{"total":52,"rows":[{"id":"2503.09567","title":"Towards Reasoning Era: A Survey of Long Chain-of-Thought for Reasoning Large Language Models","created":"2025-03-12","cited_by_count":384,"area":"lr"},{"id":"2509.02547","title":"The Landscape of Agentic Reinforcement Learning for LLMs: A Survey","created":"2025-09-02","cited_by_count":205,"area":"agents"},{"id":"2509.06941","title":"Outcome-based Exploration for LLM Reasoning","created":"2025-09-08","cited_by_count":83,"area":"lr"},{"id":"2504.05228","title":"NoveltyBench: Evaluating Language Models for Humanlike Diversity","created":"2025-04-07","cited_by_count":66,"area":null},{"id":"2504.12522","title":"Evaluating the Diversity and Quality of LLM Generated Content","created":"2025-04-16","cited_by_count":51,"area":"lr"},{"id":"2504.04736","title":"Synthetic Data Generation & Multi-Step RL for Reasoning & Tool Use","created":"2025-04-07","cited_by_count":45,"area":"lr"},{"id":"2507.09650","title":"Cultivating Pluralism In Algorithmic Monoculture: The Community Alignment Dataset","created":"2025-07-13","cited_by_count":35,"area":"alignment"},{"id":"2507.00310","title":"AutoDiscovery: Open-ended Scientific Discovery via Bayesian Surprise","created":"2025-06-30","cited_by_count":33,"area":null},{"id":"2510.20817","title":"KL-Regularized Reinforcement Learning is Designed to Mode Collapse","created":"2025-10-23","cited_by_count":31,"area":"deeprl"},{"id":"2508.19229","title":"StepWiser: Stepwise Generative Judges for Wiser Reasoning","created":"2025-08-26","cited_by_count":28,"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":"2509.04784","title":"Post-training Large Language Models for Diverse High-Quality Responses","created":"2025-09-05","cited_by_count":19,"area":null},{"id":"2512.21514","title":"DiverseGRPO: Mitigating Mode Collapse in Image Generation via Diversity-Aware GRPO","created":"2025-12-25","cited_by_count":17,"area":"lr"},{"id":"2510.11686","title":"Representation-Based Exploration for Language Models: From Test-Time to Post-Training","created":"2025-10-13","cited_by_count":16,"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":"2602.01062","title":"SetPO: Set-Level Policy Optimization for Diversity-Preserving LLM Reasoning","created":"2026-02-01","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":"2511.05650","title":"Optimizing Diversity and Quality through Base-Aligned Model Collaboration","created":"2025-11-07","cited_by_count":8,"area":null},{"id":"2509.25424","title":"Polychromic Objectives for Reinforcement Learning","created":"2025-09-29","cited_by_count":7,"area":"deeprl"},{"id":"2504.09389","title":"Measuring LLM Novelty As The Frontier Of Original And High-Quality Output","created":"2025-04-13","cited_by_count":6,"area":null},{"id":"2505.07784","title":"Domain Regeneration: How well do LLMs match syntactic properties of text domains?","created":"2025-05-12","cited_by_count":6,"area":null},{"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":"2601.20539","title":"PathWise: Planning through World Model for Automated Heuristic Design via Self-Evolving LLMs","created":"2026-01-28","cited_by_count":6,"area":"wm"},{"id":"2605.11258","title":"Unlocking LLM Creativity in Science through Analogical Reasoning","created":"2026-05-11","cited_by_count":6,"area":"lr"},{"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":"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":"2601.22629","title":"Time-Annealed Perturbation Sampling: Diverse Generation for Diffusion Language Models","created":"2026-01-30","cited_by_count":3,"area":"lr"},{"id":"2510.12699","title":"Generation Space Size: Understanding and Calibrating Open-Endedness of LLM Generations","created":"2025-10-14","cited_by_count":2,"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":"2601.22010","title":"Exploring Diverse Generation Paths via Inference-time Stiefel Activation Steering","created":"2026-01-29","cited_by_count":2,"area":"mechinterp"},{"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":"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":"2606.29985","title":"Are We Measuring Strategy or Phrasing? The Gap Between Surface- and Approach-Level Diversity in LLM Math Reasoning","created":"2026-06-29","cited_by_count":2,"area":"lr"},{"id":"2507.01726","title":"Generative flow-based warm start of the variational quantum eigensolver","created":"2025-07-02","cited_by_count":1,"area":null},{"id":"2510.15061","title":"Antislop: A Comprehensive Framework for Identifying and Eliminating Repetitive Patterns in Language Models","created":"2025-10-16","cited_by_count":1,"area":null},{"id":"2602.15894","title":"Quality-constrained Entropy Maximization Policy Optimization for LLM Diversity","created":"2026-02-11","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":"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":"2505.01706","title":"Inducing Robustness in a 2 Dimensional Direct Preference Optimization Paradigm","created":"2025-05-03","cited_by_count":0,"area":"alignment"},{"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":"2602.05113","title":"Democratic Preference Alignment via Sortition-Weighted RLHF","created":"2026-02-04","cited_by_count":0,"area":"alignment"},{"id":"2604.14969","title":"Discovering Novel LLM Experts via Task-Capability Coevolution","created":"2026-04-16","cited_by_count":0,"area":null},{"id":"2606.04095","title":"POLARIS: Guiding Small Models to Write Long Stories","created":"2026-06-02","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":"2609.10052","title":"Direct Diversity Optimization for Diverse Successful Trajectories in Preference Post-Training","created":"2026-09-09","cited_by_count":0,"area":"agents"},{"id":"2609.15078","title":"Enabling Creative Exploration for Vibe Design Agents","created":"2026-09-14","cited_by_count":0,"area":"agents"},{"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":"2609.33666","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":"2609.38805","title":"Explicit Trajectory Diversity for RL-Based Post-Training of LLM Agents","created":"2026-09-30","cited_by_count":0,"area":"agents"},{"id":"2610.03529","title":"Divergence controls entropy in distillation","created":"2026-10-02","cited_by_count":0,"area":"distill"},{"id":"2610.06729","title":"Improving Diversity in LLM Short Story Generation","created":"2026-10-05","cited_by_count":0,"area":null}],"next_cursor":null}