Tag
Agora introduces an auction-based task allocation mechanism for LLM agents, treating reasoning steps as tradeable items and using calibrated confidence to route tasks to the most capable expert models, improving reasoning performance across benchmarks.
This paper proposes an Edge-AI-driven decentralized task allocation framework for circular smart manufacturing that uses learning-to-rank to align with the ordering-based nature of winner selection. Simulation results show improved delay, deadline adherence, and energy efficiency under high-load and tight-deadline scenarios.