From Benchmark to Bench: Can Agents Survive Real-World Drug Discovery?
cs.AI
Submitted: 2026-10-05
Updated: 2026-10-09
Terminology
Sources
- Accelerating scientific discovery with Co-Scientist
- DrugAgent: Automating AI-aided Drug Discovery Programming through LLM Multi-Agent Collaboration
- CheMatAgent: Enhancing LLMs for Chemistry and Materials Science through Tree-Search Based Tool Learning
- Mozi: Governed Autonomy for Drug Discovery LLM Agents
- DrugPilot: LLM-based Parameterized Reasoning Agent for Drug Discovery
- Pushing the boundaries of Structure-Based Drug Design through Collaboration with Large Language Models
- Large Language Model Agent for Modular Task Execution in Drug Discovery
- DrugR: Optimizing Molecular Drugs through LLM-based Explicit Reasoning
- Molecular Lead Optimization via Agentic Tool Planning
- MT-Mol:Multi Agent System with Tool-based Reasoning for Molecular Optimization
- FROGENT: An End-to-End Full-process Drug Design Multi-Agent System
- Beyond SMILES: Evaluating Agentic Systems for Drug Discovery
- Alice in Wonderland: Simple Tasks Showing Complete Reasoning Breakdown in State-Of-the-Art Large Language Models
- Easy Problems That LLMs Get Wrong
- Deep Learning Foundation Models from Classical Molecular Descriptors
Related papers
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- Agents' Last Exam
- The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
- MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
- Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems