- Rating
- 3(+1)
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 3
- Soundness
- 2
Read review
Paper summary
The paper couples the reasoning abilities of the frontier LLM models with the generative abilities of the flow and diffusion models for natural language guided scientific discovery. Given knowledge about the current abilities of the generator through samples and their observables, LLM proposes the next sub-goal to optimize the generator on and provides ordinal feedback for generator training through DPO. The frozen LLM, based on its broader scientific knowledge, proposes the sub-goals that eventually lead towards the user-specified natural language goal. The authors evaluate the proposed pipeline, LFD, on discovering therapeutic peptides and small molecules. Across 5 case studies, LFD outperforms the proxy reward guided baselines on the domain specific metrics while satisfying the goal descriptions in the input prompt.
Critical strengths
- Well-motivated problem statement:
- Shifting from proxy reward functions to a more coarse natural language goal is important for scientific applications.
- The challenges of miscalibrated scores, negligible density over the goal-satisfying region are rightly identified and form a justified basis for pipeline design choices.
- Goal 5 is a strong evidence in favor of the LFD pipeline
- The pre-trained model yields no hits in 38,500 samples; LFD finds one at round 6.
- Even the reward-guided baselines fail despite an LLM-generated binary reward for the full goal, which isolates the adaptive curriculum’s contribution.
Critical weaknesses
- Unexplained experimental design choices:
- How are the number of rounds decided? The performance is sensitive to the number of rounds provided to the pipeline
- There is no information on the number of random seeds tested per experiment and how many candidates are finally proposed at the end of all the rounds
- Missing simple ablation on LFD but with only the user specified goal and no adaptive curriculum.
- Several observables are trained predictors and implicitly steer the curriculum
- Peptide observables include predicted developability bands. Further, the non-hemolysis band implicitly informs about the toxicity metric.
- The curricula track the supplied descriptors closely, so the observables implicitly steer the search. No ablation over the observable set.
- Prompts for the LLM are highly verbose and customised per task. For example, Goal 5 explicitly forbids the carbon-only linkage requirement, a domain knowledge which wasn’t necessary in the prompt.
Questions for authors
Clarification Questions:
- For the sub-goal generation, how is it ensured that the batch generated by the student is representative of the generator’s current abilities? Given the finite sample regime, it could be a limited view of the generator's terminal density and hence the sampling noise could drive the curriculum. Would a larger batch or a different sampling seed recover the same sub-goal sequence?
- How does the DPO training deal with the skewness in the sizes of the positive and negative candidate sets, that influences the size of preference dataset?
- The experimental setup mentions that Gemini 3.1 Pro was used to construct the curriculum but Gemini 3.7 Flash was used for LLM judgements. What is the rationale behind using different LLM backbones for the two tasks?
- What is the standard deviation in table 1 and 2 over? It seems to be over multiple proposed candidates instead of different end-to-end runs of the discovery process, which raises a question on performance reproducibility.
- What is the distance metric in table 1?
- Couldn’t exclusion of abstained candidates lead to loss of potential pathway to the goal? Is it possible that a candidate is neither positive nor negative at the current round, but allows for future promising candidates? Further, even the candidates with unstable classification on 2 runs are discarded. What fraction of candidates are discarded on average in the experiments?
- What happens when the specified goal is unachievable, due to infeasible constraints? How does the pipeline handle this empirically?
Suggested experiments:
- How does the performance of LFD and the designed curriculum vary with the number of rounds T, since Appendix D mentions some subgoals are reused for multiple rounds.
- Currently the main case study results are on the Gemini models. Providing results on at least 1 more LLM would be useful to evaluate the robustness of the pipeline to the choice of LLM backbone.
- It might be interesting to see an ablation where the observables just contain a compact representation of the candidate, without any other measured properties.
- Continuing the previous point, how sensitive is the performance to the provided observables? From the provided curricula, it appears that the provided observables bias the intermediate goals of the LLM towards them, providing an implicit external guidance on the trajectory to follow.
Future Work
- It could be an interesting future study on what observables are most important in the prompt and is there a pattern that surfaces across the domains.
Overall, I think the work is pretty interesting and I'll be open to improving my score based on the author responses to the questions.
6 comments
Rebuttal (2/3): Ablations, clarifications on replicability and metrics, and experiment on discarded judgments
Ablation on DPO training with unbalanced data We added “Ablation on sensitivity to unbalanced positive-negative class sizes” in Appendix E.6 of the updated manuscript. We compare 40 labelled candidates split into 20/20, 36/4, or 4/36 positives/negatives, and 80 candidates split into 40/40, 60/20, or 20/60. Each setting runs DPO from the same pre-trained model and is evaluated on 1,000 fresh peptides. Figure 13 shows similar results across these settings. Across all splits, CPP-predictor scores remain around 13% and predicted hemolysis around 42%, showing that DPO achieves comparable performance even with 9:1 or 1:9 positive-to-negative ratios in these experiments.
