Prompt Optimization

Follow this topic Ask about this topic

Prompt optimization studies how to adapt instructions and other inputs so language and multimodal models perform better without necessarily changing their weights. Common approaches use textual feedback or gradients, evolutionary search, Bayesian optimization, bandits, and reinforcement learning, with validation examples guiding candidate selection. Work increasingly optimizes prompts alongside tool schemas, workflows, agent routing, and communication, across settings such as reasoning, retrieval, tool use, and image generation. Gains can depend heavily on the evaluation data and objective: prompts may overfit, break requirements they were not scored on, or trade accuracy against cost, readability, and robustness, making held-out testing and regression checks central challenges.

Latest papers

141 papers21 papers in the last four weeks, up 75% on the four weeks before. 0.1% of all new papers.

Parameter-Efficient Neuroevolution for Diverse LLM Generation: Quality-Diversity Optimization via Prompt Embedding Evolution
May 10, 2026Dongxin Guo, Jikun Wu, Siu Ming YiuEvolutionary Optimization Large Language Model-Guided Optimization
The University of Hong Kong, China · Stellaris AI Limited, China
SecureForge: Finding and Preventing Vulnerabilities in LLM-Generated Code via Prompt Optimization
May 8, 2026Houjun Liu, Lisa Einstein, John Yang +5LLM Auditing Prompt Optimization
Stanford University
MASPO: Joint Prompt Optimization for LLM-based Multi-Agent Systems
May 7, 2026Zhexuan Wang, Xuebo Liu, Li Wang +4Multi-Agent LLM Systems Multi-Agent System Optimization
Institute of Computing and Intelligence, Harbin Institute of Technology, Shenzhen, China.
MOIRA: Policy Memory and Belief Revision for Language-Model Agents in Non-Stationary Pair Trading
May 3, 2026Polydoros Giannouris, Yuechen Jiang, Lingfei Qian +5Reinforcement Learning Hierarchical RL
The University of Manchester Manchester, UK · The Fin AI USA · Harvard University Cambridge, MA, USA +1
Optimization before Evaluation: Evaluation with Unoptimised Prompts Can be Misleading
Apr 30, 2026Nicholas Sadjoli, Tim Siefken, Atin Ghosh +2LLM Evaluation Language Model Generation Evaluation
SAP · Stanford University
Skills-Coach: A Self-Evolving Skill Optimizer via Training-Free GRPO
Apr 30, 2026Yu Tian, Jiawei Chen, Lifan Zheng +5LLM Agent Self-Improvement LLM Agent Skill Learning
University of Chinese Academy of Sciences · 2East China Normal University · 3Zhongguancun Academy +3
FlowBot: Inducing LLM Workflows with Bilevel Optimization and Textual Gradients
Apr 29, 2026Hongyeon Yu, Young-Bum Kim, Yoon KimAgentic Workflows LLM Agent Workflow Optimization
Naver Search US · Massachusetts Institute of Technology
CAP-CoT: Cycle Adversarial Prompt for Improving Chain of Thoughts in LLM Reasoning
Apr 25, 2026Shuxu Chen, Yitian Zhou, Jiaquan Zhang +6Adversarial Prompt Generation LLM Prompting
Department of Electronics and Information Convergence Engineering, Kyung Hee University, Republic of Korea · University of Electronic Science and Technology of China, Chengdu, China · East China Jiaotong University, Nanchang, China +1
Small Language Model Helps Resolve Semantic Ambiguity of LLM Prompt
Apr 25, 2026Zhenzhen Huang, Chaoning Zhang, Fachrina Dewi Puspitasari +4LLM Prompting Prompt Optimization
School of Computer Science and Engineering, University of Electronic Science and Technology of China · Department of Electronic Engineering, Kyung Hee University
Supplement Generation Training for Enhancing Agentic Task Performance
Apr 22, 2026Young Min Cho, Daniele Bonadiman, Divya Bhargavi +8LLM Agent Training Prompt Optimization
University of Pennsylvania · AWS Agentic AI Labs · Amazon
JTPRO: A Joint Tool-Prompt Reflective Optimization Framework for Language Agents
Apr 20, 2026Sandip Ghoshal, Anshul Mittal, Jyotika Singh +9AI Agent Reliability LLM Tool Use
Oracle AI
Prompt Optimization Enables Stable Algorithmic Collusion in LLM Agents
Apr 20, 2026Yingtao TianMulti-Agent Coordination Algorithmic Collusion
Sakana AI Tokyo, Japan
Semantic Density Effect (SDE): Maximizing Information Per Token Improves LLM Accuracy
Apr 19, 2026Amr AhmedLLM Prompting Prompt Optimization
