SOURCE-LINKED INTELLIGENCE

Failure-Guided Co-Evolution of Prompts and Training Data

arXiv · AI, language, vision and robotics · article · Sep 14, 2026 · UTC

Automatic prompt optimization (APO) improves language-model programs by revising prompts from task feedback, yet it typically holds its training data fixed. Repeatedly optimizing against the same instances confines feedback to weaknesses already represented in those data, leaving related failure conditions unexplored. We therefore view each failure as a dual signal: it indicates both how the prompt should be revised and what new training evidence should be synthesized. We introduce FORGE, a failure-guided framework that co-evolves prompts and training data. FORGE abstracts imperfect executions

Read original source ↗ Open in workspace

recordType

paper

region

Global