Search papers, labs, and topics across Lattice.
3
0
6
0
This work proposes DualSQL, a new Text-to-SQL system consisting of two agents powered by a single model backbone, enabling joint optimization through a robust multi-agent reinforcement learning (RL) framework, and introduces a new SQL correctness metric, robust execution match (REX), to more accurately judge SQL correctness and assign reward signals.
"Lost at the End" reveals a striking primacy bias in multimodal KB-VQA, where early context dramatically outperforms late context, challenging conventional evaluation metrics.
Open-source QUEST agents, trained solely on 8K synthetic tasks, rival or surpass proprietary research agents, proving that scaling data synthesis can unlock frontier performance.
