Optimizing Agentic Workflows using Meta-tools
This addresses operational costs and failures in agentic AI for developers and users, though it is incremental as it optimizes existing workflows rather than introducing a new paradigm.
The paper tackles the inefficiency and unreliability of agentic AI workflows by introducing Agent Workflow Optimization (AWO), which reduces LLM calls by up to 11.9% and increases task success rates by up to 4.2 percentage points.
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.