Search papers, labs, and topics across Lattice.
2
0
4
TACO reveals that agentic models can learn to optimize tool usage without external judges, achieving higher accuracy and efficiency in multimodal tasks.
Forget monolithic models: a lightweight RL policy can dynamically orchestrate ensembles of frozen experts to outperform GPT-5 and Gemini-2.5-Pro on multimodal tasks, even generalizing to unseen models and skills.
