MAS-Loop: Beyond One-Shot Orchestration towards Self-Evolving Multi-Agent Systems (Q7414973)
From MaRDI portal
!
This is the item page for this Wikibase entity, intended for internal use and editing purposes. Please use the normal view instead:
No description defined
| Language | Label | Description | Also known as |
|---|---|---|---|
| default for all languages | No label defined |
||
| English | MAS-Loop: Beyond One-Shot Orchestration towards Self-Evolving Multi-Agent Systems |
No description defined |
Statements
MAS-Loop: Beyond One-Shot Orchestration towards Self-Evolving Multi-Agent Systems (English)
0 references
28 October 2026
0 references
cs.MA
0 references
cs.AI
0 references
Hehai Lin
0 references
Qi Yang
0 references
Chengwei Qin
0 references
This paper closes the feedback loop in training-time multi-agent system (MAS) design by coupling an Orchestrator with a Refiner to execute and update MAS iteratively based on trajectories rather than only terminal outcomes; experiments show significant performance gains from this approach across various benchmarks.
0 references
Multi-Agent Systems
0 references
Self-Evolving Systems
0 references
Orchestration
0 references
Feedback Loop
0 references
