EvolveNet: Collaborative Harness Evolution for Agent Self-Improvement

By Jun Nie · Paper · cs.LG

The capabilities of an LLM agent depend not only on its model but on the harness: the executable program that constructs context, invokes tools, verifies results, and recovers from failure. Recent work shows that evolving the harness yields persistent improvements without updatin

Cs.lg

View original

HomeResourceLoading…