- Rating
- 1
- Confidence
- 4
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
The paper studies how LLMs can enable standard BO to leverage auxiliary information commonly available in optimization tasks. It proposes AUXBO-EVOLVE and AUXBO-VICINITY, which use LLMs to propose promising configurations and rank candidate configurations, respectively. The methods are evaluated on AutoML and scientific optimization tasks.
Critical strengths
The paper has a clear motivation and addresses a common setting in optimization tasks.
Critical weaknesses
- Limited novelty. LGBO, proposed in Unleashing LLMs in Bayesian Optimization: Preference-Guided Framework for Scientific Discovery (ICLR 2026), also uses LLMs to identify preferred configurations, which are then used to raise the GP mean. The approaches appear similar, while LGBO offers a simpler formulation. The methodological advances over LGBO need to be clarified.
- Insufficient experimental evaluation. The paper lacks discussion of and comparisons with recent LLM-assisted BO baselines. Moreover, the proposed methods involve multiple components, but the ablation studies are insufficient to establish the necessity of each component.
Questions for authors
- Could the authors provide component-wise ablation studies to assess the contributions of the key design choices?
- Could the authors evaluate the methods in high-dimensional settings and combinatorial optimization problems?
- Could the authors expand both the methodological discussion and empirical comparisons to include additional BO baselines, such as BOPRO (ICLR 2025), CAKE (NeurIPS 2025), LGBO (ICLR 2026), and LABO (ICML 2026)?
- How sensitive are the methods to the prompt design and the choice of LLM backbone?
4 comments
Now, Appendix A10 contains CAKE, LABO, and LGBO results for the HPOBench task. And Figure 5 with nuclear fusion results in the main paper is also updated with these baselines. AuxBO-Evolve outperforms all the baselines in both environments.
We add results from ablating the LLM of choice in the fusion task in Appendix A11. We rerun our method and baselines with qwen3-8b model. The results and conclusions are the same. AuxBO-Evolve performs the best independent of choice of LLM.
Thank you for your response
Thank you for the authors’ response. I still believe that this work lacks novelty, and the organization of the paper also requires substantial revision. I maintain my score.
Thank you for the review. First, we request you to please refer to our general official comment on “Clarification of novelty and contributions”. Here is our answers to your concerns:
We discuss ablations in our general comment on “Clarification of the experimental design and findings”. The submitted paper already includes several component-level studies: as discussed, we view synthetic standard functions as an ablation study to isolate the effect of auxiliary feedback from the task prior. In the HPO bench, we do ablations with/without auxiliary feedback on the synthetic and a πBO comparison isolating the effect of prior knowledge from auxiliary feedback.
Additionally we perform ranking-quality ablations for AuxBO-Vicinity in Appendix Figure 6; search space dimension ablation in Figure 9 (new); and UCB, PI, and posterior-variance comparisons in Appendix Figure 7 showing robustness across acquisition functions. These cover the major components of our algorithms. Also, we would be happy to run an additional targeted ablation if you identify a specific component not covered by the existing studies.
As per our understanding, HPOBench is a combinatorial optimization problem. We also now include higher dimensional settings in our general comment “AuxBO-Evolve and AuxBO-Vicinity at higher dimensions.”
Among the suggested baselines, BOPro seems to be an LLM reasoning paper only inspired by BO and there is not a clear way to use it for BO tasks. So, we omit it. All others (LGBO, LABO, CAKE) are other LLM+BO algorithms that try to exploit the prior knowledge of LLMs and do not have any study of auxiliary information. But, we acknowledge that many of these algorithms can be combined with auxiliary information. Hence, we supplied these algorithms with auxiliary information and found that they’re still underperforming AuxBO methods in the synthetic tasks. For HPOBench, so far we only added LGBO and you can see the updated HPOBench plot for results.