumber daya untuk menunjukkan ketergantungan di masa depan. Skema akses pesan-passing yang diusulkan meliputi koordinasi grafis yang ditingkatkan di lingkungan yang proaktif dan memungkinkan reperaktif,

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