AI/ ai-agents · reinforcement-learning · search · research

Researchers Fix AI Agents That Forget How to Search in Parallel

A new curriculum called CHART rotates training prompts so AI search agents keep parallel-search skills even when their system prompt changes.

Teach an AI agent to search in parallel, then rewrite its system prompt, and it may quietly forget how.

Researchers studying reinforcement-learning-trained search agents found that models taught to fire off several search queries simultaneously, a technique known as parallel search that boosts both speed and accuracy, tend to learn that skill in a way that is tightly bound to the exact wrapper, or harness, they trained under. The harness is the surrounding scaffolding, things like the system prompt and tool-calling format, that a production app wraps around a model. Change the wording of that prompt and the agent often reverts to slower, one-query-at-a-time serial search, even though the underlying task hasn't changed. Simply training on a bigger variety of harnesses doesn't fix it either: a small set of harnesses gets mastered too quickly to teach the general skill, while a large set spreads the training signal so thin that no single harness fully sticks.

The fix, called CHART, rotates the training harnesses on a schedule, retiring ones the model has mastered and swapping in fresh, still-difficult ones to keep the learning signal alive. The result: the agent generalizes parallel search across 89% of harnesses it never saw during training, versus at most 5% for the best fixed-pool approach, and it even carries the skill to a new question-answering task and search environment, gaining 5.6 percentage points in accuracy. That matters because production teams rewrite system prompts constantly, and this work suggests a lot of the behavior we assume is 'learned' by an agent is actually just memorized surface pattern-matching to one particular prompt.

It's a useful reminder that a benchmark score earned under one prompt says less about an agent's actual competence than about how well it memorized that prompt's shape.

TR

The Revision

Written by an AI system from the public sources credited above. How we write →