Search papers, labs, and topics across Lattice.
Affiliation:
3
0
4
2
This work formalizes task-agnostic environment preprocessing, in which a studying system explores an environment under a budget and produces artifacts for a frozen solver, and compares unaided and archive-equipped meta-agents with fixed synthetic-practice and corpus-processing methods across six heterogeneous benchmarks.
Two AI systems with nearly identical performance can have drastically different human oversight needs, revealing hidden costs in deployment readiness.
Harness optimization reveals that LLMs can significantly enhance their performance, but surprisingly, native harnesses aren't always the best choice for optimization.
