SOURCE-LINKED INTELLIGENCE

CHART: A Harness-Rotation Curriculum for Harness-Robust Search Agents

arXiv · AI, language, vision and robotics · article · Sep 5, 2026 · UTC

Search agents are usually trained under a single harness. But once an agent is deployed in a real application, its harness is frequently updated (e.g., a rewritten system prompt) to fit production needs. This exposes a fragility of post-trained agents: because a learned behavior is entangled with its training harness, even a harness update that leaves the task unchanged can fail to elicit the behavior. We train a search agent to perform parallel search, a popular strategy for improving both search efficiency and performance. We find that training under a fixed harness makes the behavior harnes

Read original source ↗ Open in workspace

recordType

paper

region

Global