Search papers, labs, and topics across Lattice.
LLM-powered diagnostic AI is ready for prime time: a real-world clinical trial shows it's safe, patients love it, and doctors find it useful.
An AI agent cracked an open problem in theoretical physics, deriving exact analytical solutions for gravitational radiation from cosmic strings, proving AI can do more than just pattern recognition.
Multimodal web agents are surprisingly vulnerable to cross-modal attacks, but a novel adversarial training approach can double task completion efficiency while mitigating these risks.
LLMs are becoming "epistemic agents" that shape our knowledge environment, so we need a new framework for evaluating and governing them based on trustworthiness, not just performance.
Gemini 3 Deep Think can now autonomously solve a majority of problems in a challenging math competition, signaling a leap in AI's mathematical reasoning capabilities.
Sequence models can learn to cooperate in multi-agent settings simply by training against diverse partners, no explicit meta-learning required.
Forget prompt engineering: PCAS deterministically enforces complex authorization policies in multi-agent systems, boosting compliance from 48% to 93% without restructuring existing agents.
Coding agents are vulnerable to a new class of stealthy, automated prompt injection attacks via poisoned skills, achieving high success rates even in realistic software engineering tasks.
GPT-5's scientific reasoning skills plummet by nearly 50% when tackling multi-step workflows, revealing a critical gap in current LLM agents' ability to orchestrate complex tool use.
Forget "smart plagiarism" – multi-stage LLM workflows like recursive decomposition and long-context pipelines can actually generate novel research plans, outperforming simpler reflection-based methods.
Forget hand-annotated data: Magnet distills multi-turn tool-use skills into LLMs by automatically generating training trajectories that outperform even Gemini 1.5 Pro.
