LLM-Based Agents for Competitive Landscape Mapping in Drug Asset Due Diligence
Vlad Vinogradov (Optic Inc), Alisa Vinogradova (AI Expert), Dmitrii Radkevich (Optic Inc), Ilya Yasny (Optic Inc), Dmitry Kobyzev (Optic Inc), Ivan Izmailov (Optic Inc), Katsiaryna Yanchanka (Optic Inc), Roman Doronin (Optic Inc), Andrey Doronichev (Optic Inc)
Why It Matters
What makes this one worth your time
This research addresses a critical need in the biotech industry for efficient and accurate competitor analysis, potentially saving significant time and resources for investors.
A novel LLM-based agent significantly accelerates drug asset due diligence by mapping competitive landscapes.
Summary
The paper presents a competitor-discovery AI agent that utilizes LLMs to map the competitive landscape of drug assets for due diligence, achieving notable improvements in recall and analyst turnaround time.
Key contributions
- Development of a competitor-discovery AI agent tailored for drug asset due diligence.
- Introduction of a validation mechanism using LLMs to improve the accuracy of competitor identification.
- Creation of a structured evaluation corpus from unstructured data sources.
Notable insights
- The use of a competitor validating LLM-as-a-judge agent to filter false positives is a clever approach to enhance precision in drug name retrieval.
- Transforming unstructured diligence memos into a structured evaluation corpus showcases an innovative method for leveraging existing data.
Possible limitations
- Potential limitations in the generalizability of the results to other therapeutic areas or indications are not addressed in the abstract.
- The reliance on paywalled and fragmented data sources may limit accessibility and reproducibility.
Abstract
arXiv:2508.16571v4 Announce Type: replace Abstract: In this paper, we describe and benchmark a competitor-discovery component used within an agentic AI system for fast drug asset due diligence. A competitor-discovery AI agent, given an indication, retrieves all drugs comprising the competitive landscape of that indication and extracts canonical attributes for these drugs. The competitor definition is investor-specific, and data is paywalled/licensed, fragmented across registries, ontology-mismatched by indication, alias-heavy for drug names, multimodal, and rapidly changing. Although considered the best tool for this problem, the current LLM-based AI systems aren't capable of reliably retrieving all competing drug names, and there is no accepted public benchmark for this task. To address the lack of evaluation, we use LLM-based agents to transform five years of multi-modal, unstructured diligence memos from a private biotech VC fund into a structured evaluation corpus mapping indications to competitor drugs with normalized attributes. We also introduce a competitor validating LLM-as-a-judge agent that filters out false positives from the list of predicted competitors to maximize precision and suppress hallucinations. On this benchmark, our competitor-discovery agent achieves 83% recall, exceeding OpenAI Deep Research (65%) and Perplexity Labs (60%). The system is deployed in production with enterprise users; in a case study with a biotech VC investment fund, analyst turnaround time dropped from 2.5 days to $\sim$3 hours ($\sim$20x) for the competitive analysis.