How Much of a Harness Does a Strong Agent Need for Autonomous ML Engineering?

A paper published in October 2026 by Kirill Brilliantov, Alejandro Hernández-Cano and Emmanuel Abbé finds that open-source state-of-the-art MLE agent harnesses provide no advantage over a single session of a minimal-harness coding agent baseline under an equal time budget and the same frontier LLM backbone. Through large-scale systematic ablation studies, the authors argue the machinery layers — multi-agent orchestrators and dedicated retrieval subagents — become redundant in the coding agent setting, pointing to the backbone as the primary driver of performance. The authors conclude that elaborating hand-crafted harnesses around strong models yields poor returns for current MLE benchmarks.

content type paper https://machinelearning.apple.com/research/ published October 2026 How Much of a Harness Does a Strong Agent Need for Autonomous ML Engineering? AuthorsKirill Brilliantov†‡, Alejandro Hernández-Cano†‡ , Emmanuel Abbé† Recent autonomous machine learning engineering MLE agents have made significant progress on public leaderboards. Often motivated by progress stagnation over long-horizon cycles and limited Large Language Model LLM primitives, modern MLE agents are deployed on top of increasingly elaborate machinery: multi-agent orchestrators, dedicated retrieval subagents, and more. While such harnesses expand, the use of more primitive but improved coding agents—where LLMs have direct access to the execution environment through read, write, and bash primitives—has received little attention in the field. In this paper we find that, under an equal time budget and the same frontier LLM backbone, open-source state-of-the-art harnesses provide no advantages over a single session of a minimal-harness coding agent baseline, pointing to the backbone as the primary driver for performance. Via a series of large-scale systematic ablation studies, we argue that the machinery layers become redundant in the coding agent setting. We conclude that the effort spent elaborating hand-crafted harnesses around strong models yields poor returns for current MLE benchmarks. SCLATE: A Substrate for Continual-Learning Agent Training and Evaluation September 30, 2026 research area Methods and Algorithms https://machinelearning.apple.com/research/?domain=Methods%20and%20Algorithms , research area Tools, Platforms, Frameworks https://machinelearning.apple.com/research/?domain=Tools%2C%20Platforms%2C%20Frameworks Continual-learning agents are systems of models, harnesses, and memory operating over long multi-session horizons. Evaluating and training them requires interleaving tasks with agent-side events such as session stop and start, crons, and memory consolidation. Yet existing benchmarks and training frameworks schedule only the benchmark’s own events, leaving each benchmark and agent pair to build a custom scheduling loop. We present SCLATE, an… AgentBuilder: Exploring Scaffolds for Prototyping User Experiences of Interface Agents January 9, 2026 research area Human-Computer Interaction https://machinelearning.apple.com/research/?domain=Human-Computer%20Interaction Interface agents powered by generative AI models referred to as “agents” can automate actions based on user commands. An important aspect of developing agents is their user experience i.e., agent experience . There is a growing need to provide scaffolds for a broader set of individuals beyond AI engineers to prototype agent experiences, since they can contribute valuable perspectives to designing agent experiences. In this work, we explore the…