Papers with APO
Reflection in the Dark: Exposing and Escaping the Black Box in Reflective Prompt Optimization (2026.acl-srw)
Copied to clipboard
| Challenge: | Automatic prompt optimization (APO) is a powerful paradigm for improving LLM performance without manual prompt engineering. |
| Approach: | They propose a framework that decouples hypothesis generation from prompt rewriting . they propose VISTA framework that recovers accuracy to 87.57% on same defective seed . |
| Outcome: | The proposed framework outperforms baselines on GSM8K and AIME2025 on a defective seed. |
GenPilot: A Multi-Agent System for Test-Time Prompt Optimization in Image Generation (2025.findings-emnlp)
Copied to clipboard
Wen Ye, Zhaocheng Liu, Gui Yuwei, Tingyu Yuan, Yunyue Su, Bowen Fang, Chaoyang Zhao, Qiang Liu, Liang Wang
| Challenge: | Existing methods for text-to-image synthesis lack systematic error analysis and refinement strategies, resulting in limited reliability and effectiveness. |
| Approach: | They propose a plug-and-play multi-agent system called GenPilot that integrates error analysis, clustering-based adaptive exploration, fine-grained verification and a memory module for iterative optimization. |
| Outcome: | The proposed method improves text consistency and structural coherence on images with a plug-and-play system. |
InstaJudge: Aligning Judgment Bias of LLM-as-Judge with Humans in Industry Applications (2025.emnlp-industry)
Copied to clipboard
| Challenge: | Automated evaluation using LLM-as-Judge is a viable alternative to human evaluation, but misalignment of judgment biases between humans and LLMs hinders its use in real-world applications. |
| Approach: | They propose an LLM-as-Judge library that improves alignments of judgment biases through automatic prompt optimization. |
| Outcome: | The proposed library outperforms existing LLM-as-Judge libraries by a large margin while being more cost efficient. |
Data-Efficient Automatic Prompt Optimization for Memory-Enhanced Conversational Agents (2025.emnlp-industry)
Copied to clipboard
| Challenge: | Automatic prompt optimization (APO) uses algorithms to optimize prompts for LLMs . but application to memory-enhanced conversational agents presents unique challenges . |
| Approach: | They propose a framework for automatic prompt optimization for memory-enhanced conversational agents . they leverage LLMs to holistically optimize the prompts of all agents based on memory writing, reading, and response generation . |
| Outcome: | The proposed framework is applied to memory-enhanced conversational agents . it provides a holistic quality score for responses and performs error attribution . |
Adversarial Preference Optimization: Enhancing Your Alignment via RM-LLM Game (2024.findings-acl)
Copied to clipboard
| Challenge: | Existing methods for training large language models require additional annotations to adjust to shifted distributions. |
| Approach: | They propose an algorithm that allows LLMs and reward models to update alternatively via a min-max game to improve their alignment. |
| Outcome: | The proposed framework improves existing alignment baselines in terms of LLM helpfulness and harmlessness. |
Improving Attributed Text Generation of Large Language Models via Preference Learning (2024.findings-acl)
Copied to clipboard
| Challenge: | Large language models have been widely adopted in natural language processing, yet they produce unreliable content. |
| Approach: | They propose to model the attribution task as preference learning and introduce an automatic preference optimization framework that synthesizes attribution preference data. |
| Outcome: | The proposed method achieves state-of-the-art citation F1 with higher answer quality than existing methods. |
LLM Prompt Duel Optimizer: Efficient Label-Free Prompt Optimization (2026.findings-acl)
Copied to clipboard
Yuanchen Wu, Saurabh Verma, Justin Lee, Fangzhou Xiong, Poppy Zhang, Amel Awadelkarim, Xu Chen, Yubai Yuan, Shawndra Hill
| Challenge: | Large language models (LLMs) are highly sensitive to prompts, but most automatic prompt optimization methods assume access to ground-truth references that are costly to obtain. |
| Approach: | They propose a sample-efficient framework for label-free prompt optimization based on pairwise preference feedback from an LLM judge. |
| Outcome: | Experiments on BIG-bench Hard and MS MARCO show that the proposed framework identifies stronger prompts than label-free baselines while offering favorable quality–cost trade-offs. |
FIPO: Free-form Instruction-oriented Prompt Optimization with Preference Dataset and Modular Fine-tuning Schema (2025.coling-main)
Copied to clipboard
| Challenge: | naive prompts can enhance the task performance of large language models, but they are resource-intensive. |
| Approach: | They propose an automatic prompt optimization method that refines naive prompts according to task outputs from in-box testing models. |
| Outcome: | The proposed method is based on a large-scale dataset and performed fairly across multiple models. |
ZERA: Zero-init Instruction Evolving Refinement Agent – From Zero Instructions to Structured Prompts via Principle-based Optimization (2025.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods to improve large language model performance focus on user prompts and require large sample sizes and long iteration cycles. |
| Approach: | They propose a framework that jointly optimizes both system and user prompts . they evaluate ZERA across five LLMs and nine diverse datasets spanning reasoning, summarization, and code generation tasks. |
| Outcome: | The proposed framework improves prompt construction over baselines and is available on github . it scores prompts using eight generalizable criteria and revises prompts based on structured critiques. |
View-R1: Asymmetric Policy Optimization for Difficulty-Aware Multimodal Reinforcement Learning (2026.findings-acl)
Copied to clipboard
| Challenge: | Multimodal Large Language Models (MLLMs) are powerful at integrating diverse data but struggle with complex reasoning. |
| Approach: | They propose a method which separates responses into positive and negative groups to stabilize training and preserve knowledge. |
| Outcome: | The proposed model View-R1 achieves a 10.55% improvement in reasoning and outperforms larger models while maintaining and improving performance on general tasks. |
A Systematic Survey of Automatic Prompt Optimization Techniques (2025.emnlp-main)
Copied to clipboard
Kiran Ramnath, Kang Zhou, Sheng Guan, Soumya Smruti Mishra, Xuan Qi, Zhengyuan Shen, Shuai Wang, Sangmin Woo, Sullam Jeoung, Yawei Wang, Haozhu Wang, Han Ding, Yuzhe Lu, Zhichao Xu, Yun Zhou, Balasubramaniam Srinivasan, Qiaojing Yan, Yueyan Chen, Haibo Ding, Panpan Xu, Lin Lee Cheong
| Challenge: | Recent advances in prompt engineering have created impediments for end users to adopt . however, prompt engineering remains an impedance due to rapid advances in models, tasks, and associated best practices. |
| Approach: | They propose to define APO as a 5-part unifying framework and categorize all relevant works based on their salient features. |
| Outcome: | The proposed framework aims to improve the performance of large language models on various tasks. |