AI4Science
PulseAugur coverage of AI4Science — every cluster mentioning AI4Science across labs, papers, and developer communities, ranked by signal.
2 day(s) with sentiment data
-
New multi-agent system DDIAgents enhances drug-drug interaction prediction
Researchers have developed DDIAgents, a novel multi-agent framework designed to improve the prediction of drug-drug interactions (DDIs). This system dynamically orchestrates biomedical knowledge by using a planner agent…
-
New SciRisk-Bench benchmark evaluates AI safety in science
Researchers have introduced SciRisk-Bench, a new benchmark designed to assess the safety of AI models used in scientific applications (AI4Science). This benchmark evaluates models on their ability to recognize and avoid…
-
New benchmark PolyBench enhances LLMs for polymer design
Researchers have developed PolyBench, a comprehensive benchmark dataset and training methodology for large language models (LLMs) focused on polymer design tasks. This dataset, comprising over 125,000 tasks and leveragi…
-
New benchmark SciPaths tests AI's ability to forecast scientific discovery pathways
Researchers have introduced SciPaths, a new benchmark designed to forecast the pathways to scientific discovery by identifying enabling contributions and their dependencies on prior work. Unlike existing benchmarks that…