{"total":139,"rows":[{"id":"2410.17127","title":"PAPILLON: Privacy Preservation from Internet-based and Local Language Model Ensembles","created":"2024-10-22","cited_by_count":57,"area":null},{"id":"2606.14249","title":"HarnessX: A Composable, Adaptive, and Evolvable Agent Harness Foundry","created":"2026-06-12","cited_by_count":47,"area":null},{"id":"2507.03041","title":"Optimas: Optimizing Compound AI Systems with Globally Aligned Local Rewards","created":"2025-07-03","cited_by_count":24,"area":null},{"id":"2510.02453","title":"How to Train Your Advisor: Steering Black-Box LLMs with Advisor Models","created":"2025-10-02","cited_by_count":24,"area":null},{"id":"2408.11061","title":"StructuredRAG: JSON Response Formatting with Large Language Models","created":"2024-08-07","cited_by_count":22,"area":null},{"id":"2410.23214","title":"Grounding by Trying: LLMs with Reinforcement Learning-Enhanced Retrieval","created":"2024-10-30","cited_by_count":17,"area":null},{"id":"2505.14661","title":"Abacus: A Cost-Based Optimizer for Semantic Operator Systems","created":"2025-05-20","cited_by_count":13,"area":null},{"id":"2504.07157","title":"GAAPO: Genetic Algorithmic Applied to Prompt Optimization","created":"2025-04-09","cited_by_count":11,"area":null},{"id":"2412.07820","title":"Hyperband-based Bayesian Optimization for Black-box Prompt Selection","created":"2024-12-10","cited_by_count":10,"area":null},{"id":"2411.16718","title":"Neuro-Symbolic Evaluation of Text-to-Video Models using Formal Verification","created":"2024-11-22","cited_by_count":9,"area":null},{"id":"2510.13907","title":"LLM Prompt Duel Optimizer: Efficient Label-Free Prompt Optimization","created":"2025-10-14","cited_by_count":8,"area":null},{"id":"2502.00728","title":"Meta-Prompt Optimization for LLM-Based Sequential Decision Making","created":"2025-02-02","cited_by_count":7,"area":null},{"id":"2502.08056","title":"Cognify: Supercharging Gen-AI Workflows With Hierarchical Autotuning","created":"2025-02-12","cited_by_count":7,"area":null},{"id":"2502.15944","title":"AutoMedPrompt: A New Framework for Optimizing LLM Medical Prompts Using Textual Gradients","created":"2025-02-21","cited_by_count":7,"area":null},{"id":"2506.06950","title":"What Makes a Good Natural Language Prompt?","created":"2025-06-07","cited_by_count":7,"area":null},{"id":"2605.05973","title":"Towards Reliable LLM Evaluation: Correcting the Winner's Curse in Adaptive Benchmarking","created":"2026-05-07","cited_by_count":7,"area":null},{"id":"2410.10724","title":"Large Language Models Are Active Critics in NLG Evaluation","created":"2024-10-14","cited_by_count":6,"area":null},{"id":"2502.18746","title":"A Survey of Automatic Prompt Optimization with Instruction-focused Heuristic-based Search Algorithm","created":"2025-02-26","cited_by_count":6,"area":null},{"id":"2506.00400","title":"Scaling Textual Gradients via Sampling-Based Momentum","created":"2025-05-31","cited_by_count":6,"area":null},{"id":"2506.19773","title":"Automatic Prompt Optimization for Knowledge Graph Construction: Insights from an Empirical Study","created":"2025-06-24","cited_by_count":6,"area":null},{"id":"2512.02840","title":"promptolution: A Unified, Modular Framework for Prompt Optimization","created":"2025-12-02","cited_by_count":6,"area":null},{"id":"2605.12484","title":"Learning, Fast and Slow: Towards LLMs That Adapt Continually","created":"2026-05-12","cited_by_count":6,"area":null},{"id":"2607.14004","title":"Do Agent Optimizers Compound? A Continual-Learning Evaluation on Terminal-Bench 2.0","created":"2026-07-15","cited_by_count":6,"area":null},{"id":"2409.20042","title":"Beyond Scores: A Modular RAG-Based System for Automatic Short Answer Scoring with Feedback","created":"2024-09-30","cited_by_count":5,"area":null},{"id":"2602.06221","title":"BenchMarker: An Education-Inspired Toolkit for Highlighting Flaws in Multiple-Choice Benchmarks","created":"2026-02-05","cited_by_count":5,"area":null},{"id":"2502.10522","title":"GraphiT: Efficient Node Classification on Text-Attributed Graphs with Prompt Optimized LLMs","created":"2025-02-14","cited_by_count":4,"area":null},{"id":"2506.08234","title":"Compound