ExLLM: Experience-Enhanced LLM Optimization for Molecular Design and Beyond

• URL: http://arxiv.org/abs/2502.12845v4
• Date: Wed, 08 Oct 2025 09:32:42 GMT
• Title: ExLLM: Experience-Enhanced LLM Optimization for Molecular Design and Beyond
• Authors: Nian Ran, Yue Wang, Xiaoyuan Zhang, Zhongzheng Li, Qingsong Ran, Wenhao Li, Richard Allmendinger,
• Abstract summary: We introduce ExLLM (Experience-Enhanced LLM optimization), an LLM-as-optimizer framework with three components.<n>ExLLM sets new state-of-the-art results on PMO and generalizes strongly in our setup.
• Score: 16.374785306736474
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Molecular design involves an enormous and irregular search space, where traditional optimizers such as Bayesian optimization, genetic algorithms, and generative models struggle to leverage expert knowledge or handle complex feedback. Recently, LLMs have been used as optimizers, achieving promising results on benchmarks such as PMO. However, existing approaches rely only on prompting or extra training, without mechanisms to handle complex feedback or maintain scalable memory. In particular, the common practice of appending or summarizing experiences at every query leads to redundancy, degraded exploration, and ultimately poor final outcomes under large-scale iterative search. We introduce ExLLM (Experience-Enhanced LLM optimization), an LLM-as-optimizer framework with three components: (1) a compact, evolving experience snippet tailored to large discrete spaces that distills non-redundant cues and improves convergence at low cost; (2) a simple yet effective k-offspring scheme that widens exploration per call and reduces orchestration cost; and (3) a lightweight feedback adapter that normalizes objectives for selection while formatting constraints and expert hints for iteration. ExLLM sets new state-of-the-art results on PMO and generalizes strongly in our setup, it sets records on circle packing and stellarator design, and yields consistent gains across additional domains requiring only a task-description template and evaluation functions to transfer.

Related papers

• DRAGON: LLM-Driven Decomposition and Reconstruction Agents for Large-Scale Combinatorial Optimization [40.88623618289683]
  Large Language Models (LLMs) have recently shown promise in addressing optimization problems (COPs) through prompt-based strategies.<n>We propose DRAGON, which combines the strengths of metaheuristic design and LLM reasoning.<n>By continuously interacting with the optimization environment and leveraging an adaptive experience memory, the agents iteratively learn from feedback.
  arXiv  Detail & Related papers  (2026-01-10T09:31:40Z)
• LLM4CMO: Large Language Model-aided Algorithm Design for Constrained Multiobjective Optimization [54.35609820607923]
  Large language models (LLMs) offer new opportunities for assisting with algorithm design.<n>We propose LLM4CMO, a novel CMOEA based on a dual-population, two-stage framework.<n>LLMs can serve as efficient co-designers in the development of complex evolutionary optimization algorithms.
  arXiv  Detail & Related papers  (2025-08-16T02:00:57Z)
• When Relevance Meets Novelty: Dual-Stable Periodic Optimization for Exploratory Recommendation [6.663356205396985]
  Large language models (LLMs) demonstrate potential with their diverse content generation capabilities.<n>Existing LLM-enhanced dual-model frameworks face two major limitations.<n>First, they overlook long-term preferences driven by group identity, leading to biased interest modeling.<n>Second, they suffer from static optimization flaws, as a one-time alignment process fails to leverage incremental user data for closed-loop optimization.
  arXiv  Detail & Related papers  (2025-08-01T09:10:56Z)
• Mixture of Experts in Large Language Models [3.1494372222592224]
  MoE architecture significantly enhances model performance while maintaining minimal computational overhead.<n>Our analysis identifies key advantages of MoE, including superior model capacity, improved task-specific performance, and the ability to scale model capacity efficiently.<n>This review outlines current research limitations, open challenges, and promising future directions, providing a foundation for continued innovation in MoE architecture and its applications.
  arXiv  Detail & Related papers  (2025-07-15T10:36:43Z)
• Grammar-Guided Evolutionary Search for Discrete Prompt Optimisation [63.97051732013936]
  We propose an evolutionary search approach to automated discrete prompt optimisation consisting of two phases.<n>In the first phase, grammar-guided genetic programming is invoked to synthesise prompt-creating programmes.<n>In the second phase, local search is applied to explore the neighbourhoods of best-performing programmes.
  arXiv  Detail & Related papers  (2025-07-14T14:34:15Z)
• Embed Progressive Implicit Preference in Unified Space for Deep Collaborative Filtering [13.24227546548424]
  Generalized Neural Ordinal Logistic Regression (GNOLR) is proposed to capture the structured progression of user engagement.<n>GNOLR enhances predictive accuracy, captures the progression of user engagement, and simplifies the retrieval process.<n>Experiments on ten real-world datasets show that GNOLR significantly outperforms state-of-the-art methods in efficiency and adaptability.
