QC
Qianshu Cai
cs.AIcs.LGcs.SE
On Valency
published · living versionsW_d9x5tsjc·v1 · currentpublished
DAGLoop: Aligning Method Design with Experimental Feedback in Automated AI Research
with Dengyuxing Wang, Yonggang Zhang, Huajiang Zheng, Jun Song +2
1 version
Preprints & journals
5 papers in the corpus · 2026DAGLoop: Aligning Method Design with Experimental Feedback in Automated AI Research2610.25089v1 · Dengyuxing Wang, Yonggang Zhang, Qianshu Cai et al.2026 · 0 citationsarXivon Valency
A Theory of Reliable Self-Evolution for Agent Harnesses2609.08175v2 · Qianshu Cai, Yonggang Zhang, Jun Nie et al.2026 · 0 citationsarXiv
EvolveNet: Collaborative Harness Evolution for Agent Self-Improvement2608.04968v2 · Jun Nie, Yonggang Zhang, Qianshu Cai et al.2026 · 0 citationsarXiv
TTHE: Test-Time Harness Evolution2607.08124v2 · Jun Nie, Yonggang Zhang, Jun Song et al.2026 · 0 citationsarXiv
MOSS: Self-Evolution through Source-Level Rewriting in Autonomous Agent Systems2605.22794v2 · Qianshu Cai, Yonggang Zhang, Xianzhang Jia et al.2026 · 0 citationsarXiv
Career total: 7 works. 5 are in this corpus.
Profile built from the corpus for this byline.
Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.