{"total":170,"rows":[{"id":"2509.09674","title":"SimpleVLA-RL: Scaling VLA Training via Reinforcement Learning","created":"2025-09-11","cited_by_count":151,"area":"vla"},{"id":"2507.23370","title":"Trae Agent: An LLM-based Agent for Software Engineering with Test-time Scaling","created":"2025-07-31","cited_by_count":94,"area":"lr"},{"id":"2504.07086","title":"A Sober Look at Progress in Language Model Reasoning: Pitfalls and Paths to Reproducibility","created":"2025-04-09","cited_by_count":93,"area":"lr"},{"id":"2408.05109","title":"A Survey of Text-to-SQL in the Era of LLMs: Where are we, and where are we going?","created":"2024-08-09","cited_by_count":56,"area":null},{"id":"2509.14279","title":"Towards Robust Agentic CUDA Kernel Benchmarking, Verification, and Optimization","created":"2025-09-16","cited_by_count":56,"area":"lr"},{"id":"2406.15673","title":"Large Language Models have Intrinsic Self-Correction Ability","created":"2024-06-21","cited_by_count":46,"area":"lr"},{"id":"2505.11484","title":"SoftCoT++: Test-Time Scaling with Soft Chain-of-Thought Reasoning","created":"2025-05-16","cited_by_count":41,"area":"lr"},{"id":"2506.07295","title":"Exploring the Impact of Temperature on Large Language Models:Hot or Cold?","created":"2025-06-08","cited_by_count":40,"area":null},{"id":"2405.06682","title":"Self-Reflection in LLM Agents: Effects on Problem-Solving Performance","created":"2024-05-05","cited_by_count":39,"area":"agents"},{"id":"2502.05234","title":"Optimizing Temperature for Language Models with Multi-Sample Inference","created":"2025-02-07","cited_by_count":33,"area":"lr"},{"id":"2405.19616","title":"Easy Problems That LLMs Get Wrong","created":"2024-05-30","cited_by_count":30,"area":"lr"},{"id":"2403.09732","title":"PET-SQL: A Prompt-Enhanced Two-Round Refinement of Text-to-SQL with Cross-consistency","created":"2024-03-13","cited_by_count":27,"area":null},{"id":"2503.21411","title":"Exploring the Roles of Large Language Models in Reshaping Transportation Systems: A Survey, Framework, and Roadmap","created":"2025-03-27","cited_by_count":26,"area":null},{"id":"2506.17871","title":"LLM Probability Concentration: How Alignment Shrinks the Generative Horizon","created":"2025-06-22","cited_by_count":26,"area":"alignment"},{"id":"2502.20339","title":"Thinking Slow, Fast: Scaling Inference Compute with Distilled Reasoners","created":"2025-02-27","cited_by_count":22,"area":"lr"},{"id":"2503.17439","title":"LEMMA: Learning from Errors for MatheMatical Advancement in LLMs","created":"2025-03-21","cited_by_count":21,"area":"lr"},{"id":"2504.10449","title":"M1: Towards Scalable Test-Time Compute with Mamba Reasoning Models","created":"2025-04-14","cited_by_count":21,"area":"lr"},{"id":"2507.02778","title":"Self-Correction Bench: Uncovering and Addressing the Self-Correction Blind Spot in Large Language Models","created":"2025-07-03","cited_by_count":20,"area":"lr"},{"id":"2502.05196","title":"LLMs Provide Unstable Answers to Legal Questions","created":"2025-01-28","cited_by_count":19,"area":null},{"id":"2510.01218","title":"Control the Temperature: Selective Sampling for Diverse and High-Quality LLM Outputs","created":"2025-09-20","cited_by_count":15,"area":null},{"id":"2503.20527","title":"StableToolBench-MirrorAPI: Modeling Tool Environments as Mirrors of 7,000+ Real-World APIs","created":"2025-03-26","cited_by_count":14,"area":"agents"},{"id":"2511.00432","title":"G2: Guided Generation for Enhanced Output Diversity in LLMs","created":"2025-11-01","cited_by_count":14,"area":null},{"id":"2410.11272","title":"Cognitive Overload Attack:Prompt Injection for Long Context","created":"2024-10-15","cited_by_count":13,"area":"safety"},{"id":"2505.19475","title":"Continuous Self-Improvement of Large Language Models by Test-time Training with Verifier-Driven Sample Selection","created":"2025-05-26","cited_by_count":13,"area":"synth"},{"id":"2404.00486","title":"Dialectical Alignment: Resolving the Tension of 3H and Security Threats of LLMs","created":"2024-03-30","cited_by_count":11,"area":"alignment"},{"id":"2502.07508","title":"Enhance-A-Video: Better Generated Video for Free","created":"2025-02-11","cited_by_count":11,"area":null},{"id":"2502.19830","title":"Revisiting Self-Consistency from Dynamic Distributional Alignment Perspective on Answer Aggregation","created":"2025-02-27","cited_by_count":11,"area":"lr"},{"id":"2503.00691","title":"How Diversely Can Language Models Solve Problems? Exploring the Algorithmic Diversity of Model-Generated Code","created":"2025-03-02","cited_by_count":11,"area":null},{"id":"2607.04686","title":"ToolFailBench: Diagnosing Tool-Use Failures in LLM Agents","created":"2026-07-06","cited_by_count":11,"area":"agents"},{"id":"2510.05251","title":"Let it Calm: Exploratory Annealed Decoding for Verifiable Reinforcement Learning","created":"2025-10-06","cited_by_count":10,"area":"lr"},{"id":"2604.11581","title":"Hidden Measurement Error in LLM Pipelines Distorts Annotation, Evaluation, and Benchmarking","created":"2026-04-13","cited_by_count":10,"area":null},{"id":"2410.21359","title":"Can Machines Think Like Humans? A Behavioral Evaluation of LLM Agents in Dictator Games","created":"2024-10-28","cited_by_count":9,"area":"lr"},{"id":"2411.03495","title":"Automatic Generation of Question Hints for Mathematics Problems using Large Language Models in Educational Technology","created":"2024-11-05","cited_by_count":9,"area":null},{"id":"2506.20544","title":"When Life Gives You Samples: The Benefits of Scaling up Inference Compute for Multilingual LLMs","created":"2025-06-25","cited_by_count":9,"area":"lr"},{"id":"2506.23601","title":"Semantic-guided Diverse Decoding for Large Language Model","created":"2025-06-30","cited_by_count":9,"area":null},{"id":"2510.10278","title":"Simulating Viva Voce Examinations to Evaluate Clinical Reasoning in Large Language Models","created":"2025-10-11","cited_by_count":9,"area":"lr"},{"id":"2408.08841","title":"FLEXTAF: Enhancing Table Reasoning with Flexible Tabular Formats","created":"2024-08-16","cited_by_count":8,"area":"lr"},{"id":"2412.00868","title":"Quantifying perturbation impacts for large language models","created":"2024-12-01","cited_by_count":8,"area":null},{"id":"2506.07947","title":"Statistical Hypothesis Testing for Auditing Robustness in Language Models","created":"2025-06-09","cited_by_count":8,"area":null},{"id":"2508.00033","title":"GPT-4.1 Sets the Standard in Automated Experiment Design Using Novel Python Libraries","created":"2025-07-30","cited_by_count":8,"area":null},{"id":"2601.21895","title":"Learn-to-Distance: Distance Learning for Detecting LLM-Generated Text","created":"2026-01-29","cited_by_count":8,"area":null},{"id":"2506.14276","title":"Don't throw the baby out with the bathwater: How and why deep learning for ARC","created":"2025-06-17","cited_by_count":7,"area":null},{"id":"2511.15593","title":"What Does It Take to Be a Good AI Research Agent? Studying the Role of Ideation Diversity","created":"2025-11-19","cited_by_count":7,"area":"agents"},{"id":"2602.13540","title":"On Calibration of Large Language Models: From Response To Capability","created":"2026-02-14","cited_by_count":7,"area":null},{"id":"2603.14893","title":"LLMs as Signal Detectors: Sensitivity, Bias, and the Temperature-Criterion Analogy","created":"2026-03-16","cited_by_count":7,"area":null},{"id":"2408.11879","title":"Beyond Labels: Aligning Large Language Models with Human-like Reasoning","created":"2024-08-20","cited_by_count":6,"area":"lr"},{"id":"2410.20199","title":"Rethinking the Uncertainty: A Critical Review and Analysis in the Era of Large Language Models","created":"2024-10-26","cited_by_count":6,"area":"lr"},{"id":"2504.12320","title":"Has the Creativity of Large-Language Models peaked? An analysis of inter- and intra-LLM variability","created":"2025-04-10","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":"2506.19592","title":"Adaptive Domain Modeling with Language Models: A Multi-Agent Approach to Task Planning","created":"2025-06-24","cited_by_count":6,"area":"agents"},{"id":"2508.12040","title":"Mind the Generation Process: Fine-Grained Confidence Estimation During LLM Generation","created":"2025-08-16","cited_by_count":6,"area":null},{"id":"2509.02330","title":"ReCode: Improving LLM-based