  arXiv  Detail & Related papers  (2025-05-27T08:43:35Z)
• Make Optimization Once and for All with Fine-grained Guidance [78.14885351827232]
  Learning to Optimize (L2O) enhances optimization efficiency with integrated neural networks.<n>L2O paradigms achieve great outcomes, e.g., refitting, generating unseen solutions iteratively or directly.<n>Our analyses explore general framework for learning optimization, called Diff-L2O, focusing on augmenting solutions from a wider view.
  arXiv  Detail & Related papers  (2025-03-14T14:48:12Z)
• PharMolixFM: All-Atom Foundation Models for Molecular Modeling and Generation [4.402280157389038]
  We propose PharMolixFM, a unified framework for constructing all-atom foundation models. Our framework includes three variants using state-of-the-art multi-modal generative models. PharMolixFM-Diff achieves competitive prediction accuracy in protein-small-molecule docking.
  arXiv  Detail & Related papers  (2025-03-12T12:53:43Z)
• Collaborative Expert LLMs Guided Multi-Objective Molecular Optimization [51.104444856052204]
  We present MultiMol, a collaborative large language model (LLM) system designed to guide multi-objective molecular optimization. In evaluations across six multi-objective optimization tasks, MultiMol significantly outperforms existing methods, achieving a 82.30% success rate.
  arXiv  Detail & Related papers  (2025-03-05T13:47:55Z)
• IMPROVE: Iterative Model Pipeline Refinement and Optimization Leveraging LLM Experts [28.9807389592324]
  Large language model (LLM) agents have emerged as a promising solution to automate the workflow of machine learning.<n>We introduce Iterative Refinement, a novel strategy for LLM-driven ML pipeline design inspired by how human ML experts iteratively refine models.<n>By systematically updating individual components based on real training feedback, Iterative Refinement improves overall model performance.
  arXiv  Detail & Related papers  (2025-02-25T01:52:37Z)
• Nature Language Model: Deciphering the Language of Nature for Scientific Discovery [105.55751854768297]
  Foundation models have revolutionized natural language processing and artificial intelligence. We introduce Nature Language Model (NatureLM), a sequence-based science foundation model for scientific discovery.
  arXiv  Detail & Related papers  (2025-02-11T13:08:03Z)
• Efficient and Effective Weight-Ensembling Mixture of Experts for Multi-Task Model Merging [111.8456671452411]
  Multi-task learning (MTL) leverages a shared model to accomplish multiple tasks and facilitate knowledge transfer. We propose a Weight-Ensembling Mixture of Experts (WEMoE) method for multi-task model merging. We show that WEMoE and E-WEMoE outperform state-of-the-art (SOTA) model merging methods in terms of MTL performance, generalization, and robustness.
  arXiv  Detail & Related papers  (2024-10-29T07:16:31Z)
• In-context Demonstration Matters: On Prompt Optimization for Pseudo-Supervision Refinement [71.60563181678323]
  Large language models (LLMs) have achieved great success across diverse tasks, and fine-tuning is sometimes needed to further enhance generation quality.<n>To handle these challenges, a direct solution is to generate high-confidence'' data from unsupervised downstream tasks.<n>We propose a novel approach, pseudo-supervised demonstrations aligned prompt optimization (PAPO) algorithm, which jointly refines both the prompt and the overall pseudo-supervision.
  arXiv  Detail & Related papers  (2024-10-04T03:39:28Z)
• MMEvol: Empowering Multimodal Large Language Models with Evol-Instruct [148.39859547619156]
  We propose MMEvol, a novel multimodal instruction data evolution framework.<n>MMEvol iteratively improves data quality through a refined combination of fine-grained perception, cognitive reasoning, and interaction evolution.<n>Our approach reaches state-of-the-art (SOTA) performance in nine tasks using significantly less data compared to state-of-the-art models.
  arXiv  Detail & Related papers  (2024-09-09T17:44:00Z)
• Many-Shot In-Context Learning for Molecular Inverse Design [56.65345962071059]
  Large Language Models (LLMs) have demonstrated great performance in few-shot In-Context Learning (ICL) We develop a new semi-supervised learning method that overcomes the lack of experimental data available for many-shot ICL. As we show, the new method greatly improves upon existing ICL methods for molecular design while being accessible and easy to use for scientists.
  arXiv  Detail & Related papers  (2024-07-26T21:10:50Z)
• Improving Molecular Modeling with Geometric GNNs: an Empirical Study [56.52346265722167]
  This paper focuses on the impact of different canonicalization methods, (2) graph creation strategies, and (3) auxiliary tasks, on performance, scalability and symmetry enforcement. Our findings and insights aim to guide researchers in selecting optimal modeling components for molecular modeling tasks.
