Evaluating software agents on a full benchmark is expensive. A small task subset can preserve agent rankings while yielding inaccurate scores. Historical responses provide useful structure, but tasks
Evaluating software agents on a full benchmark is expensive. A small task subset can preserve agent rankings while yielding inaccurate scores. Historical responses provide useful structure, but tasks
Details from Hugging Face ↗.
HSPR: Recovering Software-Agent Benchmark Scores via Hierarchical Posterior Inference was first seen on Hugging Face · Daily papers on Oct 21, 2026. Since then it has appeared in 1 check on 1 different day. Its best position was #29 of 30, reached on Oct 21, 01:18 UTC. It dropped off the list after Oct 21, 01:18 UTC.
This page has little history so far; it stays out of search results until the item has trended on two days or has more context.
Position on Hugging Face · Daily papers at every check (lower is better).
Best rank per day (UTC).
Archived daily, weekly and monthly lists that include this entry.
Not at the moment. It was last on the list on Oct 21, 01:18 UTC, after 1 day of trending.
#29 on Hugging Face · Daily papers, on Oct 21, 01:18 UTC. Trendoday checks this list every 120 minutes.
It was first seen on Oct 21, 2026 and has been on the list on 1 day (1 check) since.