{"total":66,"rows":[{"id":"2509.02534","title":"Jointly Reinforcing Diversity and Quality in Language Model Generations","created":"2025-09-02","cited_by_count":80,"area":null},{"id":"2507.14172","title":"Self-Improving Language Models for Evolutionary Program Synthesis: A Case Study on ARC-AGI","created":"2025-07-10","cited_by_count":36,"area":"synth"},{"id":"2510.20817","title":"KL-Regularized Reinforcement Learning is Designed to Mode Collapse","created":"2025-10-23","cited_by_count":31,"area":"deeprl"},{"id":"2504.15266","title":"Roll the dice & look before you leap: Going beyond the creative limits of next-token prediction","created":"2025-04-21","cited_by_count":29,"area":null},{"id":"2506.19807","title":"KnowRL: Exploring Knowledgeable Reinforcement Learning for Factuality","created":"2025-06-24","cited_by_count":20,"area":"lr"},{"id":"2510.04226","title":"What and Whose Knowledge? Measuring Epistemic Diversity in Large Language Models","created":"2025-10-05","cited_by_count":14,"area":null},{"id":"2511.00432","title":"G2: Guided Generation for Enhanced Output Diversity in LLMs","created":"2025-11-01","cited_by_count":14,"area":null},{"id":"2510.21150","title":"String Seed of Thought: Prompting LLMs for Distribution-Faithful and Diverse Generation","created":"2025-10-24","cited_by_count":11,"area":"lr"},{"id":"2509.24981","title":"Random Policy Valuation is Enough for LLM Reasoning with Verifiable Rewards","created":"2025-09-29","cited_by_count":10,"area":"lr"},{"id":"2512.02895","title":"MindGPT-4ov: An Enhanced MLLM via a Multi-Stage Post-Training Paradigm","created":"2025-12-02","cited_by_count":9,"area":"mllm"},{"id":"2505.18128","title":"Frankentext: Stitching random text fragments into long-form narratives","created":"2025-05-23","cited_by_count":8,"area":null},{"id":"2511.05650","title":"Optimizing Diversity and Quality through Base-Aligned Model Collaboration","created":"2025-11-07","cited_by_count":8,"area":null},{"id":"2509.21043","title":"Measuring Combinatorial Creativity in Large Language Models and Humans","created":"2025-09-25","cited_by_count":7,"area":null},{"id":"2509.25424","title":"Polychromic Objectives for Reinforcement Learning","created":"2025-09-29","cited_by_count":7,"area":"deeprl"},{"id":"2604.18005","title":"Diversity Collapse in Multi-Agent LLM Systems: Structural Coupling and Collective Failure in Open-Ended Idea Generation","created":"2026-04-20","cited_by_count":7,"area":"agents"},{"id":"2509.02170","title":"Avoidance Decoding for Diverse Multi-Branch Story Generation","created":"2025-09-02","cited_by_count":6,"area":null},{"id":"2601.09609","title":"DPWriter: Reinforcement Learning with Diverse Planning Branching for Creative Writing","created":"2026-01-14","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":"2509.22641","title":"Death of the Novel(ty): Beyond n-Gram Novelty as a Metric for Textual Creativity","created":"2025-09-26","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":"2601.11227","title":"Language of Thought Shapes Output Diversity in Large Language Models","created":"2026-01-16","cited_by_count":4,"area":"lr"},{"id":"2605.00195","title":"Diversity in Large Language Models under Supervised Fine-Tuning","created":"2026-04-30","cited_by_count":4,"area":"alignment"},{"id":"2507.13874","title":"Geometry of Knowledge Allows Extending Diversity Boundaries of Large Language Models","created":"2025-07-18","cited_by_count":3,"area":null},{"id":"2508.19200","title":"The Ramon Llull's Thinking Machine for Automated Ideation","created":"2025-08-26","cited_by_count":3,"area":"lr"},{"id":"2601.22629","title":"Time-Annealed Perturbation Sampling: Diverse Generation for Diffusion Language Models","created":"2026-01-30","cited_by_count":3,"area":"lr"},{"id":"2604.02686","title":"Beyond Semantic Manipulation: Token-Space Attacks on Reward Models","created":"2026-04-03","cited_by_count":3,"area":"alignment"},{"id":"2607.12796","title":"The One-Word Census: Answer-Choice Conformity Across 105 Language Models","created":"2026-07-14","cited_by_count":3,"area":null},{"id":"2510.04009","title":"What Shapes a Creative Machine Mind? Comprehensively Benchmarking Creativity in Foundation Models","created":"2025-10-05","cited_by_count":2,"area":null},{"id":"2512.01725","title":"Beware of Reasoning Overconfidence: Pitfalls in the Reasoning Process for Multi-solution Tasks","created":"2025-12-01","cited_by_count":2,"area":"lr"},{"id":"2512.23601","title":"Enhancing Diversity of LLM-Generated Educational Tasks","created":"2025-12-29","cited_by_count":2,"area":null},{"id":"2601.06116","title":"The Homogenization Problem in LLMs: Towards Meaningful Diversity in AI Safety","created":"2026-01-03","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":"2605.11845","title":"Probabilistic