Search papers, labs, and topics across Lattice.
Affiliation:
3
0
6
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.
Context-Calibrated DPO can cut object hallucination in MLLMs by 36% while maintaining reasoning performance, revealing a critical gap in how existing methods leverage context.
Leading LLMs falter in Korean web-browsing tasks, achieving less than half the accuracy found in previous benchmarks.
