One paper accepted at the AI4MATH workshop at ICML
CORE research group has one paper accepted at the AI4MATH workshop at the International Conference on Machine Learning (ICML) 2025.
The paper "A Compute-Matched Re-Evaluation of TroVE on MATH" by Tobias Sesterhenn, Ian Berlot-Attwell, Janis Zenkner and Christian Bartelt has been accepted at the AI4MATH workshop @ ICML 2025. The International Conference on Machine Learning (ICML, Rank A*) is the premier gathering of professionals dedicated to the advancement of the branch of machine learning and will be held in Vancouver, July 13 - July 19th, 2025.
Abstract: Reusing established theorems and formulas is central to mathematical problem solving, serving as essential building blocks for tackling increasingly complex challenges. Recent work, TroVE, argues that code-generating Large Language Models (LLMs) can benefit similarly on the MATH benchmark by inducing and reusing higher-level toolboxes. By allocating computational budget across an ensemble of three modes - directly generating code, creating tools, and reusing tools - TroVE claims to outperform a PRIMITIVE baseline that only performs direct generation. However, recent analysis (Berlot-Attwell et al., 2024) casts doubt on these gains, noting that the tools created are often trivial or rarely reused, suggesting that improvements may stem from self-consistency or self-correction. In this work, we re-evaluate TroVE on MATH, analyze the impact of each of its modes, and show that its benefit does not come from these mechanisms, but simply from a higher computational budget spent for TroVE compared to PRIMITIVE. To this end, we also perform a small correction in the original implementation of TroVE's selection mechanism, boosting TroVE's performance on MATH by 3% in accuracy. After matching for compute, the benefit of TroVE reduces to a marginal improvement of 1%, suggesting that this toolbox approach does not provide a significant benefit on MATH.