arXiv AI August 28, 2026 By Nian Ran, Zhongzheng Li, Yue Wang, Qingsong Ran, Xiaoyuan Zhang, Shikun Feng, Richard Allmendinger, Xiaoguang Zhao

MCCE: A Framework for Multi-LLM Collaborative Search in Discrete Spaces with Similarity-Filtered Preference Learning

Read the original on arXiv AI →

The paper introduces MCCE, a hybrid framework that combines a frozen closed‑source large language model (LLM) with a lightweight, trainable model for multi‑objective discrete optimization. By maintaining a trajectory memory and refining the small model through reinforcement learning, the two models jointly enhance global exploration and learning. Experiments on drug‑design benchmarks demonstrate that MCCE achieves state‑of‑the‑art Pareto front quality, outperforming existing baselines.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

arXiv Machine Learning

Jun 11

My Chemical Harness: Evolutionary Molecular Design over Synthetic Pathways with Large Language Model Agents

arXiv:2606. 11256v1 Announce Type: cross Abstract: Designing molecules with target properties is most useful when candidate structures are accompanied by feasible synthetic routes.

By C\'esar Ojeda, Darius A. Faroughy, Maryam Karimi, Payam Zarrintaj, Mir Mehdi Seyedebrahimi, Mart\'in Carballo-Pacheco

llms agents fine-tuning benchmarks

arXiv Machine Learning

Jun 30

Evolution Fine-Tuning: Learning to Discover Across 371 Optimization Tasks

arXiv:2606. 29082v1 Announce Type: cross Abstract: Would experience designing faster GPU kernels also help close in on a long-standing open mathematical conjecture?

By Young-Jun Lee, Seungone Kim, Minki Kang, Alistair Cheong Liang Chuen, Zerui Chen, Seungho Han, Taehee Jung, Dongyeop Kang

llms agents reinforcement-learning fine-tuning benchmarks

arXiv Machine Learning

Jul 7

On the Design Space of Discrete Diffusion Online Adaptation for Molecular Optimization

arXiv:2607. 02834v1 Announce Type: new Abstract: Molecular optimization often starts from a pretrained generative model that captures a broad prior over valid molecular structures.

By Trevor Chen, Ariel Dai, Jason Yang, Riccardo De Santi, Daniel Khalil, Wenda Chu, Nate Gruver, Pranav Murugan, Alexander F. G. Goldberg, Maruan Al-Shedivat, Yisong Yue

diffusion fine-tuning

arXiv Machine Learning

Jul 22

Adopting Reinforcement Learning with Verifiable Rewards for Molecular Generation

arXiv:2607. 19044v1 Announce Type: new Abstract: Leveraging large language models (LLMs) for molecular generation has shown remarkable potential in chemical and drug design.

By Mingxuan Ouyang, Hao Lan, Wanyu Lin

llms reinforcement-learning fine-tuning benchmarks

arXiv Machine Learning

Sep 7

Small Molecule Optimization with Large Language Models

The paper introduces Mol-E, an evolutionary algorithm that leverages large language models trained on molecular data to generate candidate molecules. Mol-E achieves state‑of‑the‑art performance on the Practical Molecular Optimization benchmark, scoring 17.500 in the task‑agnostic regime and 20.551 in the task‑informed regime. It also outperforms baseline methods in multi‑property optimization tasks involving docking against DRD2, MK2, and AChE.

By Philipp Guevorguian, Menua Bedrosian, Tigran Fahradyan, Gayane Chilingaryan, Armen Aghajanyan, Hrant Khachatrian

llms benchmarks

arXiv Computation and Language

Aug 25

Closed-Loop Bayesian Molecular Inverse Design with Semantic LLM Surrogates

arXiv:2608.22967v1 Announce Type: new Abstract: Practical molecular inverse design is rarely a one-shot generation problem; it often takes the form of closed-loop candidate-pool enrichment, where und...

By Yaoyao Xu, Xinjian Zhao, Xiaozhuang Song, Lei Bai, Tianshu Yu

llms rag

One email a morning, machine-written

Related stories

My Chemical Harness: Evolutionary Molecular Design over Synthetic Pathways with Large Language Model Agents

Evolution Fine-Tuning: Learning to Discover Across 371 Optimization Tasks

On the Design Space of Discrete Diffusion Online Adaptation for Molecular Optimization

Adopting Reinforcement Learning with Verifiable Rewards for Molecular Generation

Small Molecule Optimization with Large Language Models

Closed-Loop Bayesian Molecular Inverse Design with Semantic LLM Surrogates