AI Paper Atlas

Research map / Multi-agent systems and games / Cooperative multi-agent RL

Advancing Protein Design via Multi-Agent Reinforcement Learning with Pareto-Based Collaborative Optimization

Mingming Zhu, Jiahua Rao, Xiaoyu Chen, Qianmu Yuan, Yuedong Yang

AAAI 2026 · Multi-agent systems and games › Cooperative multi-agent RL · approach: MARL benchmarks and grouping · 2 citations (OpenAlex)

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 changedWhereMeasuredEffect
add consensus-weighted negotiation on top of multi-agent DPO (ablation)MAProt · Megascalesuccess rate (%): 82.9 -> 89.7Improved
add consensus-weighted negotiation on top of multi-agent DPO (ablation)MAProt · Megascalemedian scRMSD: 1.012 -> 0.890Improved
add consensus negotiation to multi-agent DPO (ablation)MAProt · Megascalemedian Pred-ddG: 2.143 -> 1.603Hurt
use multiple agents instead of ProteinMPNN alone (DPO) (ablation)ProteinMPNN · Megascalesuccess rate (%): 79.1 -> 82.9Improved
use multiple agents instead of ProteinMPNN alone (SFT) (ablation)ProteinMPNN · Megascalesuccess rate (%): 66.7 -> 69.8Improved
add SaProt agent to ProteinMPNN under DPO (ablation)ProteinMPNN · Megascalesuccess rate (%): 79.1 -> 84.1Improved
add all three agents rather than ProteinMPNN+SaProt under DPO (ablation)MAProt (DPO) · Megascalesuccess rate (%): 84.1 -> 82.9Hurt
multi-agent zero-shot vs ProteinMPNN zero-shot (ablation)MAProt · Megascalesuccess rate (%): 31.5 -> 54.4Improved
DPO fine-tuning vs SFT for ProteinMPNN (ablation)ProteinMPNN · Megascalesuccess rate (%): 66.7 -> 79.1Improved
lower beta to 0.1 vs 0.5 (ablation)MAProt · Megascalestructural deviationHurt
raise beta to 1.0 vs 0.5 (ablation)MAProt · Megascalefitness / success rateHurt
add consensus negotiation to multi-agent DPO (ablation)MAProt · AffinityDesignsuccess (%): 22.3 -> 32.1Improved

Closest papers by meaning

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy