FlowBalance, a verifier-grounded self-improvement method that learns a normalized distribution over complete responses, improves average performance over FlowRL on both Qwen3-4B and Qwen3-8B, while also improving training speed and stability, avoiding direct OPSD's response-length collapse, and exhibiting higher correc...
Zi-Xun Huang, Kishan Panaganti, Hai-Tao Mi et al.· 0 citations
Recursive Synthetic Terminal Tasks (RST) is presented, a recursive verified synthesis framework for constructing long-horizon terminal-agent tasks at scale and shows no ceiling, indicating that the process can continue well beyond the scale reported here.
Zhongzhi Li, Yucheng Shi, Zongxia Li et al.· 5 citations
By using neural networks to regress the acceleration field, TracingFlow provides an exact, efficient solution to the Dynamical Optimal Acceleration Transport (DOAT) problem and recovers dynamical structures that are both mathematically optimal and biologically plausible.
Yuhao Sun, Zekun Wu, Zi-Xun Huang et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.