FML-bench: A Controlled Study of AI Research Agent Strategies from the Perspective of Search Dynamics

TL;DR

FML-Bench is a new benchmark for evaluating AI research agent strategies across diverse ML tasks, emphasizing process-level metrics to understand exploration behaviors and strategy effectiveness.

Contribution

It introduces FML-Bench, a benchmark with 18 tasks and 12 behavioral metrics that separates strategy from infrastructure, enabling detailed analysis of agent performance.

Findings

Simple greedy hill-climbing performs nearly as well as complex tree-search agents.

Adaptive strategies that switch exploration modes outperform static agents.

Early convergence and focused exploration correlate with higher final performance.

Abstract

AI research agents accelerate ML research by automating hypothesis generation, experimentation, and empirical refinement. Existing agent strategies range from greedy hill-climbing to tree search and evolutionary optimization, yet which strategy choices drive performance remains unclear. Answering this question requires a benchmark that separates agent strategy (e.g., search topology) from execution infrastructure (e.g., code editor), so that performance differences are attributable to strategy rather than infrastructure, and that provides process-level metrics beyond final scores to analyze exploration behaviors. Existing benchmarks offer limited support. We propose FML-Bench, a benchmark of 18 fundamental ML research tasks across 10 domains that separates agent strategy from execution infrastructure and defines 12 process-level behavioral metrics. Evaluating six representative agents, we find that: (1) strategy complexity alone does not guarantee strong performance: a simple greedy hill-climber nearly matches the best-performing tree-search agent, both well above the remaining agents; (2) our analysis suggests this pattern relates to improvement opportunity structure: greedy search tends to be more effective when opportunities are dense, while tree-search and evolutionary strategies tend to be more effective when opportunities are sparse; an adaptive agent built on this insight switches to broader exploration upon detecting improvement stagnation and outperforms the other six agents, lending initial support to this observation; and (3) process-level analysis reveals that early convergence and directionally focused exploration are significantly associated with final performance, while solution diversity and compute cost are not. Our benchmark is available at: https://github.com/qrzou/FML-bench.