Search papers, labs, and topics across Lattice.
7 papers from Allen Institute for AI (AI2) on Tool Use & Agents
Nemotron 3 Super proves you can achieve comparable accuracy to existing 120B models, but with significantly higher inference throughput, by combining Mamba, Attention, and Mixture-of-Experts.
Skip the annotation bottleneck: ScheMatiQ lets you turn research questions and text corpora into structured databases with LLMs, guided by a simple web interface.
Open-source web agents can now outperform GPT-4o on key web navigation tasks, thanks to a new dataset and model family that levels the playing field.
LLM agents can appear to reason well (high entropy) while completely ignoring the input, and mutual information is a far better metric for catching this failure.
Generative multi-agent systems spontaneously exhibit collusion and conformity, mirroring societal pathologies, even without explicit programming and bypassing individual agent safeguards.
AI is poised to automate the most joyful and agentic parts of our jobs, while developers are building AI with the wrong traits.
Forget simple keyword searches – scientists are using AI research tools as collaborative partners, delegating complex tasks and engaging with results in surprisingly persistent and non-linear ways.
