Search papers, labs, and topics across Lattice.
Medical AI Scientist leapfrogs generic LLMs in clinical research, generating higher-quality, evidence-backed hypotheses and manuscripts that rival top-tier medical publications.
Generative multi-agent systems spontaneously exhibit collusion and conformity, mirroring societal pathologies, even without explicit programming and bypassing individual agent safeguards.
LLM agents can slash task completion time by almost 50% simply by predicting and pre-executing likely tool calls.
AI-generated code's fluency masks a critical flaw: it often fails to deliver what users actually intend, highlighting the urgent need for "intent formalization" to bridge the gap between informal requirements and precise program behavior.
Forget direct prompt editing: this agentic planning framework, powered by offline RL and synthetic data, masters complex image styling by breaking it down into interpretable tool sequences.
Automating software repository build and testing across languages and platforms is now possible, unlocking scalable benchmarking and training for coding agents.
A 4B parameter SLM can now rival frontier agent performance in complex tool-use environments, thanks to a novel reinforcement finetuning framework that teaches it how to strategically acquire context and execute actions.
LLM agents can now proactively protect user privacy with a new reinforcement learning approach that outperforms static defenses by 14% while maintaining helpfulness.
Agentic LLMs can be taught to refuse harmful actions with up to 50% greater success, even zero-shot across diverse models and tasks, by explicitly learning when *not* to act.
Forget same-family constraints: you can compress prompts for LLaMA with a Qwen draft model and still get 90-100% of the original performance.
LLM agents can learn to explore novel states and generalize to new tasks with a hybrid on- and off-policy RL framework that leverages memory.
GUI agents can achieve significantly stronger task-solving capabilities through carefully designed post-training and data curation, without relying on costly online data collection.
AgentOS reimagines LLMs as reasoning kernels within a structured OS, offering a blueprint for more robust and scalable AI agents.
Forget slow, reactive GUI agents – ActionEngine uses a state-machine memory to plan actions programmatically, slashing costs by 11.8x and doubling speed while boosting task success to 95%.
Imagine a world where web agents don't just click and type, but orchestrate complex tasks with the reliability of APIs – Web Verbs offer a path to that future.
World models can now effectively simulate complex desktop software environments like Microsoft Office, enabling agents to reason about actions before execution and significantly improving performance.
Guaranteeing consistent communication between AI agents is now possible: a new certification protocol slashes disagreement by up to 96% by ensuring agents share a common understanding of terms.
Forget static, homogeneous multi-agent systems: Team-of-Thoughts unlocks superior performance by dynamically orchestrating heterogeneous agents based on calibrated coordination and self-assessed domain expertise.
Enterprise AI assistants can achieve zero data retention, but the architectural and compliance paths taken by Salesforce and Microsoft reveal significant trade-offs.
Even the best LLMs fail more than 40% of the time when orchestrating multiple tools in realistic scenarios, revealing critical gaps in real-world agent capabilities.
LLMs can now automate structured reporting from nurse dictations and medical order extraction from doctor-patient consultations, thanks to two new open-source datasets and an agentic pipeline for generating realistic training data.
An LLM-powered smart tutor isn't just another homework helper; it's a real-time feedback loop for instructors, revealing student struggles and enabling more effective teaching.
LLMs and VLLMs can team up to generate synthetic image data so good, it beats state-of-the-art methods and boosts performance on rare classes and open-vocabulary object detection.
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.
Forget task-specific models: Magma, a single foundation model, now outperforms them in both UI navigation and robotic manipulation by bridging verbal and action abilities.
