EASy: Towards Efficient LLM-Based Agentic System

Agentic orchestration enables multiple autonomous agents to solve complex tasks through adaptive decomposition, delegation, and execution. However, existing orchestrators often rely on hand-crafted logic and prompting strategies, limiting adaptation and generalization across tasks and executor configurations. We propose E3-Orch, a reinforcement learning framework for effective, efficient, and extensible agentic orchestration based on a milestone-plan-act workflow. Instead of planning all subtasks upfront, E3-Orch organizes execution around milestones, a mid-level abstraction that scopes planning around meaningful intermediate objectives and allows orchestration decisions to adapt as execution progresses. For each milestone, the orchestrator builds a dependency-aware plan, assigns subtasks to suitable executors, and executes independent subtasks in parallel. We train the orchestration policy from execution feedback, using milestone and plan decisions as units for fine-grained credit assignment. Tree-structured rollouts compare alternative decisions under shared execution histories, while complementary rewards optimize task performance, execution cost, and planning completeness, including an uncertainty-aware performance reward for stochastic downstream outcomes. Across seven benchmarks, E3-Orch achieves the best task performance under multiple executor configurations, improving over the strongest baselines by 0.7--3.8 points and delivering 1.16--1.59× higher intelligence efficiency. The learned policy also transfers to unseen executor configurations introduced only at evaluation time, supporting extensible agentic orchestration.