Poster Type: Research Posters
Author: Bipin Bohara (Missouri S&T), Hao Wang (Stevens Institute of Technology), Praveenkumar Kondikoppa (Google LLC), Seung-Jong Park (Missouri S&T)
Abstract: LLM-based multi-agent systems offer strong reasoning capabilities but often incur substantial computational and operational costs. This work presents an adaptive two-orchestrator framework for coordinating heterogeneous small and large LLMs. Orchestrator-1 (O-1) determines the initial number of expert agents and model tier using task-level risk signals. The primary adaptive component, Orchestrator-2 (O-2) evaluates multiple round-level signals using a heuristic approach and selectively escalates only when the current model configuration is deemed insufficient. After evaluation across various benchmarks using models deployed with vLLM we found that compared with the Large-only configuration, the Small + Large configuration improved accuracy by 0.51–6.67 percentage points, reduced average cost per task by 15.99%–33.65%, and decreased execution time by 8.1%–18.06%. Only 0.10%–3.60% of tasks required escalation, demonstrating the effectiveness of O-2’s signal-driven decision mechanism. These results validate that dynamic escalation can preserve or improve performance while reducing unnecessary use of Larger models.
Best Poster Finalist (BP): no
Poster: PDF
Poster Summary: PDF