Research map / Multi-agent systems and games / Cooperative multi-agent RL
Expert-Inspired Multi-Agent Coordination for Multi-Objective Molecular Optimization
Daojian Zeng, Tianle Li, Jiahao Yang, Jiacai Yi, Xieping Gao, Lincheng Jiang, Tengfei Ma, Xiangxiang Zeng
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add central scheduling agent versus fixed sequential optimization chains (ablation) | MAMO · GSK3β+JNK3+QED+SA | HV: 0.501/0.510 -> 0.671 | Improved |
| add inter-agent collaboration (shared memory and scheduling) (ablation) | MAMO · GSK3β+JNK3+QED+SA | HV: 0.530 -> 0.671 | Improved |
| add inter-agent collaboration (ablation) | MAMO · GSK3β+JNK3+QED | HV: 0.580 -> 0.762 | Improved |
| use central scheduling instead of a well-ordered chain GSK3β-JNK3-QED (ablation) | MAMO · GSK3β+JNK3+QED | HV: 0.760 -> 0.762 | No clear effect |
| change fixed chain order to QED-JNK3-GSK3β (ablation) | sequential variant · GSK3β+JNK3+QED | HV: 0.760 -> 0.572 | Hurt |
| use multi-agent MAMO instead of single-agent GPT-4o mini | GPT-4o mini · Six multi-objective tasks | HV sum: 3.707 -> 4.510 | Improved |
| use MAMO instead of EAG (pipeline multi-agent) | multi-agent LLM · Six multi-objective tasks | HV sum: 3.979 -> 4.510 | Improved |
| use MAMO instead of Graph GA on QED+SA | multi-objective optimization · QED+SA | HV: 0.934 -> 0.928 | Hurt |
| use MAMO instead of REINVENT Trans on SA | QED+SA task · QED+SA | Avg SA: 0.854 -> 0.813 | Hurt |
Closest papers by meaning
- Multi-Objective Molecular Design Through Learning Latent Pareto Set (AAAI 2025 · similarity 0.88)
- MACS: Multi-Agent Reinforcement Learning for Optimization of Crystal Structures (NeurIPS 2025 · similarity 0.86)
- MAC-AMP: A Closed-Loop Multi-Agent Collaboration System for Multi-Objective Antimicrobial Peptide Design (ICLR 2026 · similarity 0.85)
- Enhancing Ligand Validity and Affinity in Structure-Based Drug Design with Multi-Reward Optimization (ICML 2025 · similarity 0.85)
- Protein Design with Agent Rosetta: A Case Study for Specialized Scientific Agents (ICML 2026 · similarity 0.85)
- Probe Before You Edit: Probing-Guided Molecular Optimization for LLM Agents in Structure-Based Drug Design (NeurIPS 2026 · similarity 0.85)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
