AI Paper Atlas

Research map / Large language models / Agents, code and math

Steering Large Language Models through the DMTA Cycle: Structure-Based Drug Design via Knowledge-Driven Bi-Level Thompson Sampling

Xuanning Hu, Hao Tuo, Jinglong Ji, Anchen Li, Qianli Xing, Bo Yang

ICML 2026 · Large language models › Agents, code and math · approach: LLMs for scientific discovery

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 upper-level Bayesian seed selection (ablation)K-BTS-rand · CrossDocked2020 (first 10 targets, K-BTS-rand ablation)Top-1 avg Vina docking score: -8.95 -> -9.83Improved
add upper-level Bayesian seed selection (ablation)K-BTS-rand · CrossDocked2020 (first 10 targets, K-BTS-rand ablation)Top-20 avg Vina docking score: -7.79 -> -9.14Improved
add lower-level Thompson sampling of actions (ablation)K-BTS-rand · CrossDocked2020 (first 10 targets, K-BTS-rand ablation)Top-1 avg Vina docking score: -9.61 -> -9.83Improved
add knowledge base of chemical actions (ablation)K-BTS-rand · CrossDocked2020 (first 10 targets, K-BTS-rand ablation)Top-1 avg Vina docking score: -9.54 -> -9.83Improved
add warm-start of knowledge base from initial molecules (ablation)K-BTS-rand · CrossDocked2020 (first 10 targets, K-BTS-rand ablation)Top-1 avg Vina docking score: -9.74 -> -9.83Improved
retrieved knowledge actions applied stochastically instead of free LLM exploration (ablation)K-BTS-rand · CrossDocked2020 (first 10 targets, K-BTS-rand ablation)Top-1 avg Vina docking score: -9.54 -> -9.61Improved
full K-BTS convergence reduces diversity (ablation)K-BTS-rand · CrossDocked2020 (first 10 targets, K-BTS-rand ablation)internal diversity avg: 0.78 -> 0.50Hurt
replace ELILLM with K-BTS iterative refinement from diffusion starting pointsK-BTS-diff · CrossDocked2020 test (100 targets)Top-1 avg Vina docking score: -9.80 -> -10.23Improved
start from random training-set ligands instead of diffusion-generated moleculesK-BTS · CrossDocked2020 test (100 targets)Top-1 avg Vina docking score: -10.23 -> -9.60Hurt
use K-BTS retrieved action heuristics vs ELILLMK-BTS-rand · CrossDocked2020 test (100 targets)SA avg: 0.63 -> 0.75Improved

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