ProRefine: Inference-time Prompt Refinement with Textual Feedback

2025-06-05 · Deepak Pandita, Tharindu Cyril Weerasooriya, Ankit Parag Shah, Christopher M. Homan, Wei Wei

Agentic workflows, where multiple AI agents collaborate to accomplish complex tasks like reasoning or planning, are becoming increasingly prevalent. However, these workflows often suffer from error propagation and sub-optimal performance, largely due to poorly designed prompts that fail to effectively guide individual agents. This is a critical problem because it limits the reliability and scalability of these powerful systems. We introduce ProRefine, an innovative inference-time prompt optimization method that leverages textual feedback from large language models (LLMs) to address this challenge. ProRefine dynamically refines prompts for multi-step reasoning tasks without additional training or ground truth labels. Evaluated on five benchmark mathematical reasoning datasets, ProRefine significantly surpasses zero-shot Chain-of-Thought baselines by 3 to 37 percentage points. This approach not only boosts accuracy but also allows smaller models to match the performance of larger ones, highlighting its potential for efficient and scalable AI deployment, and democratizing access to high-performing AI.

📄 PDF Abstract BibTeX arXiv:2506.05305

Code (0)

등록된 구현이 없습니다.

Tasks

Mathematical Reasoning

SafeCtrl-RL: Inference-Time Adaptive Behaviour Control for LLM Dialogue via RL-Driven Prompt Optimisation

2026-05-25 · Michael Orme, Yanchao Yu, Zhiyuan Tan arxiv

Ensuring safe and contextually appropriate behaviour in Large Language Models (LLMs) remains a critical challenge for real-world deployment. We present \textbf{SafeCtrl-RL}, an inference-time behavioural control framewor…

Reinforcement Learning Dialogue Generation

Medal S: Spatio-Textual Prompt Model for Medical Segmentation

2025-11-17 · Pengcheng Shi, Jiawei Chen, Jiaqi Liu, Xinglin Zhang 외 arxiv

We introduce Medal S, a medical segmentation foundation model that supports native-resolution spatial and textual prompts within an end-to-end trainable framework. Unlike text-only methods lacking spatial awareness, Meda…

Data Augmentation

PrismVAU: Prompt-Refined Inference System for Multimodal Video Anomaly Understanding

2026-01-06 · Iñaki Erregue, Kamal Nasrollahi, Sergio Escalera arxiv

Video Anomaly Understanding (VAU) extends traditional Video Anomaly Detection (VAD) by not only localizing anomalies but also describing and reasoning about their context. Existing VAU approaches often rely on fine-tuned…

Video Anomaly Detection Prompt Engineering

Injecting Image Guidance into Text-Conditioned Diffusion Models at Inference

2026-05-24 · Agata Żywot, Iason Skylitsis, Thijmen Nijdam, Zoe Tzifa-Kratira 외 arxiv

Text-to-image diffusion models like Stable Diffusion generate high-quality images from text, but lack a way to inject visual guidance (e.g. sketches, styles) at inference without retraining. Existing methods either requi…

Style Transfer

VL-SAM-v3: Memory-Guided Visual Priors for Open-World Object Detection

2026-05-05 · Chih-Chung Liu, Zhiwei Lin, Yongtao Wang arxiv

Open-world object detection aims to localize and recognize objects beyond a fixed closed-set label space. It is commonly divided into two categories, i.e., open-vocabulary detection, which assumes a predefined category l…

Object Detection