BrowseComp-Plus

Mentions · 7d0
Mentions · 30d2
All mentions2
First seenOct 13, 2026
Last mentioned7d ago

Timeline

2 articles · newest first

ReGE turns recorded agent experience into guidance for a retry

ReGE-Syn raises accuracy 9.9 points for GPT and 8.8 for Claude while cutting guidance-construction tokens versus adapted AggAgent.

Hugging Face daily papersOct 23, 20:00 UTC · 7d agoAI research1

CarryOn organizes long-horizon agent context around task objects

Authors report gains of 5.8% and 7.0% with token cuts of 51.9% and 22.9% on two benchmarks.

Hugging Face daily papersOct 13, 13:35 UTC · 17d agoAI research2 · 1 read

Appears with

AggAgentproduct · 1
CarryOnproduct · 1
Claudeai model · 1
GPTai model · 1
OSWorld 2.0product · 1
ReGE-Synproduct · 1
ReGEproduct · 1

Entities are extracted by the model from each article. First seen Oct 13, 2026, last mentioned 7d ago. Watching keeps it in this browser only (no account); the watchlist page and dashboard alerts use it.