LLM-Based Agents for Competitive Landscape Mapping in Drug Asset Due Diligence
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866913100036308992 |
|---|---|
| author | Vinogradov, Vlad Vinogradova, Alisa Radkevich, Dmitrii Yasny, Ilya Kobyzev, Dmitry Izmailov, Ivan Yanchanka, Katsiaryna Doronin, Roman Doronichev, Andrey |
| author_facet | Vinogradov, Vlad Vinogradova, Alisa Radkevich, Dmitrii Yasny, Ilya Kobyzev, Dmitry Izmailov, Ivan Yanchanka, Katsiaryna Doronin, Roman Doronichev, Andrey |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2508_16571 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | LLM-Based Agents for Competitive Landscape Mapping in Drug Asset Due Diligence Vinogradov, Vlad Vinogradova, Alisa Radkevich, Dmitrii Yasny, Ilya Kobyzev, Dmitry Izmailov, Ivan Yanchanka, Katsiaryna Doronin, Roman Doronichev, Andrey Artificial Intelligence Information Retrieval Multiagent Systems 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. |
| title | LLM-Based Agents for Competitive Landscape Mapping in Drug Asset Due Diligence |
| topic | Artificial Intelligence Information Retrieval Multiagent Systems |
| url | https://arxiv.org/abs/2508.16571 |