M3OS: A Monte Carlo Graph Search-Orchestrated Multi-Agent LLM System for Evidence-Traced Molecular Optimization
cs.LG, q-bio.BM
Submitted: 2026-09-28
Updated: 2026-09-28
Code: https://github.com/wwwangjunjie/M3OS
Terminology
Sources
- TAGMol: Target-Aware Gradient-guided Molecule Generation
- Empower Structure-Based Molecule Optimization with Gradient Guided Bayesian Flow Networks
- Voyager: An Open-Ended Embodied Agent with Large Language Models
- ChemLLM: A Chemical Large Language Model
- LlaSMol: Advancing Large Language Models for Chemistry with a Large-Scale, Comprehensive, High-Quality Instruction Tuning Dataset
- MolX: Enhancing Large Language Models for Molecular Understanding With A Multi-Modal Extension
- Efficient Evolutionary Search Over Chemical Space with Large Language Models
- PharmAgents: Building a Virtual Pharma with Large Language Model Agents
- DrugPilot: LLM-based Parameterized Reasoning Agent for Drug Discovery
- Monte-Carlo Graph Search for AlphaZero
- SMDD-Bench: Can LLMs Solve Real-World Small Molecule Drug Design Tasks?
- mCLM: A Modular Chemical Language Model that Generates Functional and Makeable Molecules
- MinerU: An Open-Source Solution for Precise Document Content Extraction
- De Novo Molecular Generation via Connection-aware Motif Mining
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: Local-Consistency Optimisation for Bayesian Neural Networks
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks