Search papers, labs, and topics across Lattice.
Affiliation:
4
0
6
1
This work proposes MATCH, a closed-loop framework for model-aware tool learning with curriculum scheduling and hierarchically gated rewards, and shows consistent improvements across four backbones from two model families.
MERIT-Rank is proposed, a framework that models complementary reasoning trajectories to improve reranking robustness and develops Progressive Rank Policy Optimization (PRPO), a progressive training framework that stabilizes reasoning trajectories while continually improving ranking quality through staged optimization objectives.
MagicSelector achieves unprecedented tool retrieval accuracy by translating vague user instructions into precise subtasks, outperforming state-of-the-art methods.
Cross-device agents struggle significantly, with top performers only managing a 12.5% success rate in executing complex, multi-device tasks.
