Optimizing Agentic Workflows using Meta-tools

TL;DR

This paper introduces AWO, a framework that optimizes agentic workflows by transforming redundant tool sequences into meta-tools, reducing costs and failures while improving success rates in complex AI tasks.

Contribution

The paper presents a novel method for analyzing and transforming agentic workflows into deterministic meta-tools to enhance efficiency and robustness.

Findings

LLM calls reduced by up to 11.9%

Task success rate increased by up to 4.2 percentage points

Workflow optimization decreases operational costs and failures

Abstract

Agentic AI enables LLM to dynamically reason, plan, and interact with tools to solve complex tasks. However, agentic workflows often require many iterative reasoning steps and tool invocations, leading to significant operational expense, end-to-end latency and failures due to hallucinations. This work introduces Agent Workflow Optimization (AWO), a framework that identifies and optimizes redundant tool execution patterns to improve the efficiency and robustness of agentic workflows. AWO analyzes existing workflow traces to discover recurring sequences of tool calls and transforms them into meta-tools, which are deterministic, composite tools that bundle multiple agent actions into a single invocation. Meta-tools bypass unnecessary intermediate LLM reasoning steps and reduce operational cost while also shortening execution paths, leading to fewer failures. Experiments on two agentic AI benchmarks show that AWO reduces the number of LLM calls up to 11.9% while also increasing the task success rate by up to 4.2 percent points.