Tag
Introduces Octopus, a neuro-symbolic architecture that combines LLM swarms with algorithmic physics engines for autonomous discovery of cancer vulnerabilities, identifying IGF2 as a biomarker for drug resistance.
CoLabScience introduces a proactive LLM assistant for biomedical research that autonomously intervenes in scientific discussions using PULI (Positive-Unlabeled Learning-to-Intervene), a novel reinforcement learning framework that determines when and how to contribute context-aware insights. The work includes BSDD, a new benchmark dataset of simulated research dialogues with intervention points derived from PubMed articles.