Toward Autonomous Long-Horizon Engineering for ML Research

TL;DR

AiScientist is a system that enhances autonomous long-horizon ML research by combining hierarchical orchestration with durable state management, significantly improving benchmark scores.

Contribution

The paper introduces AiScientist, a novel system that integrates structured orchestration and durable artifacts to address long-horizon ML research engineering challenges.

Findings

AiScientist improves PaperBench score by 10.54 points on average.

Achieves 81.82% on MLE-Bench Lite.

File-as-Bus protocol is crucial for performance, reducing scores when removed.

Abstract

Autonomous AI research has advanced rapidly, but long-horizon ML research engineering remains difficult: agents must sustain coherent progress across task comprehension, environment setup, implementation, experimentation, and debugging over hours or days. We introduce AiScientist, a system for autonomous long-horizon engineering for ML research built on a simple principle: strong long-horizon performance requires both structured orchestration and durable state continuity. To this end, AiScientist combines hierarchical orchestration with a permission-scoped File-as-Bus workspace: a top-level Orchestrator maintains stage-level control through concise summaries and a workspace map, while specialized agents repeatedly re-ground on durable artifacts such as analyses, plans, code, and experimental evidence rather than relying primarily on conversational handoffs, yielding thin control over thick state. Across two complementary benchmarks, AiScientist improves PaperBench score by 10.54 points on average over the best matched baseline and achieves 81.82 Any Medal% on MLE-Bench Lite. Ablation studies further show that File-as-Bus protocol is a key driver of performance, reducing PaperBench by 6.41 points and MLE-Bench Lite by 31.82 points when removed. These results suggest that long-horizon ML research engineering is a systems problem of coordinating specialized work over durable project state, rather than a purely local reasoning problem.