5 papers
L2G-SR: Learning to Guide LLM-based Symbolic Regression
Letian Huang, Xiangyu Wang, Haowei Lin +1
Symbolic regression searches for an equation that explains observed data. Numerical error is commonly used to guide the search, but it alone can favor an accurate surrogate over a…
Test-Time Scaling for Scientific Equation Discovery
Haowei Lin, Hubert Lim, Xiangyu Wang +2
Test-time scaling (TTS) improves language model reasoning by allocating additional test-time compute, but prior work mainly studies closed-ended tasks such as math and coding. We s…
OpenHA: A Series of Open-Source Hierarchical Agentic Models in Minecraft
Zihao Wang, Muyao Li, Kaichen He +4
The choice of action spaces is a critical yet unresolved challenge in developing capable, end-to-end trainable agents. This paper first presents a large-scale, systematic compariso…
Can Language Models Discover Scaling Laws?
Haowei Lin, Haotian Ye, Wenzheng Feng +8
Discovering scaling laws for predicting model performance at scale is a fundamental and open-ended challenge, mostly reliant on slow, case specific human experimentation. To invest…
Generative Evaluation of Complex Reasoning in Large Language Models
Haowei Lin, Xiangyu Wang, Ruilin Yan +7
With powerful large language models (LLMs) demonstrating superhuman reasoning capabilities, a critical question arises: Do LLMs genuinely reason, or do they merely recall answers f…