Siru Zhong

Current scientific agents struggle to maintain a coherent narrative across evidence and calculations, with only 34.81% achieving strict accuracy in complex tasks.

Static benchmarks mislead model performance assessments, as LiveHouse-TS reveals dramatic shifts in rankings when evaluated in real-time environments.

LLM multi-agent systems can achieve significantly higher accuracy at a fraction of the cost by learning to selectively delegate tasks instead of relying on rigid orchestration.