Why using Gemini 3.1 Pro and 3.7 Flash for different roles We used Gemini 3.1 Pro for curriculum construction, while assigning the more frequent candidate judgments to the cheaper Gemini 3.7 Flash to reduce API costs.
Standard deviation, seed tested, replicability of generative discovery The standard deviation in Table 1-2 is indeed over multiple proposed candidates. We want to clarify the replicability of our results. As is currently the standard in the community of discovery via generative models [1,2,3], we report in the manuscript the results of the best run obtained, akin to the so-called BoN (Best-of-N) procedure. This was done by evaluating LFD models after each subgoal . In particular, the model is sampled, and the generated designs are judged by the LLM on the final goal . Then, we estimated with such judgments , we kept running the most promising runs, and killed the others. Notice that in this procedure there was no exposure of the held-out predictor used for evaluation. Such a procedure is also consistent with our limited API and compute budget, a constraint which is also very likely in practical applications where LFD can be applied. We stress that the less promising (and thus killed) runs could have resulted in a good (with respect to the downstream held-out predictor) final model and samples as well, yet due to the limited resources we have not continued such runs. We also note that the number of runs that manage to achieve good results in the end are always more than one, and the exact ratio (over all runs tested) depends on the difficulty of the goal tackled. In particular, Goal 6 was the most challenging one and although multiple runs could succeed at it (2/7 runs), several runs (5) have been killed at intermediate steps to conserve computational resources and API economic costs, as explained earlier. In simpler goals such as Goal 1, where optimality is not a binary signal, all the runs were progressing well according to the LLM assessment, and the killed ones were just the slowest ones at doing so.
Distance used in Table 1 We added an explicit definition in the paragraph “Distance from prior” in Appendix D.1 of the updated manuscript. The metric is the square root of the Jensen–Shannon divergence between the amino-acid frequency distributions of generated peptides and a reference set sampled from the pre-trained generator. Using base-2 logarithms gives a distance between 0 and 1, with larger values indicating a greater shift in amino-acid composition away from the prior. This metric is standard in peptide design as supported by the referenced works in Sec. 5.
Exclusion of abstained candidates Uncertain candidate may still lead to promising designs. Nonetheless, notice that based on the DPO loss, abstain candidates receive no direct penalty in the LFD update and can be re-sampled by the generator in future rounds. For Goals 1 (peptides), and 5 (molecules), we report the following respective % of (overall) candidates discarded per round of 8.0% and 11.2%. This filtering aims to improve the LLM reliability by avoiding judgements self-classified as uncertain, particularly where the LLM lacks sufficient evidence or expertise. An alternative would be to treat a subset of abstentions as positive, encouraging exploration in the spirit of “optimism in the face of uncertainty”. This could help explore additional pathways, but might also introduce incorrect preferences and increase computational costs. We empirically try to validate this idea by running LFD on Goal 1 by exactly turning into positives all the abstantions and the samples with at least one positive judgments. Such LFD implementation achieves comparable performance (although with a different subgoal progression) as the LFD run reported in the manuscript. In particular, AntiCP2-alt is 54.87 ± 1.22 and HemoPI2 is 40.42 ± 0.86 (respectivaly compared to the 53.54 ± 3.32 and 42.48 ± 2.04 of the manuscript). However, in this end-to-end run, it is difficult to isolate the role of the optimism due to the stochasticity of the LLM (and thus the generated subgoals) and of the peptides sampled at each step. Overall, we regard this as an interesting and promising extension of LFD.
Rebuttal (3/3): LFD with GPT-6.1 Sol, unachievable goals, and references
Unachievable goal It is straighforward to add as a preprocessing step of the LFD method a simple goal checker, which utilizes the frontier LLM scientific (e.g., chemical) and logical reasoning to assess whether the goal description admits at least a positive instance. For instance, the goal "generate small molecules with at least 2 cycles, but without cycles" clearly corresponds to an empty solutions set that can be recognized by an LLM. On the other hand, checking satisfiability of arbitrary goals is impossible in general. As a consequence, it is left to the scientist utilizing LFD the task of defining a goal believed to correspond to a non-empty solution set. Empirically, if the chosen goal indeed corresponds to an empty solutions set, LFD, run with an LLM that has sufficient understanding of the specific application, is not able to generate positive solutions. Instead, it attempts to relax the initial goal into a sequence of subgoals that allows to generate designs semantically closer to the goal description, yet not fully achieving it.
Ablation: results with another frontier LLM We added “Ablation on LLM model family” in Appendix E.3,of the updated manuscript, replacing both Gemini models with GPT-6.1 Sol, using high reasoning effort, on Goal 2 (peptides) and Goal 5 (small molecules):
| Metric | LFD with Gemini | LFD with GPT-6.1 Sol |
|---|---|---|
| CPP: pLM4CPPs (%) ↑ | 69.06 ± 6.36 | 74.05 ± 2.37 |
| CPP: HemoPI2 (%) ↓ | 37.02 ± 1.69 | 33.73 ± 0.66 |
| GSK3β: GNINA ↑ | 6.77 ± 0.11 | 6.69 ± 0.07 |
| GSK3β: Vina ↓ | −8.84 ± 0.16 | −8.74 ± 0.11 |
| GSK3β: rDock ↓ | −12.87 ± 0.57 | −12.93 ± 0.33 |
LFD with GPT-6.1 Sol achieves higher mean predicted CPP activity and lower mean predicted hemolysis, while retaining comparable docking scores. These results support robustness to the teacher’s model family across the two evaluated tasks. We also report the resulting curricula in the same subsection.
Let us know if these clarifications address your questions and, if so, would lead you to raise the score as you mentioned. We would be happy to clarify any additional doubts. Thanks again for your review!
References
[1] Mathematical discoveries from program search with large language models. Romera-Paredes et al., Nature 2024.
[2] Eureka: Human-Level Reward Design via Coding Large Language Models. Ma et al., ICLR 2024.
[3] Learning to Discover at Test Time, Yuksekgonul et al., ICML 2026.
Rebuttal (1/3): Ablations and clarifications on LFD pipeline
We thank the Reviewer for recognizing the problem tackled of adaptation to natural-language goals as important, that we recognized the right challenges, and that Goal 6 (previously 5) is a strong evidence in favor of LFD. In the following, we aim to sharply address all limitations and questions mentioned within the review.
Number of rounds LFD is typically run continually: it does not require prescribing a fixed curriculum length, and T can serve as an upper limit determined by available resources or need. In practice, we stop when the LLM judges that sufficiently many generated designs satisfy the final goal according to its belief, or when the computational budget is reached. For instance, for Goal 6, we stopped the run at round 6 when the LLM judged that a generated candidate matched the final goal requirements, for which we then confirmed this hit using the held-out checker (Figure 10).
Ablation of LFD without an adaptive curriculum We added a final-goal-only baseline using LLM categorical feedback, reported in the new subsection “Ablation on directly optimizing the final goal without a curriculum” (Appendix E.7, Table 11) of the updated manuscript. The LLM judges candidates directly against the user-specified goal, without intermediate sub-goals. We evaluate this baseline on Goal 2 (CPP) and Goal 5 (GSK3β):
This baseline clearly underperforms LFD on both tasks. Moreover, final-goal-only LFD cannot form preference pairs when no positive samples are available. Goal 6 clearly demonstrates this limitation: the initial FlowMol3 model generated no final-goal positives in more than 38,000 samples. Intermediate sub-goals provide the supervision needed to begin adaptation in this setting.
Trained predictors as observables and ablation over the observable set (compact representation) We regard these observables as task-agnostic because they describe general peptide properties relevant across most peptide-design tasks, rather than properties specific to anticancer activity. We agree, however, that this distinction is ambiguous here. To address this concern, we added an ablation removing the developability and non-hemolysis bands from the observables. We report this ablation under “Ablation on the observables” (Appendix E.1, Figure 11) in the updated manuscript. We evaluate six rounds of Goal 1, retaining the sequence and remaining physicochemical descriptors. At round six, Figure 11 shows mean AntiCP2-alt scores of approximately 43% without these bands and 40% with them, corresponding HemoPI2 scores are approximately 44% and 43%, respectively. The scores remain similar, with overlapping 95% confidence intervals, although the proposed sub-goals change. Thus, the supplied observables influence curriculum construction, but LFD still improves predicted anticancer activity without these bands while maintaining predicted hemolysis comparable to the run that includes them. We thank the Reviewer for motivating this ablation.
LLM prompts verbosity The prompts provide scientific context and prior domain knowledge, together with general instructions (Appendix B.2). Making this context explicit allows scientists to inspect and validate the assumptions guiding discovery. In the example raised by the Reviewer, now Goal 6, the carbon-only linkage instruction prevents the controller from adding a requirement absent from the user’s goal. It does not impose an additional chemical restriction. Such prompt templates can easily be drafted by an LLM from the discovery goal and can be reviewed by a scientist. Their necessary detail will depend on the teacher’s capabilities: we expect more capable models may require less biological and chemical context, although prompt simplification has not been evaluated here.
Stochasticity of finite-sample generated batch for subgoal generation Indeed a finite batch estimates the generator’s current capabilities (or coverage) without fully describing its density. As in minibatch stochastic optimization (e.g., stochastic gradient descent), noisy sample estimates can nevertheless support useful updates. Both candidate sampling and LLM proposals are stochastic: larger batches can reduce sampling noise, but need not recover an identical sub-goal sequence. We therefore examined curriculum variation across different seeds. Although the proposed sub-goals differ, the resulting curricula consistently improve evaluations against the original user-specified discovery goal, supporting the practical usefulness of finite-batch feedback despite variation in the subgoal sequence.