Public Health Department, Riyadh First Health Cluster · Ministry of Health, Saudi Arabia
AutoVQA-G: Self-Improving Agentic Framework for Automated Visual Question Answering and Grounding Annotation
Apr 19, 2026Rongsheng Hu, Runwei Guan, Yicheng Di +2Visual Question Answering LLM-Assisted Annotation
School of Artificial Intelligence and Computer Science, Jiangnan University, Wuxi, China · Thrust of Artificial Intelligence, HKUST(GZ), Guangzhou, China
FRESCO: Benchmarking and Optimizing Re-rankers for Evolving Semantic Conflict in Retrieval-Augmented Generation
Apr 14, 2026Sohyun An, Hayeon Lee, Shuibenyang Yuan +4LLM Reranking RAG Evaluation
Meta Superintelligence Labs · UCLA
Learning Chain Of Thoughts Prompts for Predicting Entities, Relations, and even Literals on Knowledge Graphs
Apr 14, 2026Alkid Baci, Luke Friedrichs, Caglar Demir +2KG Completion LLM Prompting
Department of Computer Science Paderborn University Warburger Str. 100, 33098 Paderborn, Germany
PR-MaGIC: Prompt Refinement Via Mask Decoder Gradient Flow For In-Context Segmentation
Apr 13, 2026Minjae Lee, Sungwoo Hur, Soojin Hwang +1Image Segmentation Promptable Image Segmentation
Pohang University of Science and Technology, Pohang, South Korea
When Valid Signals Fail: Regime Boundaries Between LLM Features and RL Trading Policies
Apr 13, 2026Zhengzhe YangLLM-Guided RL Reinforcement Learning
Independent Researcher
Semantic Feature Analysis: Improving Agents Without Searching Over Rollouts
Apr 12, 2026Yuval David, Fabiana Fournier, Lior Limonad +1LLM Agent Self-Improvement Tool-Using Agents
IBM Software Innovation Lab Haifa, Israel
Evolutionary Token-Level Prompt Optimization for Diffusion Models
Apr 10, 2026Domício Pereira Neto, João Correia, Penousal MachadoPrompt Optimization for T2I Generation Prompt Optimization
University of Coimbra Coimbra, Portugal
Automated Instruction Revision (AIR): A Structured Comparison of Task Adaptation Strategies for LLM
Apr 10, 2026Solomiia Bilyk, Volodymyr Getmanskyi, Taras FirmanLLM Fine-Tuning Prompt Optimization
Eleks Ltd. · Ukrainian Catholic University, Lviv, Ukraine
EvolveRouter: Co-Evolving Routing and Prompt for Multi-Agent Question Answering
Apr 6, 2026Jiatan Huang, Zheyuan Zhang, Kaiwen Shi +2LLM Agent Routing Multi-Agent Collaboration
University of Connecticut, USA · University of Notre Dame, USA
Optimizing LLM Prompt Engineering with DSPy Based Declarative Learning
Apr 6, 2026Shiek Ruksana, Sailesh Kiran Kurra, Thipparthi Sanjay BaradwajLLM Prompting Prompt Optimization
Vasavi College of Engineering, Hyderabad, TS, India · Amazon, Texas, United States of America · Vasavi College of Engineering, Telangana, India
Unlocking Prompt Infilling Capability for Diffusion Language Models
Apr 4, 2026Yoshinari Fujinuma, Keisuke SakaguchiDiffusion Language Models Masked Diffusion Models
Patronus AI · Tohoku University, RIKEN
Self-Optimizing Multi-Agent Systems for Deep Research
Apr 3, 2026Arthur Câmara, Vincent Slot, Jakub ZavrelDeep Research Agents Multi-Agent LLM Systems
Zeta Alpha, Amsterdam, The Netherlands
Experience as a Compass: Multi-agent RAG with Evolving Orchestration and Agent Prompts
Apr 1, 2026Sha Li, Naren RamakrishnanRetrieval-Augmented Generation Multi-Agent Orchestration
Virginia Tech
Privacy Guard & Token Parsimony by Prompt and Context Handling and LLM Routing
Mar 30, 2026Alessio LangiuPrivacy Protection for LLM Agents Privacy Leakage in Language Models
National Research Council of Italy - Institute of Marine Sciences (CNR-ISMAR)
Beyond the Answer: Decoding the Behavior of LLMs as Scientific Reasoners
Mar 30, 2026Rohan Pandey, Eric Ye, Michael LiLLM Prompting LLM Interpretability
Carnegie Mellon University
DetPO: In-Context Learning with Multi-Modal LLMs for Few-Shot Object Detection
Mar 24, 2026Gautam Rajendrakumar Gare, Neehar Peri, Matvei Popov +3Large Vision-Language Models Few-Shot Object Detection
Carnegie Mellon University · Roboflow
P^2O: Joint Policy and Prompt Optimization
Mar 23, 2026Xinyu Lu, Kaiqi Zhang, Jinglin Yang +6RL for Language Model Reasoning Reinforcement Learning with Verifiable Rewards
Chinese Information Processing Laboratory, Institute of Software, Chinese Academy of Sciences · University of Chinese Academy of Sciences · Institute of Information Engineering, Chinese Academy of Sciences +2

