LiteEvo: Automated, Cost-Efficient Harness Evolution for Generalization to Unseen Tasks
An LLM agent is defined by two things: the weights inside its model and the harness of components assembled around it. Harnesses are still handcrafted, and HarnessX, which evolves them automatically, starts each benchmark from a handcrafted harness, reports gains on the tasks it evolved on, and budgets 100 to 175 milli...
Euntae Choi, Su-Min Song, Sungjoo Yoo
· 0 citations