# From Benchmark to Bench: Can Agents Survive Real-World Drug Discovery?

arXiv: https://arxiv.org/abs/2610.06411 · HTML: https://mlsanity.com/paper/2610.06411/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Medical and scientific domain agents, one of 16 directions in LLM agents and tool use.
- Builds on 13 of its 63 references that are in the map.
- First posted on arXiv 5 Oct 2026.

## Placed in

- LLM agents and tool use / [Medical and scientific domain agents](https://mlsanity.com/agents/medical-and-scientific-domain-agents/)

## Builds on (most cited first, 13 of 13)

- [Accelerating scientific discovery with Co-Scientist](https://mlsanity.com/paper/2502.18864/) (2025)
- [Alice in Wonderland: Simple Tasks Showing Complete Reasoning Breakdown in State-Of-the-Art Large Language Models](https://mlsanity.com/paper/2406.02061/) (2024)
- [DrugAgent: Automating AI-aided Drug Discovery Programming through LLM Multi-Agent Collaboration](https://mlsanity.com/paper/2411.15692/) (2024)
- [Easy Problems That LLMs Get Wrong](https://mlsanity.com/paper/2405.19616/) (2024)
- [DrugPilot: LLM-based Parameterized Reasoning Agent for Drug Discovery](https://mlsanity.com/paper/2505.13940/) (2025)
- [MT-Mol:Multi Agent System with Tool-based Reasoning for Molecular Optimization](https://mlsanity.com/paper/2505.20820/) (2025)
- [CheMatAgent: Enhancing LLMs for Chemistry and Materials Science through Tree-Search Based Tool Learning](https://mlsanity.com/paper/2506.07551/) (2025)
- [Deep Learning Foundation Models from Classical Molecular Descriptors](https://mlsanity.com/paper/2506.15792/) (2025)
- [Large Language Model Agent for Modular Task Execution in Drug Discovery](https://mlsanity.com/paper/2507.02925/) (2025)
- [Mozi: Governed Autonomy for Drug Discovery LLM Agents](https://mlsanity.com/paper/2603.03655/) (2026)
- [FROGENT: An End-to-End Full-process Drug Design Multi-Agent System](https://mlsanity.com/paper/2508.10760/) (2025)
- [DrugR: Optimizing Molecular Drugs through LLM-based Explicit Reasoning](https://mlsanity.com/paper/2602.08213/) (2026)
- [Molecular Lead Optimization via Agentic Tool Planning](https://mlsanity.com/paper/2605.28862/) (2026)

## Abstract (arXiv)

Agentic systems increasingly coordinate molecular-design tools, but it is unclear which layer of the stack limits outcomes on real projects. We developed MAGI, an open modular agent that authors objectives, launches and monitors optimization, interprets structure--activity relationships, and revises its strategy accordingly. MAGI generates molecules either directly through the LLM or by delegating to REINVENT 4, with scoring services interchangeable behind a common contract. We tested it across nine retrospective lead-optimization campaigns from three pharmaceutical companies, replayed under fixed temporal cutoffs. Both routes produced valid structures: LLM proposals stayed closer to local chemistry and reached comparable or higher primary activity in fewer operations, whereas REINVENT explored broader chemical space. Whether a campaign met its objective depended on the predictive models, not on the generation route: attainment followed model accuracy on the chemistry proposed, dropping once that chemistry moved outside the model's applicability domain. Separately, a blinded evaluation asked whether the MAGI's output could pass as expert work: chemists were not able to discriminate agentic proposals from held-out compounds, and judged the SAR reasoning broadly plausible yet incomplete. Together, these results position MAGI as a coordination layer pluggable into existing computational chemistry workflows. The ceiling on real projects, however, remains currently set by scorer applicability rather than by tool orchestration.