Preprint
Aug 2026
Beyond Executable Models: The Pufibara Agent Harness and the Modelica Agent Workflow Benchmark for Physical System Modeling
Pufibara is presented, an agent harness that maintains persistent engineering state across revisions, associates execution and simulation evidence with the candidate that produced it, and makes submission an explicit agent action to evaluate end-to-end Modelica agent workflows.
Zizhe Wang
· 0 citations