Pith. sign in

REVIEW 4 cited by

GeLLMO: Generalizing Large Language Models for Multi-property Molecule Optimization

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2502.13398 v2 pith:EUPNQL2T submitted 2025-02-19 cs.LG cs.AIcs.CLphysics.chem-phq-bio.QM

Vishal Dey , Xiao Hu , Xia Ning This is my paper
classification cs.LGcs.AIcs.CLphysics.chem-phq-bio.QM
keywords optimizationtasksmoleculegellmosllmsmodelsdemonstrategeneralizability
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Despite recent advancements, most computational methods for molecule optimization are constrained to single- or double-property optimization tasks and suffer from poor scalability and generalizability to novel optimization tasks. Meanwhile, Large Language Models (LLMs) demonstrate remarkable out-of-domain generalizability to novel tasks. To demonstrate LLMs' potential for molecule optimization, we introduce MuMOInstruct, the first high-quality instruction-tuning dataset specifically focused on complex multi-property molecule optimization tasks. Leveraging MuMOInstruct, we develop GeLLMOs, a series of instruction-tuned LLMs for molecule optimization. Extensive evaluations across 5 in-domain and 5 out-of-domain tasks demonstrate that GeLLMOs consistently outperform state-of-the-art baselines. GeLLMOs also exhibit outstanding zero-shot generalization to unseen tasks, significantly outperforming powerful closed-source LLMs. Such strong generalizability demonstrates the tremendous potential of GeLLMOs as foundational models for molecule optimization, thereby tackling novel optimization tasks without resource-intensive retraining. MuMOInstruct, models, and code are accessible through https://github.com/ninglab/GeLLMO.

Discussion (0). Sign in to comment.

Forward citations

Cited by 4 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. SLIM: Sparse Latent Steering for Interpretable and Property-Directed LLM-Based Molecular Editing

    cs.LG 2026-05 unverdicted novelty 7.0 of 10

    SLIM decomposes LLM hidden states via sparse autoencoders with learnable gates to enable precise, interpretable steering of molecular properties, yielding up to 42.4-point gains on the MolEditRL benchmark.

  2. HALO: Interactive Co-abductive Reasoning in Scientific Hypothesis Generation

    cs.HC 2026-07 conditional novelty 6.0 of 10

    HALO uses a three-stage co-abduction loop—clustering candidates by property improvement, distilling strategies, and synthesizing strategies—to help medicinal chemists produce more optimized and more diverse molecular ...

  3. Rethinking Scientific Discovery in the Agentic Era

    cs.CL 2026-07 conditional novelty 5.5 of 10

    SCION claims an agentic OS with Research Execution Plans and layered memory that beats autonomous research-agent baselines on reading, ideation, molecule design, and antibody screening.

  4. Molecular Lead Optimization via Agentic Tool Planning

    cs.LG 2026-05 unverdicted novelty 4.0 of 10

    TRACE is a trajectory-aware LLM agent that treats molecular tool selection as sequential decision-making to achieve higher success rates and larger ADMET improvements than one-step baselines on optimization tasks.

Pith tools