question · intermediate · partly written
Where does a negative result live in an agent system's memory?
Where does a negative result live in an agent system's memory?
What is known
The co-scientist authors say negative results and paywalled prior art are missing from what it reads. In the AI Scientist-v2 a failed experiment is a tree node that is not the best. Robin and Kosmos report what worked. 123
Reported, not yet replicated
What is not known more
How a negative result is encoded, retrieved and weighed against a positive one in any of these systems. 123
Our inference
Observation
What is known
What is not
What would settle it
Still open here
- Does an agent system exist that stores a negative result as a first-class claim?
Not yet written: Hypotheses, What is missing, Who works on it.
Linked from
Sources
- Gottweis J, et al.. Towards an AI co-scientist (Nature version). Nature 655:487-496 (2026). paper; opened 2026-11-18 all records citing this
- Sakana AI and collaborators. The AI Scientist-v2: workshop-level automated scientific discovery via agentic tree search. arXiv 2504.08066 (2025). preprint, not peer reviewed; opened 2026-11-18 all records citing this
- Ghareeb AE, et al.. Robin: a multi-agent system for automating scientific discovery (Nature version). Nature 655:497 (2026). paper; opened 2026-11-18 all records citing this
Where it sits on the map
History of this record (5)
This record has been changed 5 times, on the dates below. The note kept against each change is written for the people who maintain the atlas, in their own shorthand, so it is not shown here; it is in the record itself.
- Kind
- big-open
- Register
- open-question
- Status
- partly written
- Last updated
- 2026-11-19
- Record
- content/questions/negative-results-in-agent-memory.json