CHART: A Harness-Rotation Curriculum for Harness-Robust Search Agents
Quick summary
arXiv:2609.22247v1 Announce Type: cross Abstract: 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 traini
Key takeaways
- arXiv:2609.22247v1 Announce Type: cross Abstract: 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.
Why it matters
This development shows AI moving deeper into everyday software. Productivity potential should be weighed against price, data permissions, exportability and the preservation of human control.
Member comments