Forging More Tasks into Better Harnesses: Agentic Harness Evolution via Successive Scale Racing
Agentic harness evolution optimizes an agent's instructions, tools, and control flow by using its task execution experiences as evolving evidence. While more evolution tasks should intuitively improve performance, our preliminary study reveals a paradoxical failure mode: the performance of existing…
By Jingzhe Liu, Jiliang Tang, Tong Zhao, Neil Shah, Clark Mingxuan JuarXiv - cs.AI
Read the full story
Originally published by arXiv - cs.AI on Oct 22, 2026.
Comments
Sign in to join the discussion.