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
As large language models become more powerful, self-evolving agents are able to tackle challenging tasks including AI for machine learning (AI4ML). In AI4ML, while empirical verification is available, it often requires computationally costly model training and evaluation, limiting the speed and scale of agent evolution...
Jiamu Bai, Li-Zhu Zhang, Xin Yu et al.· 0 citations
LLM-driven evolution enables iterative model development, but two practical goals remain underexplored: finding model designs that transfer across related tasks and sustaining improvement when training is expensive. We introduce Population Evolution (PE), a collaborative, hierarchical framework that connects ongoing lo...
Bo Peng, Li-Zhu Zhang, Yu-Hang Zhou et al.· 0 citations
These results show that evolving branch objectives and proposal policies can yield complementary harnesses whose strengths a router combines without access to test outcomes.
Hao-Yu Dong, Yu-Hang Zhou, Zi-Hao Lin et al.· 0 citations
This work introduces ToolMLBench, a suite of executable tools for data inspection, code verification, and experiment diagnosis, together with an SFT and RL pipeline for learning their use, and measures how privileged context changes the likelihood of a sampled tool action and uses this difference as a turn-level reward...
Xin Yu, Li-Zhu Zhang, Jiamu Bai et al.· 0 citations
Progress-Aware Consistent Evolution (PACEvolve), a systematic framework for governing agent memory and search dynamics, maintains a global view of search momentum and achieves state-of-the-art results across complex evolutionary benchmarks.
Minghao Yan, Bo Peng, Benjamin Coleman et al.· arXiv.org· 22 citations
Ablations show that selective intervention outperforms passive bank exposure, always-on injection, advisor-only guidance, advisor-only guidance, and general retrieval, and general retrieval and that selective intervention outperforms passive bank exposure, always-on injection, advisor-only guidance, and general retriev...
