PACEvolve++ is introduced, an advisor-model reinforcement learning framework for test-time policy adaptation in evolutionary search agents, which outperforms the state-of-the-art evolutionary search framework with frontier models, achieving faster convergence and stabilizing test-time training during evolutionary searc...
Minghao Yan, Bo Peng, Benjamin Coleman et al.· arXiv.org· 4 citations
Group-relative methods for reinforcement learning with verifiable rewards (RLVR) learn from differences in rollout outcomes. Independently sampling complete trajectories is costly and does not explicitly explore the decision space at critical positions. Feedback on a completed trajectory can reveal which earlier choice...
Fan-Chao Chen, Heng-Yu Fu, S. Venkataraman et al.· arXiv.org· 0 citations
Calibrated Clipping is proposed, a dynamic method that aligns the FP8 clipping bounds with high-precision BF16 distributions by matching the lower-bound clipping quantile and rebalancing the upper bound accordingly, which eliminates entropy surges and restores performance comparable to the BF16 baseline.
Fan Chen, Zi-Heng Jiang, Zi-Yun Wei et al.· arXiv.org· 3 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.