Rong-Xi Tan

Global patterns and feasible improvement potential of phosphorus use efficiency in cereal croplands

Agentic High-Dimensional Bayesian Optimization with Hypothesis- and Evidence-Guided Search

HerA, a Hypothesis- and Evidence-guided Research Agent that uses task context, optimization feedback, and structural diagnostics to revise search hypotheses, select and configure HDBO strategies, and determine their execution length, is introduced.

Rethinking Critic Learning in PPO: Understanding and Mitigating Value Flattening

Value Flattening is identified as an important yet overlooked failure mode of critic learning in standard PPO and a simple sparse supervision strategy can mitigate it; SParse Proximal Policy Optimization is introduced, which applies the value loss to only a few well-separated states in each response to mitigate both ef...

Rethinking Learnability in Offline Data-driven Optimization

A trajectory-learning framework comprising trajectory construction, trajectory modeling, and candidate generation is formalized, and existing trajectory-based methods under it are analyzed and Uncertainty-aware Gradient-guided Trajectory Learning (UGTL), which constructs locally coherent improvement trajectories reflec...

Hot off the Press: Towards Universal Offline Black-Box Optimization via Learning Language Model Embeddings

It is suggested that unifying language model priors and learning string embedding space can overcome traditional barriers in universal BBO, paving the way for generalpurpose BBO algorithms.