{"total":105,"rows":[{"id":"2511.18850","title":"Cognitive Alpha Mining via LLM-Driven Code-Based Evolution","created":"2025-11-24","cited_by_count":15,"area":null},{"id":"2602.08235","title":"When Benign Inputs Lead to Severe Harms: Eliciting Unsafe Unintended Behaviors of Computer-Use Agents","created":"2026-02-09","cited_by_count":14,"area":"agents"},{"id":"2605.10913","title":"Shepherd: Enabling Programmable Meta-Agents via Reversible Agentic Execution Traces","created":"2026-05-11","cited_by_count":12,"area":"agents"},{"id":"2608.19197","title":"SPADE: Self-Play in Adaptive Synthetic Executable Environments","created":"2026-08-19","cited_by_count":12,"area":"synth"},{"id":"2604.06543","title":"The Illusion of Stochasticity in LLMs","created":"2026-04-08","cited_by_count":9,"area":null},{"id":"2603.09970","title":"CREATE: Testing LLMs for Associative Creativity","created":"2026-03-10","cited_by_count":7,"area":null},{"id":"2606.05622","title":"AdaPlanBench: Evaluating Adaptive Planning in Large Language Model Agents under World and User Constraints","created":"2026-06-04","cited_by_count":7,"area":"agents"},{"id":"2601.11004","title":"NOVA: NOise-aware Verbal Confidence CAlibration for Robust Large Language Models in RAG Systems","created":"2026-01-16","cited_by_count":6,"area":"rag"},{"id":"2602.03429","title":"DiscoverLLM: From Executing Intents to Discovering Them","created":"2026-02-03","cited_by_count":6,"area":null},{"id":"2603.24844","title":"Reaching Beyond the Mode: RL for Distributional Reasoning in Language Models","created":"2026-03-25","cited_by_count":6,"area":"lr"},{"id":"2604.05306","title":"LLMs Should Express Uncertainty Explicitly","created":"2026-04-07","cited_by_count":6,"area":null},{"id":"2604.26965","title":"The Impact of AI-Generated Text on the Internet","created":"2026-04-14","cited_by_count":6,"area":null},{"id":"2605.11258","title":"Unlocking LLM Creativity in Science through Analogical Reasoning","created":"2026-05-11","cited_by_count":6,"area":"lr"},{"id":"2608.12253","title":"One Frozen Simulator Is Not Enough: Simulator Collapse in Multi-Agent RL","created":"2026-08-12","cited_by_count":6,"area":"agents"},{"id":"2604.03058","title":"Verbalizing LLMs' assumptions to explain and control sycophancy","created":"2026-04-03","cited_by_count":5,"area":null},{"id":"2605.09995","title":"Annotations Mitigate Post-Training Mode Collapse","created":"2026-05-11","cited_by_count":5,"area":null},{"id":"2511.10453","title":"Reasoning about Intent for Ambiguous Requests","created":"2025-11-13","cited_by_count":4,"area":"lr"},{"id":"2512.20845","title":"MAR:Multi-Agent Reflexion Improves Reasoning Abilities in LLMs","created":"2025-12-23","cited_by_count":4,"area":"lr"},{"id":"2602.16162","title":"LLMs Exhibit Significantly Lower Uncertainty in Creative Writing Than Professional Writers","created":"2026-02-18","cited_by_count":4,"area":null},{"id":"2603.24124","title":"The Alignment Tax: Response Homogenization in Aligned LLMs and Its Implications for Uncertainty Estimation","created":"2026-03-25","cited_by_count":4,"area":"alignment"},{"id":"2605.02815","title":"FlexSQL: Flexible Exploration and Execution Make Better Text-to-SQL Agents","created":"2026-05-04","cited_by_count":4,"area":null},{"id":"2511.14275","title":"Let the Model Distribute Its Doubt: Confidence Estimation through Verbalized Probability Distribution","created":"2025-11-18","cited_by_count":3,"area":null},{"id":"2603.02479","title":"PRISM: Pushing the Frontier of Deep Think via Process Reward Model-Guided Inference","created":"2026-03-03","cited_by_count":3,"area":"lr"},{"id":"2604.18607","title":"TurboEvolve: Towards Fast and Robust LLM-Driven Program Evolution","created":"2026-04-12","cited_by_count":3,"area":null},{"id":"2606.18284","title":"Breaking the Solver Bottleneck: Training Task Generators at the Learnable Frontier","created":"2026-06-10","cited_by_count":3,"area":"lr"},{"id":"2609.02797","title":"Dutch Books for Language Models","created":"2026-09-02","cited_by_count":3,"area":null},{"id":"2601.05882","title":"An