Search papers, labs, and topics across Lattice.
Affiliation:
3
0
6
9
AgentGrad is proposed, a prompt optimization framework for multi-agent systems based on sequential intervention and semantic textual gradient abstraction that clusters semantically similar gradients to prevent mixing unrelated failure modes, and abstracts each cluster into a generalized gradient that captures the shared corrective pattern.
WearableQA, a benchmark comprising 4,084 10-option multiple-choice questions constructed from the wearable time series, blood biomarkers, and demographics of 200 real users, provides a realistic and diagnostic benchmark for evaluating LLM reasoning over real-world wearable data.
Idiolectal paraphrasing transforms how models learn reasoning by allowing them to express complex thoughts in their own unique language, leading to significant performance gains.
