{"total":104,"rows":[{"id":"2505.19590","title":"Learning to Reason without External Rewards","created":"2025-05-26","cited_by_count":210,"area":"lr"},{"id":"2505.15134","title":"The Unreasonable Effectiveness of Entropy Minimization in LLM Reasoning","created":"2025-05-21","cited_by_count":166,"area":"lr"},{"id":"2503.21878","title":"Is Best-of-N the Best of Them? Coverage, Scaling, and Optimality in Inference-Time Alignment","created":"2025-03-27","cited_by_count":97,"area":"alignment"},{"id":"2502.12118","title":"Scaling Test-Time Compute Without Verification or RL is Suboptimal","created":"2025-02-17","cited_by_count":84,"area":"lr"},{"id":"2506.10943","title":"Self-Adapting Language Models","created":"2025-06-12","cited_by_count":84,"area":null},{"id":"2509.02534","title":"Jointly Reinforcing Diversity and Quality in Language Model Generations","created":"2025-09-02","cited_by_count":80,"area":null},{"id":"2505.21493","title":"Reinforcing General Reasoning without Verifiers","created":"2025-05-27","cited_by_count":77,"area":"lr"},{"id":"2503.01067","title":"All Roads Lead to Likelihood: The Value of Reinforcement Learning in Fine-Tuning","created":"2025-03-03","cited_by_count":59,"area":"alignment"},{"id":"2506.09026","title":"e3: Learning to Explore Enables Extrapolation of Test-Time Compute for LLMs","created":"2025-06-10","cited_by_count":59,"area":"lr"},{"id":"2506.04210","title":"Does Thinking More always Help? Mirage of Test-Time Scaling in Reasoning Models","created":"2025-06-04","cited_by_count":53,"area":"lr"},{"id":"2504.10478","title":"Weight Ensembling Improves Reasoning in Language Models","created":"2025-04-14","cited_by_count":38,"area":"lr"},{"id":"2505.13445","title":"Trust, But Verify: A Self-Verification Approach to Reinforcement Learning with Verifiable Rewards","created":"2025-05-19","cited_by_count":38,"area":null},{"id":"2502.01612","title":"Self-Improving Transformers Overcome Easy-to-Hard and Length Generalization Challenges","created":"2025-02-03","cited_by_count":31,"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":"2510.07841","title":"Self-Improving LLM Agents at Test-Time","created":"2025-10-09","cited_by_count":30,"area":"agents"},{"id":"2506.10406","title":"PAG: Multi-Turn Reinforced LLM Self-Correction with Policy as Generative Verifier","created":"2025-06-12","cited_by_count":28,"area":null},{"id":"2511.19942","title":"Differential Smoothing Mitigates Sharpening and Improves LLM Reasoning","created":"2025-11-25","cited_by_count":22,"area":"lr"},{"id":"2412.15118","title":"Reasoning Through Execution: Unifying Process and Outcome Rewards for Code Generation","created":"2024-12-19","cited_by_count":21,"area":"lr"},{"id":"2502.16182","title":"IPO: Your Language Model is Secretly a Preference Classifier","created":"2025-02-22","cited_by_count":17,"area":"alignment"},{"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":"2512.02304","title":"When Does Verification Pay Off? A Closer Look at LLMs as Solution Verifiers","created":"2025-12-02","cited_by_count":15,"area":null},{"id":"2511.07378","title":"Transformers Provably Learn Chain-of-Thought Reasoning with Length Generalization","created":"2025-11-10","cited_by_count":14,"area":"lr"},{"id":"2506.05295","title":"Sample Complexity and Representation Ability of Test-time Scaling Paradigms","created":"2025-06-05","cited_by_count":12,"area":"lr"},{"id":"2507.12399","title":"ROC-n-reroll: How verifier imperfection affects test-time scaling","created":"2025-07-16","cited_by_count":12,"area":"lr"},{"id":"2601.10403","title":"Discrete Feynman-Kac Correctors","created":"2026-01-15","cited_by_count":11,"area":"diffusion"},{"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":"2601.23045","title":"The Hot Mess of AI: How Does Misalignment Scale With Model Intelligence and Task Complexity?","created":"2026-01-30","cited_by_count":10,"area":null},{"id":"2603.10263","title":"From Prior to Pro: Efficient Skill Mastery via Distribution Contractive RL Finetuning","created":"2026-03-10","cited_by_count":10,"area":"deeprl"},{"id":"2505.12050","title":"AdaBoN: Adaptive Best-of-N Alignment","created":"2025-05-17","cited_by_count":9,"area":"alignment"},{"id":"2510.03199","title":"Best-of-Majority: Minimax-Optimal Strategy for Pass@$k$ Inference Scaling","created":"2025-10-03","cited_by_count":9,"area":null},{"id":"2510.04786","title":"Learning on the Job: Test-Time Curricula for Targeted Reinforcement Learning","created":"2025-10-06","cited_by_count":9,"area":"deeprl"},{"id":"2603.23994","title":"Understanding the Challenges in Iterative Generative Optimization with LLMs","created":"2026-03-25","cited_by_count":8,"area":null},{"id":"2502.12146","title":"Diffusion-Sharpening: Fine-tuning Diffusion Models with Denoising Trajectory Sharpening","created":"2025-02-17","cited_by_count":7,"area":"diffusion"},{"id":"2602.03979","title":"Likelihood-Based Reward Designs for General LLM Reasoning","created":"2026-02-03","cited_by_count":7,"area":"lr"},{"id":"2602.09305","title":"Reward Modeling for Reinforcement Learning-Based LLM Reasoning: Design, Challenges, and Evaluation","created":"2026-02-10","cited_by_count":7,"area":"lr"},{"id":"2609.21032","title":"Scaling Discovery through Test-Time Communication","created":"2026-09-17","cited_by_count":7,"area":"agents"},{"id":"2502.10978","title":"Agentic LLM Framework for Adaptive Decision Discourse","created":"2025-02-16","cited_by_count":6,"area":"agents"},{"id":"2507.00075","title":"Theoretical Modeling of Large Language Model Self-Improvement Training Dynamics Through Solver-Verifier Gap","created":"2025-06-29","cited_by_count":6,"area":"synth"},{"id":"2512.00884","title":"Towards Active Synthetic Data Generation for Finetuning Language Models","created":"2025-11-30","cited_by_count":6,"area":"synth"},{"id":"2512.01775","title":"How Does RL Post-training Induce Skill Composition? A Case Study on Countdown","created":"2025-12-01","cited_by_count":6,"area":"lr"},{"id":"2601.08421","title":"Coverage Improvement and Fast Convergence of On-policy Preference Learning","created":"2026-01-13","cited_by_count":6,"area":"alignment"},{"id":"2606.18967","title":"EfficientRollout: System-Aware Self-Speculative Decoding for RL Rollouts","created":"2026-06-17","cited_by_count":6,"area":"lr"},{"id":"2606.26080","title":"Neglected Free Lunch from Post-training: Progress Advantage for LLM Agents","created":"2026-06-24","cited_by_count":6,"area":"lr"},{"id":"2508.06026","title":"Temporal Self-Rewarding Language Models: Decoupling Chosen-Rejected via Past-Future","created":"2025-08-08","cited_by_count":5,"area":"alignment"},{"id":"2603.29791","title":"Reasoning-Driven Synthetic Data Generation and Evaluation","created":"2026-03-31","cited_by_count":5,"area":null},{"id":"2605.04542","title":"Power Distribution Bridges Sampling, Self-Reward RL, and Self-Distillation","created":"2026-05-06","cited_by_count":5,"area":"lr"},{"id":"2412.05232","title":"LIAR: Leveraging Inference Time Alignment (Best-of-N) to Jailbreak LLMs in Seconds","created":"2024-12-06","cited_by_count":4,"area":"safety"},{"id":"2605.28814","title":"Self-Improving Language Models with Bidirectional Evolutionary Search","created":"2026-05-27","cited_by_count":4,"area":"agents"},{"id":"2606.01075","title":"On the Generalization Gap in Self-Evolving Language Model Reasoning","created":"2026-05-31","cited_by_count":4,"area":"lr"},{"id":"2608.09263","title":"Privileged Likelihood Is Not Automatically Value: Three Checks for Token Credit in On-Policy Self-Distillation","created":"2026-08-10","cited_by_count":4,"area":"distill"},{"id":"2506.07822","title":"Accelerating Diffusion Planners in Offline RL via Reward-Aware Consistency Trajectory Distillation","created":"2025-06-09","cited_by_count":3,"area":"diffusion"},{"id":"2507.20252","title":"Post-Completion Learning for Language Models","created":"2025-07-27","cited_by_count":3,"area":null},{"id":"2510.13709","title":"Training LLM Agents to Empower Humans","created":"2025-10-15","cited_by_count":3,"area":"agents"},{"id":"2511.08440","title":"Coherence Mechanisms for Provable Self-Improvement","created":"2025-11-11","cited_by_count":3,"area":"synth"},{"id":"2603.06797","title":"Best-of-Tails: Bridging Optimism and Pessimism in Inference-Time Alignment","created":"2026-03-06","cited_by_count":3,"area":"alignment"},{"id":"2604.04648","title":"From Curiosity to Caution: Mitigating Reward Hacking for Best-of-N with Pessimism","created":"2026-04-06","cited_by_count":3,"area":"lr"},{"id":"2606.30445","title":"When Does Online Imitation Learning Help in LLM Post-Training? The Role of (Non-)Realizability Beyond Horizon","created":"2026-06-29","cited_by_count":3,"area":"offlinerl"},{"id":"2505.16927","title":"Latent Principle Discovery for Language Model Self-Improvement","created":"2025-05-22","cited_by_count":2,"area":"synth"},{"id":"2506.04272","title":"Understanding the Impact of Sampling Quality in Direct Preference Optimization","created":"2025-06-03","cited_by_count":2,"area":"alignment"},{"id":"2510.18814","title":"A Model Can Help Itself: Reward-Free Self-Training for LLM Reasoning","created":"2025-10-21","cited_by_count":2,"area":"lr"},{"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":"2606.03962","title":"Using Reward Uncertainty to Induce Diverse Behaviour in Reinforcement Learning","created":"2026-06-02","cited_by_count":2,"area":"alignment"},{"id":"2606.03979","title":"Language Models Need Sleep: Learning to Self-Modify and Consolidate Memories","created":"2026-06-02","cited_by_count":2,"area":null},{"id":"2606.13125","title":"Select and Improve: Understanding the Mechanics of Post-Training for Reasoning","created":"2026-06-11","cited_by_count":2,"area":null},{"id":"2608.20290","title":"Phantom Gains: Auditing Self-Improvement Against a Measured Null","created":"2026-08-20","cited_by_count":2,"area":"synth"},{"id":"2608.22631","title":"Learning Generalizable Behaviors for Terminal Agents","created":"2026-08-23","cited_by_count":2,"area":"agents"},{"id":"2608.25756","title":"TailSFT: Filtered Fine-Tuning Improves Post-Training Performance","created":"2026-08-26","cited_by_count":2,"area":"agents"},{"id":"2503.06917","title":"Sample-Efficient Optimization over Generative Priors via Coarse Learnability","created":"2025-03-10","cited_by_count":1,"area":null},{"id":"2503.07660","title":"Research Superalignment Should Advance Now with Alternating Competence and Conformity Optimization","created":"2025-03-08","cited_by_count":1,"area":"alignment"},{"id":"2505.23557","title":"Learning Parametric Distributions from Samples and Preferences","created":"2025-05-29","cited_by_count":1,"area":"alignment"},{"id":"2511.05684","title":"A Representation Sharpening Framework for Zero Shot Dense Retrieval","created":"2025-11-07","cited_by_count":1,"area":null},{"id":"2602.01699","title":"Mitigating loss of control in advanced AI systems through instrumental goal trajectories","created":"2026-02-02","cited_by_count":1,"area":null},{"id":"2602.02051","title":"SIDiffAgent: Self-Improving Diffusion Agent","created":"2026-02-02","cited_by_count":1,"area":"diffusion"},{"id":"2602.12642","title":"Beyond Normalization: Rethinking the Partition Function as a Difficulty Scheduler for RLVR","created":"2026-02-13","cited_by_count":1,"area":"lr"},{"id":"2602.16704","title":"Reinforced Fast Weights with Next-Sequence Prediction","created":"2026-02-18","cited_by_count":1,"area":null},{"id":"2604.15453","title":"(1D) Ordered Tokens Enable Efficient Test-Time Search","created":"2026-04-16","cited_by_count":1,"area":null},{"id":"2605.27564","title":"The Future of Facts: Tracing the Factual Generation-Verification Gap","created":"2026-05-26","cited_by_count":1,"area":null},{"id":"2607.10966","title":"SVR-R1: Bootstrapping Multi-modal Reasoning with Self-verification in Reinforcement Learning","created":"2026-07-13","cited_by_count":1,"area":"lr"},{"id":"2608.14420","title":"More Correct Mass, Worse Answers: Why Power Sampling Can Fail and How to Fix It","created":"2026-08-14","cited_by_count":1,"area":null},{"id":"2608.26120","title":"Recipes for Steering and Scaling LLMs via Sampling","created":"2026-06-19","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":"2609.22547","title":"RLVR is a Kernel, Not a Function: Statistical Inference for pass@$k$ Crossovers","created":"2026-09-18","cited_by_count":1,"area":null},{"id":"2505.17288","title":"Learning to Choose or Choosing to Learn: Best-of-N vs. Supervised Fine-Tuning for Bit String Generation","created":"2025-05-22","cited_by_count":0,"area":null},{"id":"2508.06525","title":"Large Language Models Facilitate Vision Reflection in Image Classification","created":"2025-08-02","cited_by_count":0,"area":"mllm"},{"id":"2512.04044","title":"MarkTune: Improving the Quality-Detectability Trade-off in Open-Weight LLM Watermarking","created":"2025-12-03","cited_by_count":0,"area":"safety"},{"id":"2601.19055","title":"Principled Fine-tuning of LLMs from User-Edits: A Medley of Preference, Supervision, and Reward","created":"2026-01-27","cited_by_count":0,"area":null},{"id":"2602.02991","title":"Large Language Models Can Take False First Steps at Inference-time Planning","created":"2026-02-03","cited_by_count":0,"area":null},{"id":"2602.23535","title":"Partition Function Estimation under Bounded f-Divergence","created":"2026-02-26","cited_by_count":0,"area":null},{"id":"2603.03000","title":"Why Does RLAIF Work At All?","created":"2026-03-03","cited_by_count":0,"area":"alignment"},{"id":"2604.04855","title":"The Role of Generator Access in Autoregressive Post-Training","created":"2026-04-06","cited_by_count":0,"area":null},{"id":"2604.16259","title":"Beyond Distribution Sharpening: The Importance of Task Rewards","created":"2026-04-17","cited_by_count":0,"area":"lr"},{"id":"2605.09922","title":"Team-Based Self-Play With Dual Adaptive Weighting for Fine-Tuning LLMs","created":"2026-05-11","cited_by_count":0,"area":"synth"},{"id":"2607.01490","title":"Don't Let Gains FADE: Breaking Down Policy Gradient Weights in RL","created":"2026-07-01","cited_by_count":0,"area":"lr"},{"id":"2608.20041","title":"A three-dimensional typology of agency for advanced AI systems","created":"2026-08-20","cited_by_count":0,"area":"agents"},{"id":"2609.33559","title":"Fine Until Fine-Tuned: Repeated Solutions Make Reasoning Fragile","created":"2026-09-27","cited_by_count":0,"area":null},{"id":"2609.34374","title":"ABC-Align: Prediction-Powered Alignment with Adaptive Bias Control","created":"2026-09-28","cited_by_count":0,"area":"alignment"},{"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":"2609.36049","title":"Improving scalable oversight with co-trained monitors","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2609.36535","title":"When Updating Stops Being Learning: Rethinking LLM Self-Evolution via learnable information gain","created":"2026-09-29","cited_by_count":0,"area":"lr"},{"id":"2609.38672","title":"Provable Test-Time Scaling for Beam Search in LLM Reasoning","created":"2026-09-29","cited_by_count":0,"area":"lr"}],"next_cursor":"100"}