Empirical Study on Preference Tuning Generalization and Diversity Under Domain Shift","created":"2026-01-09","cited_by_count":2,"area":"alignment"},{"id":"2602.18292","title":"Decoding as Optimisation on the Probability Simplex: From Top-K to Top-P (Nucleus) to Best-of-K Samplers","created":"2026-02-20","cited_by_count":2,"area":null},{"id":"2603.18363","title":"PowerFlow: Unlocking the Dual Nature of LLMs via Principled Distribution Matching","created":"2026-03-19","cited_by_count":2,"area":null},{"id":"2603.19519","title":"Inducing Sustained Creativity and Diversity in Large Language Models","created":"2026-03-19","cited_by_count":2,"area":null},{"id":"2604.02319","title":"No Single Best Model for Diversity: Learning a Router for Sample Diversity","created":"2026-04-02","cited_by_count":2,"area":null},{"id":"2605.11128","title":"Sampling More, Getting Less: Calibration is the Diversity Bottleneck in LLMs","created":"2026-05-11","cited_by_count":2,"area":null},{"id":"2605.25358","title":"AI-Associated Lexical Shifts Across 34 Languages: Cross-Lingual Convergence and Diachronic Uptake in News Writing","created":"2026-05-25","cited_by_count":2,"area":null},{"id":"2605.25680","title":"Simulating Human Memory with Language Models","created":"2026-05-25","cited_by_count":2,"area":null},{"id":"2606.06667","title":"The Piggyback Hypothesis of Generalization: Explaining and Mitigating Emergent Misalignment","created":"2026-06-04","cited_by_count":2,"area":null},{"id":"2606.10302","title":"Where You Inject Diversity Matters: A Unified Framework for Diverse Generation","created":"2026-06-09","cited_by_count":2,"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":"2601.13752","title":"Finding RELIEF: Shaping Reasoning Behavior without Reasoning Supervision via Belief Engineering","created":"2026-01-20","cited_by_count":1,"area":"lr"},{"id":"2602.00238","title":"DIVERGE: Diversity-Enhanced RAG for Open-Ended Information Seeking","created":"2026-01-30","cited_by_count":1,"area":"rag"},{"id":"2602.06665","title":"Not All Layers Need Tuning: Selective Layer Restoration Recovers Diversity","created":"2026-02-06","cited_by_count":1,"area":null},{"id":"2603.15276","title":"Dataset Diversity Metrics and Impact on Classification Models","created":"2026-03-16","cited_by_count":1,"area":null},{"id":"2603.15916","title":"Auto Researching, not hyperparameter tuning: Convergence Analysis of 10,000 Experiments","created":"2026-03-16","cited_by_count":1,"area":"agents"},{"id":"2603.29301","title":"Self-Consistency for LLM-Based Motion Trajectory Generation and Verification","created":"2026-03-31","cited_by_count":1,"area":"lr"},{"id":"2604.06061","title":"PromptEvolver: Prompt Inversion through Evolutionary Optimization in Natural-Language Space","created":"2026-04-03","cited_by_count":1,"area":null},{"id":"2604.11742","title":"Discourse Diversity in Multi-Turn Empathic Dialogue","created":"2026-04-13","cited_by_count":1,"area":null},{"id":"2604.22503","title":"How AI Writing Assistance Distorts Perceptions of AI Users and Their Opinions","created":"2026-04-24","cited_by_count":1,"area":null},{"id":"2605.26442","title":"Alignment Tuning for Large Language Models: A Data-Centric Lens on Alignment Data Pipelines","created":"2026-04-07","cited_by_count":1,"area":null},{"id":"2605.27878","title":"Narrative Flattening: How Post-Training Compresses Thematic, Affective, and Stylistic Variation in LLM Fiction","created":"2026-05-27","cited_by_count":1,"area":null},{"id":"2605.30021","title":"Recovering Diversity Without Losing Alignment: A DPO Recipe for Post-Trained LLMs","created":"2026-05-28","cited_by_count":1,"area":"alignment"},{"id":"2605.31099","title":"KnowledgeGain: Evaluating and Optimizing Science News Generation for Reader Learning","created":"2026-05-29","cited_by_count":1,"area":null},{"id":"2606.01736","title":"Argument Collapse: LLMs Flatten Long-Form Public Debate","created":"2026-06-01","cited_by_count":1,"area":null},{"id":"2606.17350","title":"Do Large Language Models Always Tell The Same Stories?","created":"2026-06-15","cited_by_count":1,"area":null},{"id":"2606.21891","title":"Learning the ARTS of Search for Automated Discovery","created":"2026-06-20","cited_by_count":1,"area":null},{"id":"2609.14896","title":"Forty Shades of Blue: Quality-Diversity Alignment via Mode-Conditioned Reinforcement Learning","created":"2026-09-14","cited_by_count":1,"area":"alignment"},{"id":"2601.00867","title":"The Silicon Psyche: Anthropomorphic Vulnerabilities in Large Language Models","created":"2025-12-30","cited_by_count":0,"area":"safety"},{"id":"2602.00017","title":"SafeTalkCoach: Diversity-Driven Multi-Agent Simulation for Parent-Teen Health Conversations","created":"2026-01-14","cited_by_count":0,"area":"agents"},{"id":"2602.02862","title":"STEER: Inference-Time Risk Control via Constrained Quality-Diversity Search","created":"2026-02-02","cited_by_count":0,"area":null},{"id":"2602.11220","title":"Patch the Distribution Mismatch: RL Rewriting Agent for Stable Off-Policy SFT","created":"2026-02-11","cited_by_count":0,"area":"agents"},{"id":"2602.14265","title":"STATe-of-Thoughts: Structured Action Templates for Tree-of-Thoughts","created":"2026-02-15","cited_by_count":0,"area":"lr"},{"id":"2602.15868","title":"Understanding LLM Failures: A Multi-Tape Turing Machine Analysis of Systematic Errors in Language Model Reasoning","created":"2026-01-27","cited_by_count":0,"area":"lr"},{"id":"2603.13305","title":"Evidence-based Distributional Alignment for Large Language Models","created":"2026-03-03","cited_by_count":0,"area":"alignment"},{"id":"2603.19294","title":"Maximizing Mutual Information Between Prompt and Response Improves LLM Performance With No Additional Data","created":"2026-03-10","cited_by_count":0,"area":null},{"id":"2604.01504","title":"Magic, Madness, Heaven, Sin: LLM Output Diversity is Everything, Everywhere, All at Once","created":"2026-04-02","cited_by_count":0,"area":null},{"id":"2604.07147","title":"Dynamic Context Evolution for Scalable Synthetic Data Generation","created":"2026-04-08","cited_by_count":0,"area":"synth"},{"id":"2604.13552","title":"Training-Free Test-Time Contrastive Learning for Large Language Models","created":"2026-04-15","cited_by_count":0,"area":"lr"},{"id":"2604.17244","title":"DORA Explorer: Improving the Exploration Ability of LLMs Without Training","created":"2026-04-19","cited_by_count":0,"area":null},{"id":"2604.25203","title":"BARRED: Synthetic Training of Custom Policy Guardrails via Asymmetric Debate","created":"2026-04-28","cited_by_count":0,"area":"safety"},{"id":"2605.10574","title":"LLM Jaggedness Unlocks Scientific Creativity","created":"2026-05-11","cited_by_count":0,"area":null},{"id":"2606.00022","title":"lmfaoooo at SemEval-2026 Task 1: Humor Is an Audience. Preference Modeling for Constrained Humor Generation","created":"2026-04-14","cited_by_count":0,"area":null},{"id":"2606.00334","title":"Isolating LLM Lexical Bias: A Curation-Free Triangulated Metric for Preference-Stage Learning","created":"2026-05-29","cited_by_count":0,"area":"alignment"},{"id":"2606.00467","title":"On the Limits of LLM Adaptability: Impact of Model-Internalized Priors on Annotation Task Performance","created":"2026-05-30","cited_by_count":0,"area":null},{"id":"2606.01811","title":"\"I've Seen How This Goes\": Characterizing Diversity via Progressive Conditional Surprise","created":"2026-06-01","cited_by_count":0,"area":null},{"id":"2606.03165","title":"Fully Automated Identification of Lexical Alignment and Preference-Stage Shifts in Large Language Models","created":"2026-06-02","cited_by_count":0,"area":"alignment"},{"id":"2606.09603","title":"Automated IEP Generation from Traditional Chinese Parent-Teacher Interviews via Corpus-Grounded Feature Diffusion","created":"2026-06-08","cited_by_count":0,"area":null},{"id":"2606.12790","title":"GENIE: A Fine-Grained Measure for Novelty","created":"2026-06-11","cited_by_count":0,"area":null},{"id":"2606.18258","title":"Examining Human-Like Behaviors in LLMs: A Multi-Dimensional Analysis