AI Systems Optimization: A Survey of Methods, Challenges, and Future Directions","created":"2025-06-09","cited_by_count":4,"area":null},{"id":"2506.15846","title":"Finance Language Model Evaluation (FLaME)","created":"2025-06-18","cited_by_count":4,"area":null},{"id":"2510.09030","title":"Automated Refinement of Essay Scoring Rubrics for Language Models via Reflect-and-Revise","created":"2025-10-10","cited_by_count":4,"area":null},{"id":"2510.23941","title":"Auto prompting without training labels: An LLM cascade for product quality assessment in e-commerce catalogs","created":"2025-10-27","cited_by_count":4,"area":null},{"id":"2510.25808","title":"PRESTO: Preimage-Informed Instruction Optimization for Prompting Black-Box LLMs","created":"2025-10-29","cited_by_count":4,"area":null},{"id":"2605.19633","title":"optimize_anything: A Universal API for Optimizing any Text Parameter","created":"2026-05-19","cited_by_count":4,"area":null},{"id":"2503.02650","title":"The Effectiveness of Large Language Models in Transforming Unstructured Text to Standardized Formats","created":"2025-03-04","cited_by_count":3,"area":null},{"id":"2511.20836","title":"Structured Prompts Improve Evaluation of Language Models","created":"2025-11-25","cited_by_count":3,"area":null},{"id":"2601.13922","title":"Automatic Prompt Optimization for Dataset-Level Feature Discovery","created":"2026-01-20","cited_by_count":3,"area":null},{"id":"2602.08306","title":"TextResNet: Decoupling and Routing Optimization Signals in Compound AI Systems via Deep Residual Tuning","created":"2026-02-09","cited_by_count":3,"area":null},{"id":"2603.18388","title":"Reflection in the Dark: Exposing and Escaping the Black Box in Reflective Prompt Optimization","created":"2026-03-19","cited_by_count":3,"area":null},{"id":"2605.21318","title":"TextReg: Mitigating Prompt Distributional Overfitting via Regularized Text-Space Optimization","created":"2026-05-20","cited_by_count":3,"area":null},{"id":"2608.11772","title":"Diagnosis Before Recovery: Turning Agent Failures into Selective Self-Correction","created":"2026-08-12","cited_by_count":3,"area":null},{"id":"2501.11114","title":"Clinical trial cohort selection using Large Language Models on n2c2 Challenges","created":"2025-01-19","cited_by_count":2,"area":null},{"id":"2502.20315","title":"LangProBe: a Language Programs Benchmark","created":"2025-02-27","cited_by_count":2,"area":null},{"id":"2503.11118","title":"UMB@PerAnsSumm 2025: Enhancing Perspective-Aware Summarization with Prompt Optimization and Supervised Fine-Tuning","created":"2025-03-14","cited_by_count":2,"area":null},{"id":"2506.00056","title":"Toward Knowledge-Guided AI for Inverse Design in Manufacturing: A Perspective on Domain, Physics, and Human-AI Synergy","created":"2025-05-29","cited_by_count":2,"area":null},{"id":"2509.00038","title":"Compiling Prompts, Not Crafting Them: A Reproducible Workflow for AI-Assisted Evidence Synthesis","created":"2025-08-22","cited_by_count":2,"area":null},{"id":"2512.11013","title":"PIAST: Rapid Prompting with In-context Augmentation for Scarce Training data","created":"2025-12-11","cited_by_count":2,"area":null},{"id":"2604.00280","title":"Spec-Harness: Assessing and Guiding LLM-Synthesized Formal Specifications Beyond Verifiability","created":"2026-03-31","cited_by_count":2,"area":null},{"id":"2605.21516","title":"Harnesses for Inference-Time Alignment over Execution Trajectories","created":"2026-05-15","cited_by_count":2,"area":null},{"id":"2605.24564","title":"Summoning the Oracle to Slay It: Mitigating Look-Ahead Bias in Financial Backtesting with Large Language Models","created":"2026-05-23","cited_by_count":2,"area":null},{"id":"2608.09140","title":"Beyond Direct Identifiers: Probabilistic Privacy Risk Estimation for Privacy-Conscious LLM Query Delegation","created":"2026-08-10","cited_by_count":2,"area":null},{"id":"2506.08422","title":"Transforming Expert Knowledge into Scalable Ontology via Large Language Models","created":"2025-06-10","cited_by_count":1,"area":null},{"id":"2508.18210","title":"Why Synthetic Isn't Real Yet: A Diagnostic Framework for Contact Center Dialogue