Learning to Construct Practical Agentic Systems

📅 2026-05-29
📈 Citations: 0
Influential: 0
📄 PDF

career value

191K/year
🤖 AI Summary
Existing large language model agent systems struggle to meet the demands of production environments—such as simplicity, controllability, and predictable inference costs—due to their high complexity, unbounded reasoning expenses, and unpredictable behavior. To address these limitations, this work proposes a practical, utility-driven agent design framework that employs “pseudo-tools” to enforce modularity, replaces dynamic planning with fixed workflows, and integrates a dedicated learning algorithm to jointly optimize component performance. The approach innovatively applies multi-objective optimization to balance inference cost and response quality, while supporting result fusion across multiple systems. Experimental results demonstrate that the proposed method significantly reduces inference costs and improves accuracy across diverse tasks, outperforming handcrafted dynamic planning baselines.
📝 Abstract
Automated design and optimization of agentic LLM-based systems leads to sophisticated systems that substantially improve result quality over off-the-shelf agentic patterns. However, studies of fielded agentic systems show that production systems focus much more on issues such as simplicity, controllability, and predictability of inference costs. In this paper we propose principled approaches to designing and optimizing practical agentic systems. We describe an agent framework that enables designers to enforce modularity in agentic systems, by defining "pseudo-tools" that call LLMs recursively on a restricted context. Using this framework we hand-engineer agents for a diverse set of tasks, and show that relative to dynamically-planned workflows, hand-constructed fixed workflows are generally cheaper and more accurate. We then propose novel learning methods for the agentic components required by this framework, namely pseudo-tools and fixed workflows. These learning methods generally outperform hand-engineered agents. We also exploit the modularity of the framework to apply multi-objective optimization methods to jointly optimize cost and response quality and blend the results of multiple learning systems.
Problem

Research questions and friction points this paper is trying to address.

agentic systems
practical design
inference cost
modularity
multi-objective optimization
Innovation

Methods, ideas, or system contributions that make the work stand out.

practical agentic systems
pseudo-tools
fixed workflows
multi-objective optimization
modular LLM agents
🔎 Similar Papers
2023-08-22Frontiers Comput. Sci.Citations: 866
2024-08-15arXiv.orgCitations: 20
A
Aditya Kumar
Carnegie Mellon University
Z
Zhihan Lei
Carnegie Mellon University
J
Jerry Yan
Carnegie Mellon University
J
Joshua W. Momo
Carnegie Mellon University
L
Lauhitya Reddy
Dept. of Computer Science, Emory University
R
Rafael Enrique Cabrera Jimenez
Carnegie Mellon University
C
Cassandra A. Cohen
Carnegie Mellon University
A
Arthur Kajiyama
Carnegie Mellon University
W
William W. Cohen
Carnegie Mellon University