In multi-agent systems, complex tasks are decomposed into directed acyclic graphs (DAGs) of specialized agent executions, creating natural opportunities for caching intermediate results across queries. However, existing cache eviction policies treat all cached entries uniformly based on access history, ignoring structural and workload signals uniquely available in agentic execution environments.
We present a workload-aware eviction policy that combines three signals: recomputation cost, DAG dependency count, and agent invocation frequency, into a unified scoring function that retains the most valuable entries under memory constraints.
Evaluated across three multi-agent benchmarks spanning diverse reuse regimes, our policy reduces latency by up to 64.7% relative to the uncached baseline and achieves an average latency reduction of 31.1% over the next best finite-capacity baseline, while approaching the performance of an unbounded cache and maintaining accuracy on par with or exceeding all competing finite-capacity methods.
Furthermore, we show that workload-aware content caching is complementary to other agentic system optimization methods, including plan-level caching and parallel agent execution, with each technique targeting a distinct efficiency bottleneck in multi-agent pipelines.
Blogger's Review: The proposed workload-aware caching strategy demonstrates significant performance improvements in multi-agent systems, especially under resource constraints. The unified scoring function that incorporates multiple signals offers a novel approach for optimizing caching strategies, highlighting the importance of unique characteristics in agentic execution environments for performance enhancement. This study provides valuable insights for future optimizations in multi-agent systems.