paper-with-me

홈 › Papers

CRAFT: Cost-aware Refinement And Front-aware Tuning of Prompts

2026-06-03 · Shanu Kumar, Shubhanshu Khandelwal, Akhila Yesantarao Venkata, Parag Agrawal, Yova Kementchedjhieva, Manish Gupta arxiv

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.

📄 PDF Abstract BibTeX arXiv:2606.04661

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

NavCrafter: Exploring 3D Scenes from a Single Image

2026-04-03 · Hongbo Duan, Peiyu Zhuang, Yi Liu, Zhengyang Zhang 외 arxiv

Creating flexible 3D scenes from a single image is vital when direct 3D data acquisition is costly or impractical. We introduce NavCrafter, a novel framework that explores 3D scenes from a single image by synthesizing no…

3D Reconstruction

A Communication-Theoretic Framework for LLM Agents: Cost-Aware Adaptive Reliability

2026-05-09 · Hamed Omidvar, Vahideh Akhlaghi arxiv

Agents built on large language models (LLMs) rely on a range of reliability techniques, including retry, majority voting, and self-consistency, that have been developed in parallel rather than within a common analytical …

DA-Flow: Degradation-Aware Optical Flow Estimation with Diffusion Models

2026-03-24 · Jaewon Min, Jaeeun Lee, Yeji Choi, Paul Hyunbin Cho 외 arxiv

Optical flow models trained on high-quality data often degrade severely when confronted with real-world corruptions such as blur, noise, and compression artifacts. To overcome this limitation, we formulate Degradation-Aw…

Optical Flow EstimationImage Restoration

BAGEN: Are LLM Agents Budget-Aware?

2026-05-29 · Yuxiang Lin, Zihan Wang, Mengyang Liu, Yuxuan Shan 외 arxiv

While agents are increasingly spending more resources, today agent cost is mostly measured only after execution. A Budget-Aware Agent (BAGEN) should treat budget as an active control signal, rather than a passive cost me…

Global Task-aware Fault Detection, Identification For On-Orbit Multi-Spacecraft Collaborative Inspection

2025-05-06 · Akshita Gupta, Yashwanth Kumar Nakka, Changrak Choi, Amir Rahmani

In this paper, we present a global-to-local task-aware fault detection and identification algorithm to detect failures in a multi-spacecraft system performing a collaborative inspection (referred to as global) task. The …

Fault Detection