Search papers, labs, and topics across Lattice.
5
0
7
Evolving evaluation metrics can enhance LLM performance by up to 110% while maintaining transparency and robustness against manipulation.
A biased judge can silently disable skill retirement in self-evolving agents, leading to unnoticed performance degradation that can jeopardize deployment.
LLMs can teach themselves new tricks: a simple self-improvement loop, "Ratchet," lets a frozen LLM agent significantly boost its coding performance by autonomously managing its own library of natural-language skills.
End-to-end prompt optimization is often a waste of time and money, succeeding only when coaxing models into specific output formats they're already capable of.
Expert-written rules for coding agents are often useless or even harmful, with random constraints working just as well and negative constraints outperforming positive directives.
