Search papers, labs, and topics across Lattice.
5
20
7
16
Static environments can be transformed on-the-fly to better suit agent learning, resulting in up to a 9.0-point performance boost with fewer execution steps.
FinanceHarness not only automates financial deep research but also reveals that even advanced LLMs struggle with specialized financial tasks, scoring below 40% on rigorous benchmarks.
PI-Hunter uncovers hidden prompt injection vulnerabilities in LLM agents that traditional defenses miss, revealing a critical gap in current security practices.
Forget slow, white-box optimization: VQQA uses a multi-agent system to ask questions about generated videos, using the answers as semantic gradients to drastically improve video quality via black-box prompt refinement.
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.
