{"ID":3050138,"CreatedAt":"2026-06-04T02:13:16.786527022Z","UpdatedAt":"2026-06-06T08:58:50.400332682Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2606.04661","arxiv_id":"2606.04661","title":"CRAFT: Cost-aware Refinement And Front-aware Tuning of Prompts","abstract":"Prompts tuned for accuracy often grow long, raising inference cost on every model call. The best accuracy-cost trade-off depends on the task and the budget, so prompt optimization is a search over the Pareto front of accuracy and prompt-token cost rather than for one prompt. The usual shortcut, collapsing the objectives into a weighted sum, fixes the trade-off weight before search and often recovers only a narrow region of the front, a failure we call scalarization collapse. We present CRAFT (Cost-aware Refinement And Front-aware Tuning), a Pareto-front prompt optimizer that treats target-LLM validation calls as the scarce resource and allocates them to candidates near the optimistic candidate front. Each round, complementary accuracy-oriented and cost-oriented generators propose edits, Pareto-gap acquisition spends the per-round validation budget, and NSGA-II retention keeps a spread-out population. Across six classification and reasoning benchmarks, CRAFT's retained fronts reach both high-accuracy and low-cost regions, while accuracy-only, cost-only, and weighted-sum baselines each concentrate in narrower regions. The accuracy-cost trade-off becomes a post-search choice, not a pre-search weight.","short_abstract":"Prompts tuned for accuracy often grow long, raising inference cost on every model call. The best accuracy-cost trade-off depends on the task and the budget, so prompt optimization is a search over the Pareto front of accuracy and prompt-token cost rather than for one prompt. The usual shortcut, collapsing the objective...","url_abs":"https://arxiv.org/abs/2606.04661","url_pdf":"https://arxiv.org/pdf/2606.04661v1","authors":"[\"Shanu Kumar\",\"Shubhanshu Khandelwal\",\"Akhila Yesantarao Venkata\",\"Parag Agrawal\",\"Yova Kementchedjhieva\",\"Manish Gupta\"]","published":"2026-06-03T09:40:03Z","proceeding":"cs.CL","tasks":"[\"cs.CL\",\"cs.LG\"]","methods":"[\"Large Language Model\"]","has_code":false}