Improving the speed and energy-efficiency of AI agents
A new system, known as Murakkab, optimizes the design and deployment of multistep workflows that power AI applications.
Record details
Published: 25 June 2026
Source: MIT News
Category: News
Topics: Agents & autonomy · Environment
Retrieved: 14 July 2026
Related evidence
These records share source-supplied organisations, an exact publisher byline, automatic topics or regions. The reason is shown on every link; related does not mean supporting, agreeing with or verifying this record.
Q&A: What is agentic AI today, and what do we want it to be?
MIT News · 30 June 2026
Tiny robot boats build floating structures
MIT News · 9 July 2026
Mercor buys Deeptune to build training environments for AI agents
SiliconANGLE AI · 9 July 2026
New method aims to keep kids safe from illegal AI-generated content
MIT News · 13 July 2026
Turing Award winner Rich Sutton founds Oak Lab to build AI agents that learn on their own
The Decoder · 13 July 2026
AI agents create virtual playgrounds to help robots get crucial training data
MIT News · 13 July 2026
How to cite this record
ethics.ai (25 June 2026), “Improving the speed and energy-efficiency of AI agents,” evidence record 1608, https://ethics.ai/record/1608 (originally published by MIT News).
Use and limitations
This page is a stable index and citation surface for a source record. ethics.ai did not author the underlying report and has not independently verified every claim. Automatic topics may be imperfect. For consequential use, quote and cite the original publisher.