Large language models are increasingly participating in complex real-world tasks in the form of algorithm-design agents, designing and refining algorithms. Many successful algorithm-design agents adopt pure in-context evolutionary frameworks, but they may quickly plateau in domains that require specialized knowledge. P...
Chen-Han Lu, Ke Xue, Si-Yuan Xu et al.· 0 citations
A novel method, namely AnDPro, is proposed, which introduces a projection-based scoring function to more accurately measure token importance and guide more accurate token selection in key-Value cache eviction.
Zijie Geng, Jie Wang, Ziqi Liu et al.· Neural Information Processin...· 6 citations
Experiments across diverse multi-agent workloads show that AGAO improves task effectiveness while reducing unnecessary computation, latency, and token consumption compared with existing graph-based execution strategies.