Search papers, labs, and topics across Lattice.
4
0
5
Up to 47% of reported fine-tuning gains in tool retrieval are an evaluation illusion caused by benchmarks treating functionally equivalent tools as retrieval failures.
ATLAS reveals that understanding both immediate request trajectories and long-term user interactions can dramatically enhance the performance of industrial tool-use agents.
CoKL enables LLMs to learn new tasks without sacrificing previously acquired capabilities, striking a balance that traditional methods fail to achieve.
UniMem achieves a remarkable 4.0 EM point improvement in task execution fidelity by seamlessly integrating episodic and parametric memory without the need for explicit task labels.
