MolHop: Scaffold-Hopping Molecular Design with Agentic Reinforcement Learning

arXiv:2610.19920 · cs.LG, cs.CL · Submitted 2026-10-14 · Read on arXiv

cs.LG, cs.CL

Submitted: 2026-10-14

Updated: 2026-10-14

Comments: Under review at ICLR 2027

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Reinforcement Learning — 1× in this paper · explained in 4 episodes

Sources

• Gemma 4 Technical Report
• Phi-4 Technical Report
• Agentic reinforcement learning empowers next-generation chemical language models for molecular design and synthesis
• LLM-Guided Dynamic Action Spaces for Synthesizable Molecular Optimization
• The Llama 3 Herd of Models
• DeepSeek-V4.1-Flash: Pushing the Limits of KV Cache Compression
• MolAct: An Agentic RL Framework for Molecular Editing and Property Optimization
• ChemLLM: A Chemical Large Language Model
• ChemDFM-R: A Chemical Reasoning LLM Enhanced with Atomized Chemical Knowledge
• ToolMol: Evolutionary Agentic Framework for Multi-objective Drug Discovery

Related papers

• Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
• AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
• Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
• Convergence issues in Relational Concept Analysis based on AOC-posets
• Beliefs Beyond Posteriors: The Predictive Cost of ELBO Binding
• Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks