Search papers, labs, and topics across Lattice.
5
0
8
2
Muon can boost agentic RL performance by up to 88% compared to AdamW, challenging assumptions about optimizer efficacy in sparse-reward settings.
Trustworthy medical agents could evolve autonomously through interactive learning, rather than relying solely on parameter scaling.
SearchEyes achieves state-of-the-art performance in multimodal search by unifying training data, environments, and rewards into a cohesive simulated world.
Early detection of failure in LLM agents can save over 47% of inference compute by leveraging internal representations rather than observable behavior.
Current MLLM benchmarks are missing the forest for the trees: Agentic-MME reveals that strong final-answer accuracy masks surprisingly poor tool use and planning in complex multimodal tasks.
