How Much of a Harness Does a Strong Agent Need for Autonomous ML Engineering?
How Much of a Harness Does a Strong Agent Need for Autonomous ML Engineering? - Apple Machine Learning Research research area Methods and Algorithms content type paper published October 2026 How Much of a Harness Does a Strong Agent Need for Autonomous ML Engineering?
- Apple Machine Learning Research research area Methods and Algorithms content type paper published October 2026 How Much of a Harness Does a Strong Agent Need for Autonomous ML Engineering?
- Authors Kirill Brilliantov†‡, Alejandro Hernández-Cano†‡**, Emmanuel Abbé† Recent autonomous machine learning engineering (MLE) agents have made significant progress on public leaderboards.
- We conclude that the effort spent elaborating hand-crafted harnesses around strong models yields poor returns for current MLE benchmarks.
- Apple Machine Learning Research research area Methods and Algorithms
content type paper published October 2026
How Much of a Harness Does a Strong Agent Need for Autonomous ML Engineering?
Authors Kirill 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 , research area Tools, Platforms, Frameworks
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
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…
Discover opportunities in Machine Learning.
Our research in machine learning breaks new ground every day.
Sources
Related stories
DeskForge Corpus Improves Computer-Use Agent Accuracy
A new corpus of annotated desktop observations, DeskForge, enables computer-use agents to achieve higher accuracy in complex desktop scenes.
SCLATE: A Substrate for Continual-Learning Agent Training and Evaluation
- Apple Machine Learning Research research area Methods and Algorithms , research area Tools, Platforms, Frameworks content type paper published September 2026 SCLATE: A Substrate for Continual-Learning Agent Training and Evaluation Authors Youngmok Jung, Sirajul Salekin, Henry.
Why Read a Research Paper When You Can Turn It Into an AI Agent?
Have you ever read a paper in Science or Nature and thought, “Man, that research was so cool.
Salesforce Signs Definitive Agreement to Acquire Listen Labs
Salesforce, the 1 AI CRM, today announced it has signed a definitive agreement to acquire Listen Labs, an AI-powered customer research and human simulation platform. Listen Labs’s AI agents design studies, conduct in-depth research, and synthesize insights, automating the.
Automating coherent long-form video generation
Yale Song and Yiwen Song, Research Scientists, Google We introduce a unified multi-agent framework that autonomously generates temporally consistent, long-form video narratives, overcoming the identity drift and cascading failures of current linear AI pipelines. Recent.
ToolGrad: Efficient tool-use dataset generation with textual "gradients"
Zhongyi Zhou, Research Scientist, and Ruofei Du, Interactive Perception & Graphics Lead, Google XR ToolGrad is a data generation framework that reverses the traditional paradigm by first generating tool-use answers before user queries. We show this design enables LLMs to achieve.
NVIDIA DGX Spark 64GB Gives Developers More Ways to Build and Scale Local AI
Local AI is becoming more useful by the token. As AI agents move from experiments into everyday development, increasingly capable open models are shrinking to fit on more devices, giving builders more to run locally.
Agentic Retrieval Guide: Beyond Naive RAG - LlamaIndex
RAG has come a long way since the days of naive chunk retrieval; now agentic strategies are table stakes. Nowadays, an AI engineer has to be aware of a plethora of techniques and terminology that encompass the data-retrieval aspects of agentic systems: hybrid search, CRAG.