VeRO: An Evaluation Harness for Agents to Optimize Agents

TL;DR

VERO is a comprehensive evaluation framework and benchmark suite designed to systematically assess and improve the performance of coding agents through iterative optimization and structured evaluation.

Contribution

The paper introduces VERO, a reproducible evaluation harness and benchmark suite for agent optimization, enabling systematic analysis of agent performance improvements.

Findings

VERO facilitates structured evaluation of agent optimization strategies.

Empirical results identify modifications that reliably enhance agent performance.

The framework supports reproducible research in agent optimization.

Abstract

An important emerging application of coding agents is agent optimization: the iterative improvement of a target agent through edit-execute-evaluate cycles. Despite its relevance, the community lacks a systematic understanding of coding agent performance on this task. Agent optimization differs fundamentally from conventional software engineering: the target agent interleaves deterministic code with stochastic LLM completions, requiring structured capture of both intermediate reasoning and downstream execution outcomes. To address these challenges, we introduce VERO (Versioning, Rewards, and Observations), which provides (1) a reproducible evaluation harness with versioned agent snapshots, budget-controlled evaluation, and structured execution traces, and (2) a benchmark suite of target agents and tasks with reference evaluation procedures. Using VERO, we conduct an empirical study comparing optimizer configurations across tasks and analyzing which modifications reliably improve target agent performance. We release VERO to support research on agent optimization as a core capability for coding agents.