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 multimodal, 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. In this benchmark, our competitor discovery agent (Bioptic 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 ~3 hours (~20x) for the competitive analysis.

Recently, the vehicle localization has become a major problem in the field of intelligent transportation systems (ITS). Modern vehicles support multiple systems for localization, such as Global Positioning System (GPS), Inertial Measurement Unit (IMU), lidar, and video feed. However, the problem of merging data from different sources for reducing errors remains challenging. This problem becomes increasingly hard if we use data with high uncertainty - for example, crowdsourced environmental features. Such data can provide invaluable information, especially when other data sources, such as GPS, are not available. Unfortunately, using it for vehicle localization requires great care, as crowdsourced data can be very noisy and imprecise. In this paper we present a Bayesian approach for sensor fusion, and use it to improve vehicle localization using crowdsourced data of traffic sign positions. We show that this method offers noticeable improvements (error reduction by 8.2%) compared to using GNSS and IMU only, and is comparable to the use of precise traffic signs positions - which are superior to crowdsourced positions, but very hard to obtain at scale.