Tag
This paper evaluates context engineering configurations for LLM agents in enterprise tool-use workflows, showing that summarization with selective pruning achieves 91.6% accuracy while reducing token usage by over 60% compared to full-context baselines.
LaMR introduces a structured pruning framework for coding agents that decomposes code relevance into semantic evidence and dependency support dimensions, using dedicated CRFs and a mixture-of-experts gate to reduce token usage by up to 31% while maintaining or improving task performance.