  arXiv  Detail & Related papers  (2024-07-11T09:04:12Z)
• Efficient Evolutionary Search Over Chemical Space with Large Language Models [31.31899988523534]
  optimization objectives can be non-differentiable. We introduce chemistry-aware Large Language Models (LLMs) into evolutionary algorithms. Our algorithm improves both the quality of the final solution and convergence speed.
  arXiv  Detail & Related papers  (2024-06-23T06:22:49Z)
• Discovering Preference Optimization Algorithms with and for Large Language Models [50.843710797024805]
  offline preference optimization is a key method for enhancing and controlling the quality of Large Language Model (LLM) outputs. We perform objective discovery to automatically discover new state-of-the-art preference optimization algorithms without (expert) human intervention. Experiments demonstrate the state-of-the-art performance of DiscoPOP, a novel algorithm that adaptively blends logistic and exponential losses.
  arXiv  Detail & Related papers  (2024-06-12T16:58:41Z)
• Large Language Model Agent as a Mechanical Designer [7.136205674624813]
  We propose a framework that leverages a pretrained Large Language Model (LLM) in conjunction with an FEM module to autonomously generate, evaluate, and refine structural designs.<n>LLM operates without domain-specific fine-tuning, using general reasoning to propose design candidates, interpret FEM-derived performance metrics, and apply structurally sound modifications.<n>Compared to Non- Sorting Genetic Algorithm II (NSGA-II), our method achieves faster convergence and fewer FEM evaluations.
  arXiv  Detail & Related papers  (2024-04-26T16:41:24Z)
• Latent Chemical Space Searching for Plug-in Multi-objective Molecule Generation [9.442146563809953]
  We develop a versatile 'plug-in' molecular generation model that incorporates objectives related to target affinity, drug-likeness, and synthesizability. We identify PSO-ENP as the optimal variant for multi-objective molecular generation and optimization.
  arXiv  Detail & Related papers  (2024-04-10T02:37:24Z)
• Instruction Multi-Constraint Molecular Generation Using a Teacher-Student Large Language Model [49.64512917330373]
  We introduce a multi-constraint molecular generation large language model, TSMMG, akin to a student. To train TSMMG, we construct a large set of text-molecule pairs by extracting molecular knowledge from these 'teachers' We experimentally show that TSMMG remarkably performs in generating molecules meeting complex, natural language-described property requirements.
  arXiv  Detail & Related papers  (2024-03-20T02:15:55Z)
• Maximize to Explore: One Objective Function Fusing Estimation, Planning, and Exploration [87.53543137162488]
  We propose an easy-to-implement online reinforcement learning (online RL) framework called textttMEX. textttMEX integrates estimation and planning components while balancing exploration exploitation automatically. It can outperform baselines by a stable margin in various MuJoCo environments with sparse rewards.
  arXiv  Detail & Related papers  (2023-05-29T17:25:26Z)
• Scaling Vision-Language Models with Sparse Mixture of Experts [128.0882767889029]
  We show that mixture-of-experts (MoE) techniques can achieve state-of-the-art performance on a range of benchmarks over dense models of equivalent computational cost. Our research offers valuable insights into stabilizing the training of MoE models, understanding the impact of MoE on model interpretability, and balancing the trade-offs between compute performance when scaling vision-language models.
  arXiv  Detail & Related papers  (2023-03-13T16:00:31Z)
• Molecule optimization via multi-objective evolutionary in implicit chemical space [8.72872397589296]
  MOMO is a multi-objective molecule optimization framework to address the challenge by combining learning of chemical knowledge with multi-objective evolutionary search. We demonstrate the high performance of MOMO on four multi-objective property and similarity optimization tasks, and illustrate the search capability of MOMO through case studies.
  arXiv  Detail & Related papers  (2022-12-17T09:09:23Z)
• A Molecular Multimodal Foundation Model Associating Molecule Graphs with Natural Language [63.60376252491507]
  We propose a molecular multimodal foundation model which is pretrained from molecular graphs and their semantically related textual data. We believe that our model would have a broad impact on AI-empowered fields across disciplines such as biology, chemistry, materials, environment, and medicine.
  arXiv  Detail & Related papers  (2022-09-12T00:56:57Z)
• Multi-Objective Latent Space Optimization of Generative Molecular Design Models [3.1996400013865656]
  We propose a multi-objective latent space optimization (LSO) method that can significantly enhance the performance of generative molecular design (GMD) We demonstrate that our multi-objective GMD LSO method can significantly improve the performance of GMD for jointly optimizing multiple molecular properties.
  arXiv  Detail & Related papers  (2022-03-01T15:12:05Z)
• Molecular Attributes Transfer from Non-Parallel Data [57.010952598634944]
  We formulate molecular optimization as a style transfer problem and present a novel generative model that could automatically learn internal differences between two groups of non-parallel data. Experiments on two molecular optimization tasks, toxicity modification and synthesizability improvement, demonstrate that our model significantly outperforms several state-of-the-art methods.
  arXiv  Detail & Related papers  (2021-11-30T06:10:22Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.