Generation","created":"2025-08-25","cited_by_count":1,"area":null},{"id":"2508.18244","title":"Type-Compliant Adaptation Cascades: Adapting Programmatic LM Workflows to Data","created":"2025-08-25","cited_by_count":1,"area":null},{"id":"2509.02363","title":"Towards Temporal Knowledge-Base Creation for Fine-Grained Opinion Analysis with Language Models","created":"2025-09-02","cited_by_count":1,"area":null},{"id":"2510.07993","title":"Leveraging Author-Specific Context for Scientific Figure Caption Generation: 3rd SciCap Challenge","created":"2025-10-09","cited_by_count":1,"area":null},{"id":"2511.23376","title":"Is Passive Expertise-Based Personalization Enough? A Case Study in AI-Assisted Test-Taking","created":"2025-11-28","cited_by_count":1,"area":null},{"id":"2512.24933","title":"ADOPT: Adaptive Dependency-Guided Joint Prompt Optimization for Multi-Step LLM Pipelines","created":"2025-12-31","cited_by_count":1,"area":null},{"id":"2602.05762","title":"RocqSmith: Can Automatic Optimization Forge Better Proof Agents?","created":"2026-02-05","cited_by_count":1,"area":null},{"id":"2602.20743","title":"Adaptive Text Anonymization: Learning Privacy-Utility Trade-offs via Prompt Optimization","created":"2026-02-24","cited_by_count":1,"area":null},{"id":"2603.03298","title":"TATRA: Training-Free Instance-Adaptive Prompting Through Rephrasing and Aggregation","created":"2026-02-06","cited_by_count":1,"area":null},{"id":"2603.16045","title":"POaaS: Minimal-Edit Prompt Optimization as a Service to Lift Accuracy and Cut Hallucinations on On-Device sLLMs","created":"2026-03-17","cited_by_count":1,"area":null},{"id":"2603.20667","title":"REVERE: Reflective Evolving Research Engineer","created":"2026-03-21","cited_by_count":1,"area":null},{"id":"2604.27082","title":"When Your LLM Reaches End-of-Life: A Framework for Confident Model Migration in Production Systems","created":"2026-04-29","cited_by_count":1,"area":null},{"id":"2604.27637","title":"Optimization before Evaluation: Evaluation with Unoptimised Prompts Can be Misleading","created":"2026-04-30","cited_by_count":1,"area":null},{"id":"2605.06937","title":"A Reproducible Optimisation Protocol for Calibrating Prompt-Based Large Language Model Workflows in Evidence Synthesis","created":"2026-05-07","cited_by_count":1,"area":null},{"id":"2605.14561","title":"Prompt Segmentation and Annotation Optimisation: Controlling LLM Behaviour via Optimised Segment-Level Annotations","created":"2026-05-14","cited_by_count":1,"area":null},{"id":"2605.15721","title":"Contexting as Recommendation: Evolutionary Collaborative Filtering for Context Engineering","created":"2026-05-15","cited_by_count":1,"area":null},{"id":"2605.18512","title":"Easier to Judge than to Find: Predicting In-Context Learning Success for Demonstration Selection","created":"2026-05-18","cited_by_count":1,"area":null},{"id":"2605.18869","title":"MO-CAPO: Multi-Objective Cost-Aware Prompt Optimization","created":"2026-05-15","cited_by_count":1,"area":null},{"id":"2605.19093","title":"Embedding by Elicitation: Dynamic Representations for Bayesian Optimization of System Prompts","created":"2026-05-18","cited_by_count":1,"area":null},{"id":"2606.18889","title":"Improving Medical Communication using Rubric-Guided Counterfactual Recommendations","created":"2026-06-17","cited_by_count":1,"area":null},{"id":"2606.19605","title":"FAPO: Fully Automated Prompt Optimization of Multi-Step LLM Pipelines","created":"2026-06-17","cited_by_count":1,"area":null},{"id":"2606.31036","title":"Teaching LLMs to Recommend and Defer in Underrepresented Epilepsy Care","created":"2026-06-30","cited_by_count":1,"area":null},{"id":"2608.06714","title":"The Optimizer Is the Agent: Reasoning-Driven Search across Prompts, Programs, and ML Workflows","created":"2026-08-07","cited_by_count":1,"area":null},{"id":"2608.10471","title":"RLMOpt: Adaptive Prompt Optimization via Recursive Language Models","created":"2026-08-11","cited_by_count":1,"area":null},{"id":"2608.24804","title":"StarHarness: Evolving Harnesses with Stratified Search for Enterprise Environments","created":"2026-08-25","cited_by_count":1,"area":null},{"id":"2609.01564","title":"From