{"total":141,"rows":[{"id":"2503.13657","title":"Why Do Multi-Agent LLM Systems Fail?","created":"2025-03-17","cited_by_count":604,"area":"agents"},{"id":"2501.13958","title":"A Survey of Graph Retrieval-Augmented Generation for Customized Large Language Models","created":"2025-01-21","cited_by_count":88,"area":"rag"},{"id":"2502.06855","title":"Self-Supervised Prompt Optimization","created":"2025-02-07","cited_by_count":37,"area":"lr"},{"id":"2508.03923","title":"CoAct-1: Computer-using Multi-Agent System with Coding Actions","created":"2025-08-05","cited_by_count":35,"area":null},{"id":"2502.18695","title":"Policy-as-Prompt: Rethinking Content Moderation in the Age of Large Language Models","created":"2025-02-25","cited_by_count":31,"area":"lr"},{"id":"2502.18878","title":"Learning to Generate Structured Output with Schema Reinforcement Learning","created":"2025-02-26","cited_by_count":29,"area":"lr"},{"id":"2502.12964","title":"Trust Me, I'm Wrong: LLMs Hallucinate with Certainty Despite Knowing the Answer","created":"2025-02-18","cited_by_count":27,"area":null},{"id":"2504.06969","title":"Towards LLMs Robustness to Changes in Prompt Format Styles","created":"2025-04-09","cited_by_count":21,"area":null},{"id":"2506.08184","title":"Unable to Forget: Proactive Interference Reveals Working Memory Limits in LLMs Beyond Context Length","created":"2025-06-09","cited_by_count":20,"area":null},{"id":"2502.04134","title":"The Order Effect: Investigating Prompt Sensitivity to Input Order in LLMs","created":"2025-02-06","cited_by_count":19,"area":null},{"id":"2507.17512","title":"Can One Domain Help Others? A Data-Centric Study on Multi-Domain Reasoning via Reinforcement Learning","created":"2025-07-23","cited_by_count":17,"area":"lr"},{"id":"2502.02534","title":"Adaptive Self-improvement LLM Agentic System for ML Library Development","created":"2025-02-04","cited_by_count":16,"area":"agents"},{"id":"2502.04295","title":"Beyond Prompt Content: Enhancing LLM Performance via Content-Format Integrated Prompt Optimization","created":"2025-02-06","cited_by_count":16,"area":null},{"id":"2504.01002","title":"Token embeddings violate the manifold hypothesis","created":"2025-04-01","cited_by_count":16,"area":null},{"id":"2503.06745","title":"Beyond Black-Box Benchmarking: Observability, Analytics, and Optimization of Agentic Systems","created":"2025-03-09","cited_by_count":14,"area":"agents"},{"id":"2504.11972","title":"Reassessing Extractive QA Datasets at Scale: LLM-as-a-Judge and In-Depth Analyses","created":"2025-04-16","cited_by_count":14,"area":null},{"id":"2504.04893","title":"SCAM: A Real-World Typographic Robustness Evaluation for Multimodal Foundation Models","created":"2025-04-07","cited_by_count":13,"area":"mllm"},{"id":"2509.03986","title":"Promptception: How Sensitive Are Large Multimodal Models to Prompts?","created":"2025-09-04","cited_by_count":13,"area":"mllm"},{"id":"2510.10052","title":"Think Twice to See More: Iterative Visual Reasoning in Medical VLMs","created":"2025-10-11","cited_by_count":13,"area":"lr"},{"id":"2501.17178","title":"Tuning LLM Judge Design Decisions for 1/1000 of the Cost","created":"2025-01-24","cited_by_count":11,"area":null},{"id":"2505.11604","title":"Talk to Your Slides: High-Efficiency Slide Editing via Language-Driven Structured Data Manipulation","created":"2025-05-16","cited_by_count":11,"area":null},{"id":"2503.05587","title":"Quantifying and Improving the Robustness of Retrieval-Augmented Language Models Against Spurious Features in Grounding Data","created":"2025-03-07","cited_by_count":10,"area":"rag"},{"id":"2503.07329","title":"Assessing the Macro and Micro Effects of Random Seeds on Fine-Tuning Large Language Models","created":"2025-03-10","cited_by_count":10,"area":null},{"id":"2506.00751","title":"Alignment Revisited: Are Large Language Models Consistent in Stated and Revealed Preferences?","created":"2025-05-31","cited_by_count":10,"area":"alignment"},{"id":"2502.00313","title":"Distributive Fairness in Large Language Models: Evaluating Alignment with Human Values","created":"2025-02-01","cited_by_count":9,"area":"alignment"},{"id":"2505.12402","title":"Automated