Code Repair with Fine-Grained Retrieval-Augmented Generation","created":"2025-09-02","cited_by_count":6,"area":"rag"},{"id":"2509.12434","title":"Building Coding Agents via Entropy-Enhanced Multi-Turn Preference Optimization","created":"2025-09-15","cited_by_count":6,"area":"lr"},{"id":"2602.02555","title":"Learning to Explore with Parameter-Space Noise: A Deep Dive into Parameter-Space Noise for Reinforcement Learning with Verifiable Rewards","created":"2026-01-30","cited_by_count":6,"area":"lr"},{"id":"2411.13244","title":"Leveraging Prior Experience: An Expandable Auxiliary Knowledge Base for Text-to-SQL","created":"2024-11-20","cited_by_count":5,"area":null},{"id":"2501.16356","title":"Evaluating Binary Decision Biases in Large Language Models: Implications for Fair Agent-Based Financial Simulations","created":"2025-01-20","cited_by_count":5,"area":"agents"},{"id":"2504.16121","title":"LegalRAG: A Hybrid RAG System for Multilingual Legal Information Retrieval","created":"2025-04-19","cited_by_count":5,"area":"rag"},{"id":"2505.17202","title":"CHART-6: Human-Centered Evaluation of Data Visualization Understanding in Vision-Language Models","created":"2025-05-22","cited_by_count":5,"area":"mllm"},{"id":"2506.12012","title":"Tracing LLM Reasoning Processes with Strategic Games: A Framework for Planning, Revision, and Resource-Constrained Decision Making","created":"2025-06-13","cited_by_count":5,"area":"lr"},{"id":"2506.14092","title":"Fragile Preferences: A Deep Dive Into Order Effects in Large Language Models","created":"2025-06-17","cited_by_count":5,"area":null},{"id":"2507.02226","title":"DecoRTL: A Run-time Decoding Framework for RTL Code Generation with LLMs","created":"2025-07-03","cited_by_count":5,"area":null},{"id":"2509.08480","title":"Acquiescence Bias in Large Language Models","created":"2025-09-10","cited_by_count":5,"area":null},{"id":"2511.12693","title":"HEDGE: Hallucination Estimation via Dense Geometric Entropy for VQA with Vision-Language Models","created":"2025-11-16","cited_by_count":5,"area":"mllm"},{"id":"2512.23712","title":"STED and Consistency Scoring: A Framework for Evaluating LLM Structured Output Reliability","created":"2025-11-27","cited_by_count":5,"area":null},{"id":"2601.19969","title":"E2HiL: Entropy-Guided Sample Selection for Efficient Real-World Human-in-the-Loop Reinforcement Learning","created":"2026-01-27","cited_by_count":5,"area":"deeprl"},{"id":"2411.09255","title":"DAHL: Domain-specific Automated Hallucination Evaluation of Long-Form Text through a Benchmark Dataset in Biomedicine","created":"2024-11-14","cited_by_count":4,"area":null},{"id":"2501.09126","title":"Augmenting Human-Annotated Training Data with Large Language Model Generation and Distillation in Open-Response Assessment","created":"2025-01-15","cited_by_count":4,"area":null},{"id":"2502.20689","title":"WiseMind: a knowledge-guided multi-agent framework for accurate and empathetic psychiatric diagnosis","created":"2025-02-28","cited_by_count":4,"area":"agents"},{"id":"2503.03170","title":"AttackSeqBench: Benchmarking the Capabilities of LLMs for Attack Sequences Understanding","created":"2025-03-05","cited_by_count":4,"area":null},{"id":"2503.20036","title":"Agents in the Sandbox: End-to-End Crash Bug Reproduction for Minecraft","created":"2025-03-25","cited_by_count":4,"area":"agents"},{"id":"2505.03988","title":"Can Large Language Models Predict Parallel Code Performance?","created":"2025-05-06","cited_by_count":4,"area":null},{"id":"2505.13672","title":"A*-Decoding: Token-Efficient Inference Scaling","created":"2025-05-19","cited_by_count":4,"area":"lr"},{"id":"2505.23838","title":"Exploring the Landscape of Text-to-SQL with Large Language Models: Progresses, Challenges and Opportunities","created":"2025-05-28","cited_by_count":4,"area":null},{"id":"2508.20186","title":"AI Propaganda factories with language models","created":"2025-08-27","cited_by_count":4,"area":null},{"id":"2512.12066","title":"The Instability of Safety: How Random Seeds and Temperature Expose Inconsistent LLM Refusal Behavior","created":"2025-12-12","cited_by_count":4,"area":"alignment"},{"id":"2410.05292","title":"CaLMFlow: