AI Paper Atlas

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

CocoRNA: Collective RNA Design with Cooperative Multi-agent Reinforcement Learning

Tianmeng Hu, Biao Luo, Ke Li

ICML 2026 · Multi-agent systems and games › Cooperative multi-agent RL · approach: MARL benchmarks and grouping

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 multi-agent decomposition (4 agents) instead of a single agent (ablation)CocoRNA · Rfam RNA inverse design (650 test structures)success rate (%): 52.43 -> 97.75Improved
Add search-augmented exploration (SAE) (ablation)CocoRNA · Rfam RNA inverse design (650 test structures)success rate (%): 92.25 -> 97.75Improved
Add SAE under terminal-only reward (ablation)CocoRNA · Rfam, terminal rewardsuccess rate (%): 87.69 -> 92.92Improved
Add SAE under delayed reward (ablation)CocoRNA · Rfam, delayed rewardsuccess rate (%): 95.54 -> 97.54Improved
Use position-based instead of random decomposition (ablation)CocoRNA · Rfam, six splitssuccess rate (%): 91.74 -> 97.44Improved
Use position-based instead of structure-type decomposition (ablation)CocoRNA · Rfam, six splitssuccess rate (%): 96.69 -> 97.44No clear effect
Increase agents from 2 to 4 (ablation)CocoRNA · Rfam RNA inverse design (650 test structures)success rate (%): 92.46 -> 97.85Improved
Increase agents from 4 to 8 (ablation)CocoRNA · Rfam RNA inverse design (650 test structures)success rate (%): 97.85 -> 94.62Hurt
Share policy parameters across agents (ablation)CocoRNA-PBD · Rfam RNA inverse design (650 test structures)success rate (%): 97.85 -> 95.69Hurt
Use terminal-only reward instead of per-step reward (ablation)CocoRNA · Rfam RNA inverse design (650 test structures)success rate (%): 97.75 -> 92.92Hurt
Use delayed reward every 10 steps instead of every step (ablation)CocoRNA · Rfam RNA inverse design (650 test structures)success rate (%): 97.75 -> 97.54No clear effect
Use CocoRNA instead of single-agent on TF Bind 10 and ChEMBL (ablation)CocoRNA · DesignBench TF Bind 10 / ChEMBLscore: 0.725 -> 1.000; 0.595 -> 0.811Improved

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