Search papers, labs, and topics across Lattice.
This paper introduces EASy, a novel framework for optimizing both task performance and computational efficiency in LLM-based agentic systems through reinforcement learning. By incorporating executor capability and cost profiles, EASy enables context-sensitive coordination that adapts to evolving task contexts and intermediate feedback. Experimental results demonstrate that EASy outperforms existing agentic baselines in achieving favorable performance-efficiency trade-offs across various complex tasks, including mathematical reasoning and embodied decision-making.
EASy achieves superior performance-efficiency trade-offs by intelligently coordinating heterogeneous executors based on their capabilities and costs, reshaping agentic system design.
Agentic systems have emerged as a promising paradigm for solving complex tasks by coordinating specialized LLM-based agents. However, most existing systems primarily optimize task success while giving limited consideration to execution efficiency under practical constraints such as executor capability and computational cost. Existing router-based methods have limited ability to reason over rich, evolving task contexts, multi-step dependencies, and intermediate execution feedback, and often generalize poorly to unseen executors. We propose EASy, a trainable agentic framework that jointly optimizes task performance and computational efficiency through reinforcement learning. EASy equips an LLM-based orchestrator with explicit knowledge of the capability and cost profiles of heterogeneous executors, enabling context-sensitive coordination beyond performance-only routing. It further introduces a milestone-plan-act workflow that decomposes complex tasks into manageable milestones, constructs dependency-aware execution graphs, assigns suitable executors, and parallelizes independent steps while adapting subsequent decisions to intermediate outcomes. To train the orchestrator, we develop a tree-structured rollout procedure that explores alternative milestone decompositions and execution plans, together with multi-component rewards that capture task correctness, execution efficiency, and trajectory completeness. Extensive experiments on mathematical reasoning, embodied decision-making, and deep research benchmarks show that EASy consistently achieves stronger performance-efficiency trade-offs than strong agentic baselines.