Volterra Flow Matching using Causal Language Models","created":"2024-10-03","cited_by_count":3,"area":"diffusion"},{"id":"2501.16309","title":"Evaluating The Performance of Using Large Language Models to Automate Summarization of CT Simulation Orders in Radiation Oncology","created":"2025-01-27","cited_by_count":3,"area":null},{"id":"2502.18487","title":"AuPair: Golden Example Pairs for Code Repair","created":"2025-02-12","cited_by_count":3,"area":"lr"},{"id":"2509.14899","title":"CARGO: A Framework for Confidence-Aware Routing of Large Language Models","created":"2025-09-18","cited_by_count":3,"area":null},{"id":"2510.01235","title":"Automated Extraction of Material Properties using LLM-based AI Agents","created":"2025-09-23","cited_by_count":3,"area":"agents"},{"id":"2510.18908","title":"Improving Topic Modeling of Social Media Short Texts with Rephrasing: A Case Study of COVID-19 Related Tweets","created":"2025-10-21","cited_by_count":3,"area":null},{"id":"2602.17445","title":"ABCD: All Biases Come Disguised","created":"2026-02-19","cited_by_count":3,"area":null},{"id":"2603.28304","title":"The Necessity of Setting Temperature in LLM-as-a-Judge","created":"2026-03-30","cited_by_count":3,"area":null},{"id":"2410.08058","title":"Closing the Loop: Learning to Generate Writing Feedback via Language Model Simulated Student Revisions","created":"2024-10-10","cited_by_count":2,"area":null},{"id":"2501.05601","title":"Exploring Large Language Models for Translating Romanian Computational Problems into English","created":"2025-01-09","cited_by_count":2,"area":null},{"id":"2505.10013","title":"DIF: A Framework for Benchmarking and Verifying Implicit Bias in LLMs","created":"2025-05-15","cited_by_count":2,"area":null},{"id":"2507.15157","title":"Can LLMs Generate User Stories and Assess Their Quality?","created":"2025-07-20","cited_by_count":2,"area":null},{"id":"2507.15715","title":"From Queries to Criteria: Understanding How Astronomers Evaluate LLMs","created":"2025-07-21","cited_by_count":2,"area":null},{"id":"2511.03023","title":"PublicAgent: Multi-Agent Design Principles From an LLM-Based Open Data Analysis Framework","created":"2025-11-04","cited_by_count":2,"area":"agents"},{"id":"2512.12858","title":"Information-Consistent Language Model Recommendations through Group Relative Policy Optimization","created":"2025-12-14","cited_by_count":2,"area":"lr"},{"id":"2512.21635","title":"Heaven-Sent or Hell-Bent? Benchmarking the Intelligence and Defectiveness of LLM Hallucinations","created":"2025-12-25","cited_by_count":2,"area":null},{"id":"2602.16811","title":"Evaluating Monolingual and Multilingual Large Language Models for Greek Question Answering: The DemosQA Benchmark","created":"2026-02-18","cited_by_count":2,"area":null},{"id":"2602.17691","title":"Tethered Reasoning: Decoupling Entropy from Hallucination in Quantized LLMs via Manifold Steering","created":"2026-02-06","cited_by_count":2,"area":"lr"},{"id":"2605.21071","title":"Fine-grained Claim-level RAG Benchmark for Law","created":"2026-05-20","cited_by_count":2,"area":"rag"},{"id":"2605.25773","title":"Efficient Benchmarking Is Just Feature Selection and Multiple Regression","created":"2026-05-25","cited_by_count":2,"area":null},{"id":"2606.27687","title":"Mitigating LLM-based p-Hacking by Preregistering for the Next LLM","created":"2026-06-26","cited_by_count":2,"area":null},{"id":"2608.29988","title":"AutoCRAT: Within-trajectory Joint Control of Stochasticity and Compute for LLM Reasoning","created":"2026-08-30","cited_by_count":2,"area":"lr"},{"id":"2609.04047","title":"The Dice Roll Method: A Standardized Protocol for Repeated-Query Auditing of Large Language Model Brand Recommendations","created":"2026-09-03","cited_by_count":2,"area":null},{"id":"2411.07441","title":"Automatically Detecting Online Deceptive Patterns","created":"2024-11-11","cited_by_count":1,"area":null},{"id":"2504.08779","title":"Can AI Master Construction Management (CM)? Benchmarking State-of-the-Art Large Language Models on CM Certification Exams","created":"2025-04-04","cited_by_count":1,"area":null}],"next_cursor":"100"}