May 10, 2026J/K move · Enter open · S save

Parameter-Efficient Neuroevolution for Diverse LLM Generation: Quality-Diversity Optimization via Prompt Embedding Evolution

Dongxin Guo, Jikun Wu, Siu Ming Yiu

The University of Hong Kong, China · Stellaris AI Limited, China

Evolutionary Optimization Large Language Model-Guided Optimization Quality-Diversity Optimization Diverse Text Generation Prompt Optimization Neuroevolution

Open paper AskPDF arXiv

Large Language Models exhibit mode collapse, producing homogeneous outputs that fail to explore valid solution spaces. We present QD-LLM, a framework for parameter-efficient neuroevolution that evolves prompt embeddings, compact neural interfaces (~32K parameters) that steer generation in frozen LLMs (70B+ parameters), within a Quality-Diversity (QD) optimization framework. Our contributions: (1) evolved prompt embeddings via gradient-free optimization enabling behavioral steering without model fine-tuning; (2) hybrid behavior characterization combining semantic and explicit features with formal coverage bounds (Theorem 1) under validated near-independence (NMI

= 0.08 \pm 0.02

); (3) co-evolutionary variation operators including targeted behavioral mutation via finite-difference gradient estimation. On HumanEval (164 problems), MBPP, and creative writing benchmarks, QD-LLM achieves 46.4% higher coverage and 41.4% higher QD-Score than QDAIF (

p<0.001

, 30 runs, Vargha-Delaney

A=0.94

). We demonstrate downstream utility: diverse archives improve test generation (34% more edge cases) and fine-tuning data quality (8.3% accuracy gain). We validate across open-source LLMs (Llama-3-70B, Mistral-Large) with full embedding access, establishing prompt embedding evolution as an effective paradigm bridging neuroevolution and modern LLMs.