Calibration Is a Trainable Capability in Language Models","created":"2026-05-12","cited_by_count":2,"area":null},{"id":"2606.02293","title":"AI as a Tool for Simulation-Based Experiments in Literary Studies","created":"2026-06-01","cited_by_count":2,"area":null},{"id":"2606.03962","title":"Using Reward Uncertainty to Induce Diverse Behaviour in Reinforcement Learning","created":"2026-06-02","cited_by_count":2,"area":"alignment"},{"id":"2606.07818","title":"Representational Similarity and Model Behavior in Multi-Agent Interaction","created":"2026-06-05","cited_by_count":2,"area":"agents"},{"id":"2510.01472","title":"LLM-NAS: LLM-driven Hardware-Aware Neural Architecture Search","created":"2025-10-01","cited_by_count":1,"area":null},{"id":"2602.21317","title":"Shared Nature, Unique Nurture: PRISM for Pluralistic Reasoning via In-context Structure Modeling","created":"2026-02-24","cited_by_count":1,"area":"lr"},{"id":"2605.06540","title":"Ex Ante Evaluation of AI-Induced Idea Diversity Collapse","created":"2026-05-07","cited_by_count":1,"area":null},{"id":"2605.30150","title":"Anchorless Diversification for Parallel LLM Ideation","created":"2026-05-28","cited_by_count":1,"area":null},{"id":"2606.11456","title":"AI Coding Agents in Social Science: Methodologically Diverse, Empirically Consistent, Interpretively Vulnerable","created":"2026-06-09","cited_by_count":1,"area":"agents"},{"id":"2608.30047","title":"Can LLM Agents Discover? Evaluating Creativity on ML Engineering Tasks","created":"2026-08-30","cited_by_count":1,"area":"agents"},{"id":"2609.00683","title":"Creative Generation via Multi-Agent Debate: Does Debate Suppress Diversity?","created":"2026-09-01","cited_by_count":1,"area":"agents"},{"id":"2510.20849","title":"Cultural Alien Sampler: Open-ended art generation balancing originality and coherence","created":"2025-10-21","cited_by_count":0,"area":null},{"id":"2510.21341","title":"Magellan: Guided MCTS for Latent Space Exploration and Novelty Generation","created":"2025-10-24","cited_by_count":0,"area":null},{"id":"2602.10583","title":"Flow of Spans: Generalizing Language Models to Dynamic Span-Vocabulary via GFlowNets","created":"2026-02-11","cited_by_count":0,"area":null},{"id":"2604.03374","title":"CresOWLve: Benchmarking Creative Problem-Solving Over Real-World Knowledge","created":"2026-04-03","cited_by_count":0,"area":"lr"},{"id":"2604.11522","title":"Triviality Corrected Endogenous Reward","created":"2026-04-13","cited_by_count":0,"area":null},{"id":"2605.13450","title":"Assessing the Creativity of Large Language Models: Testing, Limits, and New Frontiers","created":"2026-05-13","cited_by_count":0,"area":null},{"id":"2605.26492","title":"Elias in the Lighthouse, Again? Diagnosing Low Diversity in LLM Stories","created":"2026-05-26","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":"2606.05985","title":"Beyond Alignment: Value Diversity as a Collective Property in Multicultural Agent Systems","created":"2026-06-04","cited_by_count":0,"area":"agents"},{"id":"2607.01849","title":"Decomposer: Learning to Decompile Symbolic Music to Programs","created":"2026-07-02","cited_by_count":0,"area":null},{"id":"2607.02668","title":"Improving LLMs via Validator-to-Generator Alignment","created":"2026-07-02","cited_by_count":0,"area":null},{"id":"2608.05576","title":"Where Models Converge and Humans Diverge: A Coverage Framework for Distributional Pluralism in Open-Ended Generation","created":"2026-08-06","cited_by_count":0,"area":null},{"id":"2608.24228","title":"Evaluating Multiple LLM Generations with Validated Task Coverage","created":"2026-08-25","cited_by_count":0,"area":null},{"id":"2609.08634","title":"Suan: Rectifying Direct Preference Safety Alignment in Large Language Models","created":"2026-09-08","cited_by_count":0,"area":"alignment"},{"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":"2609.33947","title":"Simple Diffusion Language Models Are More Effective Few-Step Generators Than Reported","created":"2026-09-27","cited_by_count":0,"area":"diffusion"},{"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":"2609.36900","title":"STAR-GRPO: Canonical Anchoring and Reliability-First Advantages against Representation-Dependent Reward Hacking","created":"2026-09-29","cited_by_count":0,"area":"lr"},{"id":"2610.01382","title":"Gacha Decoding: Eliciting Diverse Generations Through Instruction Following","created":"2026-10-01","cited_by_count":0,"area":null},{"id":"2610.11539","title":"Design Creativity Bench: Measuring creativity in LLM-Generated UI","created":"2026-10-08","cited_by_count":0,"area":null},{"id":"2610.12998","title":"Evaluating LLM Creativity through Long-Tail Performance","created":"2026-10-09","cited_by_count":0,"area":null}],"next_cursor":null}