Multi-Agent Coordination Adaptation via Structure-Guided Orchestration
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2026
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866911715938009088 |
|---|---|
| author | Li, Haoran Chen, Shulun Sun, Shaoyuan Wang, Hanchen |
| author_facet | Li, Haoran Chen, Shulun Sun, Shaoyuan Wang, Hanchen |
| contents | As large language model (LLM)-based multi-agent systems scale to handle increasingly complex tasks, balancing structural stability and dynamic adaptability becomes increasingly challenging. Existing systems typically adopt either structure-centric methods, committing to structures determined upfront that limit fine-grained control, or orchestration-centric methods, adapting decisions dynamically while leaving coordination structure implicit and unstable. To address this challenge, we revisit multi-agent coordination from a probabilistic perspective, casting it as posterior inference over the joint distribution of structure and orchestration. We introduce MACA, an automated coordination framework that learns a task- and budget-conditioned structural prior over agent participation and interactions. This prior guides a policy-based orchestration as an approximation to posterior inference, enabling efficient solutions with fine-grained control. Across benchmarks, MACA outperforms adaptive multi-agent baselines by an average of 8.42% while using 43.19% fewer tokens. Further investigation reveals that joint adaptation of structure and orchestration suppresses redundant interactions, converging coordination toward task-effective execution. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_25746 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Multi-Agent Coordination Adaptation via Structure-Guided Orchestration Li, Haoran Chen, Shulun Sun, Shaoyuan Wang, Hanchen Multiagent Systems Artificial Intelligence As large language model (LLM)-based multi-agent systems scale to handle increasingly complex tasks, balancing structural stability and dynamic adaptability becomes increasingly challenging. Existing systems typically adopt either structure-centric methods, committing to structures determined upfront that limit fine-grained control, or orchestration-centric methods, adapting decisions dynamically while leaving coordination structure implicit and unstable. To address this challenge, we revisit multi-agent coordination from a probabilistic perspective, casting it as posterior inference over the joint distribution of structure and orchestration. We introduce MACA, an automated coordination framework that learns a task- and budget-conditioned structural prior over agent participation and interactions. This prior guides a policy-based orchestration as an approximation to posterior inference, enabling efficient solutions with fine-grained control. Across benchmarks, MACA outperforms adaptive multi-agent baselines by an average of 8.42% while using 43.19% fewer tokens. Further investigation reveals that joint adaptation of structure and orchestration suppresses redundant interactions, converging coordination toward task-effective execution. |
| title | Multi-Agent Coordination Adaptation via Structure-Guided Orchestration |
| topic | Multiagent Systems Artificial Intelligence |
| url | https://arxiv.org/abs/2605.25746 |