{"total":63,"rows":[{"id":"2507.21046","title":"A Survey of Self-Evolving Agents: What, When, How, and Where to Evolve on the Path to Artificial Super Intelligence","created":"2025-07-28","cited_by_count":170,"area":"agents"},{"id":"2602.02919","title":"DeltaEvolve: Accelerating Scientific Discovery through Momentum-Driven Evolution","created":"2026-02-02","cited_by_count":26,"area":null},{"id":"2603.04900","title":"EvoTool: Self-Evolving Tool-Use Policy Optimization in LLM Agents via Blame-Aware Mutation and Diversity-Aware Selection","created":"2026-03-05","cited_by_count":24,"area":"agents"},{"id":"2601.13295","title":"CooperBench: Why Coding Agents Cannot be Your Teammates Yet","created":"2026-01-19","cited_by_count":23,"area":"agents"},{"id":"2608.01918","title":"HarnessCompass: Guiding Automatic Harness Evolution toward Generalizable and Effective Agent Harnesses","created":"2026-08-03","cited_by_count":17,"area":"agents"},{"id":"2510.16932","title":"Prompt-MII: Meta-Learning Instruction Induction for LLMs","created":"2025-10-19","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":"2606.23127","title":"Managing Procedural Memory in LLM Agents: Control, Adaptation, and Evaluation","created":"2026-06-22","cited_by_count":8,"area":"agents"},{"id":"2509.23387","title":"No Loss, No Gain: Gated Refinement and Adaptive Compression for Prompt Optimization","created":"2025-09-27","cited_by_count":7,"area":null},{"id":"2510.09201","title":"Multimodal Prompt Optimization: Why Not Leverage Multiple Modalities for MLLMs","created":"2025-10-10","cited_by_count":7,"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":"2508.02053","title":"ProCut: LLM Prompt Compression via Attribution Estimation","created":"2025-08-04","cited_by_count":6,"area":"inference"},{"id":"2510.07217","title":"GenPilot: A Multi-Agent System for Test-Time Prompt Optimization in Image Generation","created":"2025-10-08","cited_by_count":6,"area":null},{"id":"2510.17881","title":"POPI: Personalizing LLMs via Optimized Natural Language Preference Inference","created":"2025-10-17","cited_by_count":6,"area":null},{"id":"2510.24810","title":"COMMUNITYNOTES: A Dataset for Exploring the Helpfulness of Fact-Checking Explanations","created":"2025-10-28","cited_by_count":5,"area":null},{"id":"2603.09022","title":"MEMO: Memory-Augmented Model Context Optimization for Robust Multi-Turn Multi-Agent LLM Games","created":"2026-03-09","cited_by_count":5,"area":"agents"},{"id":"2606.23664","title":"MAS-PromptBench: When Does Prompt Optimization Improve Multi-Agent LLM Systems?","created":"2026-06-22","cited_by_count":5,"area":"agents"},{"id":"2504.21117","title":"Beyond One-Size-Fits-All: Inversion Learning for Highly Effective NLG Evaluation Prompts","created":"2025-04-29","cited_by_count":4,"area":null},{"id":"2509.00482","title":"Talk Less, Call Right: Enhancing Role-Play LLM Agents with Automatic Prompt Optimization and Role Prompting","created":"2025-08-30","cited_by_count":4,"area":"agents"},{"id":"2510.21148","title":"How to Auto-optimize Prompts for Domain Tasks? Adaptive Prompting and Reasoning through Evolutionary Domain Knowledge Adaptation","created":"2025-10-24","cited_by_count":4,"area":"lr"},{"id":"2602.13576","title":"Rubrics as an Attack Surface: Stealthy Preference Drift in LLM Judges","created":"2026-02-14","cited_by_count":4,"area":"alignment"},{"id":"2508.15610","title":"Transduction is All You Need for Structured Data Workflows","created":"2025-08-21","cited_by_count":3,"area":"agents"},{"id":"2601.07477","title":"JudgeFlow: Agentic Workflow Optimization via Block Judge","created":"2026-01-12","cited_by_count":3,"area":"agents"},{"id":"2602.21103","title":"Prompt-Level Distillation: A Non-Parametric Alternative to Model Fine-Tuning for Efficient Reasoning","created":"2026-02-24","cited_by_count":3,"area":"lr"},{"id":"2604.00901","title":"Experience as a Compass: Multi-agent RAG with Evolving Orchestration and Agent Prompts","created":"2026-04-01","cited_by_count":3,"area":"rag"},{"id":"2609.08572","title":"AgentGrad: Intervention-guided Prompt Optimization for Multi Agent Systems","created":"2026-09-08","cited_by_count":3,"area":"agents"},{"id":"2506.02326","title":"Something Just Like TRuST : Toxicity Recognition of Span and Target","created":"2025-06-02","cited_by_count":2,"area":null},{"id":"2510.25860","title":"Through the Judge's Eyes: Inferred Thinking Traces Improve Reliability of LLM Raters","created":"2025-10-29","cited_by_count":2,"area":"lr"},{"id":"2512.13598","title":"Textual Gradients are a Flawed Metaphor for Automatic Prompt Optimization","created":"2025-12-15","cited_by_count":2,"area":null},{"id":"2603.15968","title":"MAC: Multi-Agent Constitution Learning","created":"2026-03-16","cited_by_count":2,"area":"agents"},{"id":"2603.23455","title":"DetPO: In-Context Learning with Multi-Modal LLMs for Few-Shot Object Detection","created":"2026-03-24","cited_by_count":2,"area":"mllm"},{"id":"2605.15393","title":"LPDS: