SciBench
PulseAugur coverage of SciBench — every cluster mentioning SciBench across labs, papers, and developer communities, ranked by signal.
1 day(s) with sentiment data
-
LLMs Learn to Read and Write Neural Network Weights Directly
Researchers are exploring "Weight-Space Programming" (WSP), a novel technique where Large Language Models (LLMs) can directly read, diagnose, and modify the raw numerical weights of neural networks. This approach bypass…
-
Roles in multi-agent LLM systems impact feedback and recovery
A new research paper explores how roles within multi-agent large language model (LLM) systems influence feedback and recovery processes. The study found that while roles don't necessarily decrease initial accuracy, they…
-
New Large Knowledge Model aims to organize scientific literature for AI agents
Researchers have introduced the Large Knowledge Model (LKM), a novel knowledge foundation designed to support agentic science at scale. LKM organizes scientific literature into reasoning graphs, where claims are nodes l…