Skip to main content
Search

# Evidence-driven harness co-evolution

1 related articles

Subscribe to updates
  1. arXiv

    Agents stop waiting for external scores: Verify by Doing co-evolves execution and verification inside a single task

    Agents that improve themselves at test time usually need benchmark scores or reference answers to tell whether a task is done, and real tasks often lack that external feedback. Verify by Doing gives the executing agent and the verifying agent separate editable harnesses of instructions, skills and checklists, gathers completion evidence by actively inspecting artifacts and environment state, and uses those findings to update both execution and verification. Across AutomationBench, Banking and 133 GDPval tasks it posts the highest overall scores among compared methods without external feedback, and on a fixed candidate pool the evolved evaluator raises pass rate from 31.2% to 35.8%.

You’re all caught up