Vestrum: Improving Agent Harnesses by Adapting Their Verification, Structure and Memory
An agent harness controls how a language model accesses information, uses tools, preserves memory, and checks its work. Improving this software is costly when each evaluation requires a long interaction with an environment. We introduce Vestrum, a framework that turns failures in execution traces into scoped harness ch...
Jayant Parashar, Eugene F. Douglass, William C. Bastian et al.
· 0 citations