Profile Inference with Language Model Agents","created":"2025-05-18","cited_by_count":9,"area":"agents"},{"id":"2510.03595","title":"Decoupling Task-Solving and Output Formatting in LLM Generation","created":"2025-10-04","cited_by_count":9,"area":"lr"},{"id":"2502.01179","title":"Joint Localization and Activation Editing for Low-Resource Fine-Tuning","created":"2025-02-03","cited_by_count":8,"area":null},{"id":"2505.15818","title":"InstructSAM: A Training-Free Framework for Instruction-Oriented Remote Sensing Object Recognition","created":"2025-05-21","cited_by_count":8,"area":null},{"id":"2506.00688","title":"Existing Large Language Model Unlearning Evaluations Are Inconclusive","created":"2025-05-31","cited_by_count":8,"area":"safety"},{"id":"2509.14404","title":"A Taxonomy of Prompt Defects in LLM Systems","created":"2025-09-17","cited_by_count":8,"area":null},{"id":"2605.03353","title":"SkCC: Portable and Secure Skill Compilation for Cross-Framework LLM Agents","created":"2026-05-05","cited_by_count":8,"area":"agents"},{"id":"2505.19514","title":"SIPDO: Closed-Loop Prompt Optimization via Synthetic Data Feedback","created":"2025-05-26","cited_by_count":7,"area":"synth"},{"id":"2509.19841","title":"ThinkFake: Reasoning in Multimodal Large Language Models for AI-Generated Image Detection","created":"2025-09-24","cited_by_count":7,"area":"lr"},{"id":"2507.02954","title":"Advanced Financial Reasoning at Scale: A Comprehensive Evaluation of Large Language Models on CFA Level III","created":"2025-06-29","cited_by_count":6,"area":"lr"},{"id":"2505.12837","title":"The Hidden Structure -- Improving Legal Document Understanding Through Explicit Text Formatting","created":"2025-05-19","cited_by_count":5,"area":null},{"id":"2505.21362","title":"Evaluating LLM Adaptation to Sociodemographic Factors: User Profile vs. Dialogue History","created":"2025-05-27","cited_by_count":5,"area":null},{"id":"2507.12841","title":"AnyCap Project: A Unified Framework, Dataset, and Benchmark for Controllable Omni-modal Captioning","created":"2025-07-17","cited_by_count":5,"area":null},{"id":"2510.19806","title":"The Art of Asking: Multilingual Prompt Optimization for Synthetic Data","created":"2025-10-22","cited_by_count":5,"area":"synth"},{"id":"2602.05447","title":"Structured Context Engineering for File-Native Agentic Systems: Evaluating Schema Accuracy, Format Effectiveness, and Multi-File Navigation at Scale","created":"2026-02-05","cited_by_count":5,"area":"agents"},{"id":"2502.10760","title":"Why is prompting hard? Understanding prompts on binary sequence predictors","created":"2025-02-15","cited_by_count":4,"area":null},{"id":"2510.14773","title":"Finding Answers in Thought Matters: Revisiting Evaluation on Large Language Models with Reasoning","created":"2025-10-16","cited_by_count":4,"area":"lr"},{"id":"2511.20284","title":"Can LLMs Make (Personalized) Access Control Decisions?","created":"2025-11-25","cited_by_count":4,"area":null},{"id":"2512.08606","title":"Decoupling Template Bias in CLIP: Harnessing Empty Prompts for Enhanced Few-Shot Learning","created":"2025-12-09","cited_by_count":4,"area":null},{"id":"2602.21223","title":"Measuring Pragmatic Influence in Large Language Model Instructions","created":"2026-02-02","cited_by_count":4,"area":null},{"id":"2412.18011","title":"StructTest: Benchmarking LLMs' Reasoning through Compositional Structured Outputs","created":"2024-12-23","cited_by_count":3,"area":"lr"},{"id":"2504.10786","title":"Visual Language Models show widespread visual deficits on neuropsychological tests","created":"2025-04-15","cited_by_count":3,"area":"lr"},{"id":"2508.15815","title":"User-Assistant Bias in LLMs","created":"2025-08-16","cited_by_count":3,"area":null},{"id":"2510.06931","title":"Textual interpretation of transient image classifications from large language models","created":"2025-10-08","cited_by_count":3,"area":null},{"id":"2510.08413","title":"Prompts Generalize with Low Data: Non-vacuous Generalization Bounds for Optimizing Prompts with More Informative Priors","created":"2025-10-09","cited_by_count":3,"area":null},{"id":"2601.21339","title":"Within-Model vs Between-Prompt Variability in Large Language Models for Creative Tasks","created":"2026-01-29","cited_by_count":3,"area":null},{"id":"2604.14930","title":"IE as Cache: Information Extraction Enhanced Agentic Reasoning","created":"2026-04-16","cited_by_count":3,"area":"lr"},{"id":"2606.05632","title":"Evaluation of LLMs for Mathematical Formalization in Lean","created":"2026-06-04","cited_by_count":3,"area":null},{"id":"2502.12859","title":"PAFT: Prompt-Agnostic Fine-Tuning","created":"2025-02-18","cited_by_count":2,"area":null},{"id":"2502.15723","title":"Balancing Content Size in RAG-Text2SQL System","created":"2025-01-28","cited_by_count":2,"area":null},{"id":"2502.18650","title":"Single- vs. Dual-Prompt Dialogue Generation with LLMs for Job Interviews in Human Resources","created":"2025-02-25","cited_by_count":2,"area":null},{"id":"2504.15918","title":"Ask2Loc: Learning to Locate Instructional Visual Answers by Asking Questions","created":"2025-04-22","cited_by_count":2,"area":null},{"id":"2505.12135","title":"LLM-BabyBench: Can Language Models Plan in Worlds They Can Simulate?","created":"2025-05-17","cited_by_count":2,"area":"agents"},{"id":"2505.12592","title":"PromptPrism: A Linguistically-Inspired Taxonomy for Prompts","created":"2025-05-19","cited_by_count":2,"area":null},{"id":"2505.17131","title":"Relative Bias: A Comparative Framework for Quantifying Bias in LLMs","created":"2025-05-22","cited_by_count":2,"area":null},{"id":"2508.21452","title":"From Canonical to Complex: Benchmarking LLM Capabilities in Undergraduate Thermodynamics","created":"2025-08-29","cited_by_count":2,"area":null},{"id":"2509.01182","title":"Question-to-Knowledge (Q2K): Multi-Agent Generation of Inspectable Facts for Product Mapping","created":"2025-09-01","cited_by_count":2,"area":null},{"id":"2510.00880","title":"HalluGuard: Evidence-Grounded Small Reasoning Models to Mitigate Hallucinations in Retrieval-Augmented Generation","created":"2025-10-01","cited_by_count":2,"area":"lr"},{"id":"2510.08524","title":"Efficient Prompt Optimisation for Legal Text Classification with Proxy Prompt Evaluator","created":"2025-10-09","cited_by_count":2,"area":null},{"id":"2510.12637","title":"COSTAR-A: A prompting framework for enhancing Large Language Model performance on Point-of-View questions","created":"2025-10-14","cited_by_count":2,"area":null},{"id":"2512.14805","title":"Sharing State Between Prompts and Programs","created":"2025-12-16","cited_by_count":2,"area":null},{"id":"2512.23982","title":"Coding With AI: From a Reflection on Industrial Practices to Future Computer Science and Software Engineering Education","created":"2025-12-30","cited_by_count":2,"area":"agents"},{"id":"2601.04716","title":"Identifying and Mitigating Bottlenecks in Role-Playing Agents: A Systematic Study of Disentangling Character Profile Axes","created":"2026-01-08","cited_by_count":2,"area":"agents"},{"id":"2603.29678","title":"View-oriented Conversation Compiler for Agent Trace Analysis","created":"2026-03-31","cited_by_count":2,"area":null},{"id":"2605.15393","title":"LPDS: Evaluating LLM Robustness Through Logic-Preserving Difficulty Scaling","created":"2026-05-14","cited_by_count":2,"area":null},{"id":"2605.30646","title":"Same Patient, Different Words, Different Diagnosis? Evaluating Semantic Stability in Clinical LLMs","created":"2026-05-28","cited_by_count":2,"area":null},{"id":"2607.12962","title":"Form, Not Content? A Preregistered, Placebo-Controlled Evaluation of Learned Error-Conditioned Self-Repair Through Prompts and Weights in Frozen Small Code Models","created":"2026-07-14","cited_by_count":2,"area":null},{"id":"2412.17189","title":"Talking with Tables for Better LLM Factual Data Interactions","created":"2024-12-22","cited_by_count":1,"area":null},{"id":"2504.21850","title":"Visual Compositional Tuning","created":"2025-04-30","cited_by_count":1,"area":null},{"id":"2506.23133","title":"Format-Adapter: Improving Reasoning Capability of LLMs by Adapting Suitable Format","created":"2025-06-29","cited_by_count":1,"area":"lr"},{"id":"2508.13948","title":"Prompt Orchestration Markup Language","created":"2025-08-19","cited_by_count":1,"area":null},{"id":"2509.06307","title":"Can