Confusion to Clarity: Confusion-Aware Retrieval and Knowledge Injection for Text Classification","created":"2026-09-01","cited_by_count":1,"area":null},{"id":"2609.30967","title":"MoMHa: Multi-Objective Optimization of LLM Harnesses over Accuracy, Safety, and Tokens","created":"2026-09-25","cited_by_count":1,"area":null},{"id":"2609.39148","title":"Do Self-Evolving Skills Generalize to Held-Out Tasks?","created":"2026-09-30","cited_by_count":1,"area":null},{"id":"2505.03030","title":"UCSC at SemEval-2025 Task 3: Context, Models and Prompt Optimization for Automated Hallucination Detection in LLM Output","created":"2025-05-05","cited_by_count":0,"area":null},{"id":"2505.17137","title":"Cog-TiPRO: Iterative Prompt Refinement with LLMs to Detect Cognitive Decline via Longitudinal Voice Assistant Commands","created":"2025-05-22","cited_by_count":0,"area":null},{"id":"2505.20591","title":"Effectiveness of Prompt Optimization in NL2SQL Systems","created":"2025-05-26","cited_by_count":0,"area":null},{"id":"2507.10590","title":"Repairing Language Model Pipelines by Meta Self-Refining Competing Constraints at Runtime","created":"2025-07-11","cited_by_count":0,"area":null},{"id":"2509.20412","title":"Structuring Collective Action with LLM-Guided Evolution: From Ill-Structured Problems to Executable Heuristics","created":"2025-09-24","cited_by_count":0,"area":null},{"id":"2509.21907","title":"A Large-Scale Dataset and Citation Intent Classification in Turkish with LLMs","created":"2025-09-26","cited_by_count":0,"area":null},{"id":"2511.02936","title":"Zero-shot data citation function classification using transformer-based large language models (LLMs)","created":"2025-11-04","cited_by_count":0,"area":null},{"id":"2512.11202","title":"amc: The Automated Mission Classifier for Telescope Bibliographies","created":"2025-12-12","cited_by_count":0,"area":null},{"id":"2601.16800","title":"Large Language Models as Automatic Annotators and Annotation Adjudicators for Fine-Grained Opinion Analysis","created":"2026-01-23","cited_by_count":0,"area":null},{"id":"2602.00352","title":"DETOUR: An Interactive Benchmark for Dual-Agent Search and Reasoning","created":"2026-01-30","cited_by_count":0,"area":null},{"id":"2602.00997","title":"Error Taxonomy-Guided Prompt Optimization","created":"2026-02-01","cited_by_count":0,"area":null},{"id":"2602.05413","title":"SciDef: Datasets and Tools for Automated Definition Extraction from Scientific Literature with LLMs","created":"2026-02-05","cited_by_count":0,"area":null},{"id":"2602.22483","title":"Importance of Prompt Optimisation for Error Detection in Medical Notes Using Language Models","created":"2026-02-25","cited_by_count":0,"area":null},{"id":"2603.10004","title":"Fine-Tune, Don't Prompt, Your Language Model to Identify Biased Language in Clinical Notes","created":"2026-02-16","cited_by_count":0,"area":null},{"id":"2603.14130","title":"The GELATO Dataset for Legislative NER","created":"2026-03-14","cited_by_count":0,"area":null},{"id":"2604.00586","title":"More Human, More Efficient: Aligning Annotations with Quantized SLMs","created":"2026-04-01","cited_by_count":0,"area":null},{"id":"2604.03189","title":"Reflective Context Learning: Studying the Optimization Primitives of Context Space","created":"2026-04-03","cited_by_count":0,"area":null},{"id":"2604.09418","title":"Automated Instruction Revision (AIR): A Structured Comparison of Task Adaptation Strategies for LLM","created":"2026-04-10","cited_by_count":0,"area":null},{"id":"2604.10513","title":"Semantic Feature Analysis: Improving Agents Without Searching Over Rollouts","created":"2026-04-12","cited_by_count":0,"area":null},{"id":"2604.22565","title":"Learning Evidence Highlighting for Frozen LLMs","created":"2026-04-24","cited_by_count":0,"area":null},{"id":"2604.26258","title":"FlowBot: Inducing LLM Workflows with Bilevel Optimization and Textual Gradients","created":"2026-04-29","cited_by_count":0,"area":null},{"id":"2605.03092","title":"Semantically Enriching Investor Micro-blogs for Opinion-Aware Emotion Analysis: A Practical Approach","created":"2026-05-04","cited_by_count":0,"area":null}],"next_cursor":"100"}