A Vocabulary for Multi-Agent Automated Research Systems
We introduce a vocabulary for automated research systems built from one or more agents to make their design choices easier to describe and compare. The vocabulary specifies 1) who the agents are, 2) what operations are available in the system, 3) who may invoke them, 4) how agents communicate, 5) what information is visible within and across runs, 6) how the next action is chosen, 7) how a run begins, and 8) how outputs are evaluated. A trajectory records one run from the input task to the retur
Record details
Published: 12 July 2026
Source: HuggingFace Daily Papers
Category: Research
Topics: Agents & autonomy
Retrieved: 29 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.
See like a Robot: Robot-Centric Pointmaps for Vision-Language-Action Models
HuggingFace Daily Papers · 12 July 2026
Know Before Fix: QA-Driven Repository Knowledge Acquisition for Software Issue Resolution
HuggingFace Daily Papers · 12 July 2026
LOGOS: A Living Logic for AI Agent Teams That Evolve With Humans
arXiv · 12 July 2026
How Do Practitioners Build SE Agents? Insights from a Mixed-Methods Study
arXiv cs.HC · 12 July 2026
From wantons to moral agents
Alignment Forum · 12 July 2026
Route, Communicate, and Reason: Gated Routing and Adaptive Depth for Efficient Multi-Agent Reasoning
arXiv · 12 July 2026
How to cite this record
ethics.ai (12 July 2026), “A Vocabulary for Multi-Agent Automated Research Systems,” evidence record 14091, https://ethics.ai/record/14091 (originally published by HuggingFace Daily Papers).
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.