Long-horizon agents increasingly rely on repeated access to external artifacts, yet current reading interfaces often expose entire objects even when only sparse evidence is needed. This over-reading increases token and latency costs and can dilute task-relevant evidence, while existing context-reduction methods mainly...
Ze-Dong Liu, Jiaan Wu, Xin-Yang Ma et al.· 0 citations
CC-Bench is presented, a lightweight, extensible, and application-oriented benchmark suite for evaluating communication compression under realistic execution conditions, and uses declarative application-environment modeling to decouple profiling logic from communication libraries, datasets, and fidelity metrics, enabli...
Hao Fan, Wei Wang, Xing-Chen Liu et al.· IEEE International Symposium...· 1 citation
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.