SciMARS: Multi-Agent Recursive Self-Improvement for Closed-Loop Scientific Discovery
Opens the thread with a harness design: recursive per-task adaptation of a multi-agent discovery loop.
3 items · 2 sources · 3 days
Operational story trace
Follow in this browser to see new updates on your Live feed.
Latest change
Openhagen Worlds (Nov 18) adds calibrated environments meant to measure whether a discovery agent picks informative experiments, separate from recall, hidden scoring rules or shortcut policies.
This is a research thread, not one event: three arXiv papers on LLM agents that run scientific discovery. SciMARS (Nov 9) adapts multi-agent harnesses for closed-loop experiments, and Contrastive Discovery (Nov 10) argues agents should test competing explanations instead of one hypothesis against its negation.
Arc
Opens the thread with a harness design: recursive per-task adaptation of a multi-agent discovery loop.
Shifts the focus to hypothesis testing, proposing comparison against competing explanations.
Adds the measurement side: environments built to stop recall and shortcuts from inflating discovery scores.
Opens the thread with a harness design: recursive per-task adaptation of a multi-agent discovery loop.
Shifts the focus to hypothesis testing, proposing comparison against competing explanations.
Adds the measurement side: environments built to stop recall and shortcuts from inflating discovery scores.
What to watch — open questions
Storylines are threaded mechanically from the feed: stories that share a distinctive anchor across multiple days and sources. Each item links to its original source. The evidence trace, current state, and open questions are written by the editor routine and refreshed whenever a new beat lands.