Showing cs.AIShow all
2 papers · 1 filter
cs.AI2026
Iris: Climbing to the Search Frontier
Ziyuan Liu, Hengqi Liu, Zichuan Wang +6
We present Iris-mini and Iris-pro, two search agents trained at the 35B-A3B and 397B-A17B scales, together with the data pipeline and training recipe behind them. Tasks are reverse…
cs.AI2026
PILOT in the Loop: Live Self-Improvement for Long-Horizon Agents
Yang Xiao, Yusong Sun, Haoyi Wu +7
Long-horizon agent runs generate experience that can improve both the current run and future work. Most self-improvement methods process this experience only after execution ends,…