of Model Behaviors, User Factors, and System Prompts","created":"2026-05-07","cited_by_count":0,"area":null},{"id":"2606.24937","title":"The Hitchhiker's Guide to Agentic AI: From Foundations to Systems","created":"2026-06-22","cited_by_count":0,"area":"lr"},{"id":"2607.05761","title":"Synthetic Consumer Insight Generation with Large Language Models","created":"2026-07-07","cited_by_count":0,"area":null},{"id":"2607.20429","title":"More Is Not More: What Matters for Diversity in LLM Opinions?","created":"2026-05-10","cited_by_count":0,"area":null},{"id":"2608.02618","title":"Beyond the Hivemind: Escaping LLM Homogeneity via Meta-Persona Anchoring and Sequential Temperature Scaling","created":"2026-05-31","cited_by_count":0,"area":null},{"id":"2608.07460","title":"CreativeInstruct: Scalably Teaching LLMs to Balance Quality, Creativity, and Diversity","created":"2026-08-07","cited_by_count":0,"area":null},{"id":"2608.13947","title":"Scaling Creative Writing Beyond Story-Centric Data with Attribute-Guided Genre Expansion","created":"2026-08-14","cited_by_count":0,"area":null},{"id":"2608.23317","title":"Spicing up Genetic Netlist Generation with LLMs","created":"2026-08-24","cited_by_count":0,"area":null},{"id":"2609.05437","title":"Beyond Right and Wrong: Evaluating Second-order Social Reasoning in Large Language Models","created":"2026-07-17","cited_by_count":0,"area":"lr"},{"id":"2609.09882","title":"Scored vs. Generated Readouts in Behavioral Language Models: An Empirical Study of Elicitation Format","created":"2026-09-09","cited_by_count":0,"area":null},{"id":"2609.15078","title":"Enabling Creative Exploration for Vibe Design Agents","created":"2026-09-14","cited_by_count":0,"area":"agents"},{"id":"2609.16051","title":"\"Looking for Something Weird to Happen\": How Humans Sustain AI Agent Novelty Amid Semantic Collapse","created":"2026-09-13","cited_by_count":0,"area":null},{"id":"2609.16454","title":"Fine-Tuning Fixes Mode Collapse and Over-Dispersion in LLMs","created":"2026-09-15","cited_by_count":0,"area":null},{"id":"2609.23997","title":"RoboTalk: Learning Multi-Robot Communication and Coordination from Multimodal Demonstrations","created":"2026-09-21","cited_by_count":0,"area":null},{"id":"2609.28806","title":"A Harness for Synthesizing Diverse Naturalistic Full-Duplex Conversations","created":"2026-09-23","cited_by_count":0,"area":null},{"id":"2609.31571","title":"Strategically Diverse Sampling for Self-Training","created":"2026-09-25","cited_by_count":0,"area":"lr"},{"id":"2609.31688","title":"Don't Repeat Yourself: Self-Supervised Fine-Tuning for Coverage","created":"2026-09-16","cited_by_count":0,"area":null},{"id":"2609.33155","title":"Where Do Test-Time Scaling and Training Fall Short in Individual Stance Prediction?","created":"2026-09-27","cited_by_count":0,"area":"lr"},{"id":"2609.33433","title":"CORA: A Protocol for Diagnosing Boundary Robustness in Text-to-Audio Retrieval under Query Reformulations","created":"2026-09-27","cited_by_count":0,"area":null},{"id":"2609.33666","title":"One Model Is Not a Crowd: Multi-LLM and Aspect-Conditioned Diverse Comment Generation","created":"2026-09-27","cited_by_count":0,"area":null},{"id":"2609.33936","title":"How Strong Is the Evidence for the Artificial Hivemind? Reevaluating Evidence for the Open-Ended Homogeneity of Language Models","created":"2026-09-27","cited_by_count":0,"area":null},{"id":"2609.34929","title":"Sample What You Say: Aligning Language Models to Sample the Distributions They State","created":"2026-09-28","cited_by_count":0,"area":"alignment"},{"id":"2609.38448","title":"Reach Into The CHOIR: Free-List Elicitation Uncovers Distinct Model Voices in LLM Ensembles","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2610.00707","title":"Initialization Improves LLM-Driven Discovery","created":"2026-09-30","cited_by_count":0,"area":null},{"id":"2610.01382","title":"Gacha Decoding: Eliciting Diverse Generations Through Instruction Following","created":"2026-10-01","cited_by_count":0,"area":null}],"next_cursor":"100"}