MARCO: Multi-Round Agentic Reinforcement for Conditional Molecular Optimization
cs.LG, cs.CL
Submitted: 2026-09-29
Updated: 2026-09-29
Code: https://github.com/euReKa025/MARCO-release
Terminology
Sources
- DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
- Mistral 7B
- Speak-to-Structure: Evaluating LLMs in Open-domain Natural Language-Driven Molecule Generation
- Reference-guided Policy Optimization for Molecular Optimization via LLM Reasoning
- Qwen2.5 Technical Report
- Proximal Policy Optimization Algorithms
- DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
- RAGEN: Understanding Self-Evolution in LLM Agents via Multi-Turn Reinforcement Learning
- Qwen3 Technical Report
- MolAct: An Agentic RL Framework for Molecular Editing and Property Optimization
- ArCHer: Training Language Model Agents via Hierarchical Multi-Turn RL
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