AI Make Energy Retrofit Decisions? An Evaluation of Large Language Models","created":"2025-09-08","cited_by_count":1,"area":null},{"id":"2509.13680","title":"Prompt Stability in Code LLMs: Measuring Sensitivity across Emotion- and Personality-Driven Variations","created":"2025-09-17","cited_by_count":1,"area":null},{"id":"2510.01831","title":"Syntactic Blind Spots: How Misalignment Leads to LLMs Mathematical Errors","created":"2025-10-02","cited_by_count":1,"area":null},{"id":"2510.16635","title":"MA-SAPO: Multi-Agent Reasoning for Score-Aware Prompt Optimization","created":"2025-10-18","cited_by_count":1,"area":"lr"},{"id":"2510.26193","title":"RCScore: Quantifying Response Consistency in Large Language Models","created":"2025-10-30","cited_by_count":1,"area":null},{"id":"2511.22341","title":"Unexplored flaws in multiple-choice VQA make benchmarking unreliable","created":"2025-11-27","cited_by_count":1,"area":null},{"id":"2512.08646","title":"QSTN: A Modular Framework for Robust Questionnaire Inference with Large Language Models","created":"2025-12-09","cited_by_count":1,"area":null},{"id":"2512.11984","title":"Evidence-Driven Decision Support for AI Model Selection in Research Software Engineering","created":"2025-12-12","cited_by_count":1,"area":null},{"id":"2601.04940","title":"CurricuLLM: Designing Personalized and Workforce-Aligned Cybersecurity Curricula Using Fine-Tuned LLMs","created":"2026-01-08","cited_by_count":1,"area":null},{"id":"2601.07790","title":"Benchmarking Small Language Models and Small Reasoning Language Models on System Log Severity Classification","created":"2026-01-12","cited_by_count":1,"area":"lr"},{"id":"2602.06384","title":"FMBench: Adaptive Large Language Model Output Formatting","created":"2026-02-06","cited_by_count":1,"area":null},{"id":"2603.27626","title":"Umwelt Engineering: Designing the Cognitive Worlds of Linguistic Agents","created":"2026-03-29","cited_by_count":1,"area":"agents"},{"id":"2604.16420","title":"Breaking Validity-Induced Boundaries to Expand Algorithm Search Space: A Two-Stage AST-Based Operator for LLM-Driven Automated Heuristic Evolution","created":"2026-04-03","cited_by_count":1,"area":null},{"id":"2605.23189","title":"Empirical Bayes Conformal Prediction for Vision and Language Models","created":"2026-05-22","cited_by_count":1,"area":null},{"id":"2606.04109","title":"Discourse-Role Labels as Presentation-Time Variables for Context Use in Language Models","created":"2026-06-02","cited_by_count":1,"area":null},{"id":"2606.20978","title":"How Should Agents Read Demonstrations? Hierarchical Structure Beats Flat Action Logs","created":"2026-06-18","cited_by_count":1,"area":"agents"},{"id":"2607.19257","title":"Prompt Design at Scale: How Format, Instruction Count, and Context Length Shape Instruction Adherence and Hallucination in Large Language Models","created":"2026-07-21","cited_by_count":1,"area":null},{"id":"2609.34187","title":"LLMs are not stochastic parrots: Evidence for meaning-mediated abstraction from conlang-like tasks","created":"2026-09-28","cited_by_count":1,"area":null},{"id":"2503.12206","title":"TLAC: Two-stage LMM Augmented CLIP for Zero-Shot Classification","created":"2025-03-15","cited_by_count":0,"area":null},{"id":"2503.16868","title":"Joint Extraction Matters: Prompt-Based Visual Question Answering for Multi-Field Document Information Extraction","created":"2025-03-21","cited_by_count":0,"area":null},{"id":"2504.05764","title":"Layer-Aware Embedding Fusion for LLMs in Text Classifications","created":"2025-04-08","cited_by_count":0,"area":null},{"id":"2506.00622","title":"Improving Dialogue State Tracking through Combinatorial Search for In-Context Examples","created":"2025-05-31","cited_by_count":0,"area":null},{"id":"2506.00856","title":"Can AI Master Econometrics? Evidence from Econometrics AI Agent on Expert-Level Tasks","created":"2025-06-01","cited_by_count":0,"area":"agents"},{"id":"2508.21389","title":"AllSummedUp: un framework open-source pour comparer les metriques d'evaluation de resume","created":"2025-08-29","cited_by_count":0,"area":null}],"next_cursor":"100"}