Evaluating LLM Robustness Through Logic-Preserving Difficulty Scaling","created":"2026-05-14","cited_by_count":2,"area":null},{"id":"2507.07421","title":"SynthEHR-Eviction: Enhancing Eviction SDoH Detection with LLM-Augmented Synthetic EHR Data","created":"2025-07-10","cited_by_count":1,"area":null},{"id":"2508.16603","title":"GreenTEA: Gradient Descent with Topic-modeling and Evolutionary Auto-prompting","created":"2025-08-12","cited_by_count":1,"area":null},{"id":"2508.17890","title":"UniAPO: Unified Multimodal Automated Prompt Optimization","created":"2025-08-25","cited_by_count":1,"area":null},{"id":"2601.00290","title":"ClinicalReTrial: Clinical Trial Redesign with Self-Evolving Agents","created":"2026-01-01","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":"2603.18009","title":"How Confident Is the First Token? An Uncertainty-Calibrated Prompt Optimization Framework for Large Language Model Classification and Understanding","created":"2026-02-23","cited_by_count":1,"area":"rag"},{"id":"2604.20726","title":"Exploiting LLM-as-a-Judge Disposition on Free Text Legal QA via Prompt Optimization","created":"2026-04-22","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":"2605.21781","title":"Reflective Prompt Tuning through Language Model Function-Calling","created":"2026-05-20","cited_by_count":1,"area":"agents"},{"id":"2606.09334","title":"How Far Can Prompting Go for Minimal-Edit Ukrainian Grammatical Error Correction?","created":"2026-06-08","cited_by_count":1,"area":null},{"id":"2512.05557","title":"2K-Characters-10K-Stories: A Quality-Gated Stylized Narrative Dataset with Disentangled Control and Sequence Consistency","created":"2025-12-05","cited_by_count":0,"area":null},{"id":"2601.13122","title":"Responsible AI for General-Purpose Systems: Overview, Challenges, and A Path Forward","created":"2026-01-19","cited_by_count":0,"area":null},{"id":"2601.13481","title":"Towards Efficient and Robust Linguistic Emotion Diagnosis for Mental Health via Multi-Agent Instruction Refinement","created":"2026-01-20","cited_by_count":0,"area":"agents"},{"id":"2602.03358","title":"GFlowPO: Generative Flow Network as a Language Model Prompt Optimizer","created":"2026-02-03","cited_by_count":0,"area":null},{"id":"2602.17867","title":"ADAPT: Hybrid Prompt Optimization for LLM Feature Visualization","created":"2026-02-19","cited_by_count":0,"area":null},{"id":"2606.04661","title":"CRAFT: Cost-aware Refinement And Front-aware Tuning of Prompts","created":"2026-06-03","cited_by_count":0,"area":null},{"id":"2606.18902","title":"SAGE: Stochastic Prompt Optimization via Agent-Guided Exploration","created":"2026-06-17","cited_by_count":0,"area":null},{"id":"2606.24004","title":"Towards Spec Learning: Inference-Time Alignment from Preference Pairs","created":"2026-06-22","cited_by_count":0,"area":"alignment"},{"id":"2607.00010","title":"Prompt Optimization for User Simulation in Conversational Recommender Systems: A Multi-Objective Framework","created":"2026-05-08","cited_by_count":0,"area":null},{"id":"2607.01972","title":"Object Aligner: A Configurable JSON Schema Similarity Score for Graphs, Applied to LLM Prompt Optimization","created":"2026-07-02","cited_by_count":0,"area":"agents"},{"id":"2607.20497","title":"From Errors to Rules: Iterative Prompt Optimization for Text Classification","created":"2026-06-15","cited_by_count":0,"area":null},{"id":"2607.22683","title":"Imprompt: A Language Framework for Prompt Programming","created":"2026-07-13","cited_by_count":0,"area":null},{"id":"2608.28067","title":"SEPO: Evidence-Grounded Prompt Optimization via Structural Editing","created":"2026-08-28","cited_by_count":0,"area":null},{"id":"2609.10810","title":"Larger Context Window, Fewer Overcorrections: Optimizing Prompts and Batching for Minimal-Edit Grammatical Error Correction","created":"2026-09-09","cited_by_count":0,"area":null},{"id":"2609.32898","title":"When Less Compute Is More: Adaptive Early Exit Improves Pretrained Outlier Detection","created":"2026-09-26","cited_by_count":0,"area":"inference"},{"id":"2609.34397","title":"SkillFocus: Evolving Agent Skills via Capability Decomposition","created":"2026-09-28","cited_by_count":0,"area":"agents"},{"id":"2609.37574","title":"MERGE: Multi-LLM Ensemble for Retrieval via Generative Enrichment","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2609.40330","title":"Turbo Harness: Instance-Adaptive Harness Optimization","created":"2026-09-30","cited_by_count":0,"area":null},{"id":"2610.00416","title":"Benchmarking Prompt Optimization of Large Language Models With Chess","created":"2026-09-30","cited_by_count":0,"area":null},{"id":"2610.13386","title":"MoPrO-SD: Modular Prompt Optimization for Stance Detection","created":"2026-10-09","cited_by_count":0,"area":null},{"id":"2610.14519","title":"Query-Adaptive Neuron Steering for LLMs","created":"2026-10-10","cited_by_count":0,"area":null}],"next_cursor":null}