SOURCE-LINKED INTELLIGENCE

CordisBench: Can Language Models Reason About Component Lifecycles in Dynamic Agent Harnesses?

arXiv · AI, language, vision and robotics · article · Sep 1, 2026 · UTC

Dynamic agent harnesses let language models change the software that shapes their own execution. This flexibility brings a new reasoning burden: a local plugin change can propagate through dependencies and cleanup. We introduce CordisBench, a 1,200-question benchmark of this lifecycle reasoning. It combines a controlled formal setting with programs executed against Cordis, a runtime that manages component dependencies and cleanup, and asks models to identify affected components, predict state after a specified teardown order, determine which conditions hold under all or some orders, and choose

Read original source ↗ Open in workspace

recordType

paper

region

Global