{"list":"other","total":56,"rows":[{"id":"2005.11401","title":"Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks","created":"2020-05-22","cited_by_count":9297},{"id":"2306.05685","title":"Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena","created":"2023-06-09","cited_by_count":8626},{"id":"2304.03442","title":"Generative Agents: Interactive Simulacra of Human Behavior","created":"2023-04-07","cited_by_count":3568},{"id":"2303.17651","title":"Self-Refine: Iterative Refinement with Self-Feedback","created":"2023-03-30","cited_by_count":3442},{"id":"2310.06770","title":"SWE-bench: Can Language Models Resolve Real-World GitHub Issues?","created":"2023-10-10","cited_by_count":3373},{"id":"2305.16291","title":"Voyager: An Open-Ended Embodied Agent with Large Language Models","created":"2023-05-25","cited_by_count":2191},{"id":"2310.01405","title":"Representation Engineering: A Top-Down Approach to AI Transparency","created":"2023-10-02","cited_by_count":1336},{"id":"2305.14251","title":"FActScore: Fine-grained Atomic Evaluation of Factual Precision in Long Form Text Generation","created":"2023-05-23","cited_by_count":1282},{"id":"2312.06681","title":"Steering Llama 2 via Contrastive Activation Addition","created":"2023-12-09","cited_by_count":1085},{"id":"2211.01910","title":"Large Language Models Are Human-Level Prompt Engineers","created":"2022-11-03","cited_by_count":1045},{"id":"2308.10144","title":"ExpeL: LLM Agents Are Experiential Learners","created":"2023-08-20","cited_by_count":876},{"id":"2309.03409","title":"Large Language Models as Optimizers","created":"2023-09-07","cited_by_count":864},{"id":"2404.13076","title":"LLM Evaluators Recognize and Favor Their Own Generations","created":"2024-04-15","cited_by_count":686},{"id":"2305.14627","title":"Enabling Large Language Models to Generate Text with Citations","created":"2023-05-24","cited_by_count":595},{"id":"2309.16797","title":"Promptbreeder: Self-Referential Self-Improvement Via Prompt Evolution","created":"2023-09-28","cited_by_count":551},{"id":"2507.19457","title":"GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning","created":"2025-07-25","cited_by_count":542},{"id":"2211.08411","title":"Large Language Models Struggle to Learn Long-Tail Knowledge","created":"2022-11-15","cited_by_count":458},{"id":"2409.07429","title":"Agent Workflow Memory","created":"2024-09-11","cited_by_count":383},{"id":"2507.21509","title":"Persona Vectors: Monitoring and Controlling Character Traits in Language Models","created":"2025-07-29","cited_by_count":345},{"id":"2305.13300","title":"Adaptive Chameleon or Stubborn Sloth: Revealing the Behavior of Large Language Models in Knowledge Conflicts","created":"2023-05-22","cited_by_count":341},{"id":"2310.10158","title":"Character-LLM: A Trainable Agent for Role-Playing","created":"2023-10-16","cited_by_count":339},{"id":"2410.12784","title":"JudgeBench: A Benchmark for Evaluating LLM-based Judges","created":"2024-10-16","cited_by_count":318},{"id":"2602.12670","title":"SkillsBench: Benchmarking How Well Agent Skills Work Across Diverse Tasks","created":"2026-02-13","cited_by_count":315},{"id":"2304.09848","title":"Evaluating Verifiability in Generative Search Engines","created":"2023-04-19","cited_by_count":303},{"id":"2203.11147","title":"Teaching language models to support answers with verified quotes","created":"2022-03-21","cited_by_count":292},{"id":"2210.08726","title":"RARR: Researching and Revising What Language Models Say, Using Language Models","created":"2022-10-17","cited_by_count":287},{"id":"2406.07791","title":"Judging the Judges: A Systematic Study of Position Bias in LLM-as-a-Judge","created":"2024-06-12","cited_by_count":269},{"id":"2410.21819","title":"Self-Preference Bias in LLM-as-a-Judge","created":"2024-10-29","cited_by_count":258},{"id":"2308.07702","title":"Better Zero-Shot Reasoning with Role-Play Prompting","created":"2023-08-15","cited_by_count":223},{"id":"2404.18231","title":"From Persona to Personalization: A Survey on Role-Playing Language Agents","created":"2024-04-28","cited_by_count":212},{"id":"2310.17976","title":"InCharacter: Evaluating Personality Fidelity in Role-Playing Agents through Psychological Interviews","created":"2023-10-27","cited_by_count":179},{"id":"2312.05934","title":"Fine-Tuning or Retrieval? Comparing Knowledge Injection in LLMs","created":"2023-12-10","cited_by_count":178},{"id":"2310.00746","title":"RoleLLM: Benchmarking, Eliciting, and Enhancing Role-Playing Abilities of Large Language Models","created":"2023-10-01","cited_by_count":175},{"id":"2402.10811","title":"Quantifying the Persona Effect in LLM Simulations","created":"2024-02-16","cited_by_count":169},{"id":"2308.10168","title":"Head-to-Tail: How Knowledgeable are Large Language Models (LLMs)? A.K.A. Will LLMs Replace Knowledge Graphs?","created":"2023-08-20","cited_by_count":168},{"id":"2305.14688","title":"ExpertPrompting: Instructing Large Language Models to be Distinguished Experts","created":"2023-05-24","cited_by_count":142},{"id":"2602.12430","title":"Agent Skills for Large Language Models: Architecture, Acquisition, Security, and the Path Forward","created":"2026-02-12","cited_by_count":113},{"id":"2310.11501","title":"CoMPosT: Characterizing and Evaluating Caricature in LLM Simulations","created":"2023-10-17","cited_by_count":97},{"id":"2407.18416","title":"PersonaGym: Evaluating Persona Agents and LLMs","created":"2024-07-25","cited_by_count":97},{"id":"2603.15401","title":"SWE-Skills-Bench: Do Agent Skills Actually Help in Real-World Software Engineering?","created":"2026-03-16","cited_by_count":82},{"id":"2311.10054","title":"When \"A Helpful Assistant\" Is Not Really Helpful: Personas in System Prompts Do Not Improve Performances of Large Language Models","created":"2023-11-16","cited_by_count":53},{"id":"2605.10999","title":"SkillGen: Verified Inference-Time Agent Skill Synthesis","created":"2026-05-09","cited_by_count":36},{"id":"2502.14642","title":"How Far are LLMs from Being Our Digital Twins? A Benchmark for Persona-Based Behavior Chain Simulation","created":"2025-02-20","cited_by_count":22},{"id":"2407.02099","title":"Helpful assistant or fruitful facilitator? Investigating how personas affect language model behavior","created":"2024-07-02","cited_by_count":21},{"id":"2508.19764","title":"Principled Personas: Defining and Measuring the Intended Effects of Persona Prompting on Task Performance","created":"2025-08-27","cited_by_count":18},{"id":"2605.18693","title":"SkillGenBench: Benchmarking Skill Generation Pipelines for LLM Agents","created":"2026-05-18","cited_by_count":18},{"id":"2605.25430","title":"CODESKILL: Learning Self-Evolving Skills for Coding Agents","created":"2026-05-25","cited_by_count":12},{"id":"2603.14473","title":"AI Can Learn Scientific Taste","created":"2026-03-15","cited_by_count":11},{"id":"2603.18507","title":"Expert Personas Improve LLM Alignment but Damage Accuracy: Bootstrapping Intent-Based Persona Routing with PRISM","created":"2026-03-19","cited_by_count":9},{"id":"2606.11435","title":"Agent Skill Evaluation and Evolution: Frameworks and Benchmarks","created":"2026-06-09","cited_by_count":8},{"id":"2607.01456","title":"From Anatomy to Smells: An Empirical Study of SKILL.md in Agent Skills","created":"2026-07-01","cited_by_count":6},{"id":"2608.11888","title":"Agent Skills Can Be Harmful: An Empirical Study of Skill-Induced Failures in LLM Agents","created":"2026-08-12","cited_by_count":6},{"id":"2603.14805","title":"Knowledge Activation: AI Skills as the Institutional Knowledge Primitive for Agentic Software Development","created":"2026-03-16","cited_by_count":4},{"id":"2605.29420","title":"When Does Persona Prompting Actually Help? A Retrieval and Metric Analysis of Expert Role Injection in LLMs","created":"2026-05-28","cited_by_count":4},{"id":"2605.31264","title":"COLLEAGUE.SKILL: Automated AI Skill Generation via Expert Knowledge Distillation","created":"2026-05-29","cited_by_count":3},{"id":"2606.20631","title":"Harnessing Agent Skills: Architectural Patterns and a Reference Architecture for Skill-Mediated LLM Agents","created":"2026-05-29","cited_by_count":1}],"next_cursor":null}