{"total":83,"rows":[{"id":"2510.14901","title":"Reasoning with Sampling: Your Base Model is Smarter Than You Think","created":"2025-10-16","cited_by_count":89,"area":"lr"},{"id":"2511.10395","title":"AgentEvolver: Towards Efficient Self-Evolving Agent System","created":"2025-11-13","cited_by_count":85,"area":"agents"},{"id":"2510.10150","title":"Rethinking Entropy Interventions in RLVR: An Entropy Change Perspective","created":"2025-10-11","cited_by_count":52,"area":"lr"},{"id":"2601.18779","title":"POPE: Learning to Reason on Hard Problems via Privileged On-Policy Exploration","created":"2026-01-26","cited_by_count":42,"area":"lr"},{"id":"2602.02710","title":"Maximum Likelihood Reinforcement Learning","created":"2026-02-02","cited_by_count":36,"area":"deeprl"},{"id":"2509.19170","title":"Soft Tokens, Hard Truths","created":"2025-09-23","cited_by_count":35,"area":"lr"},{"id":"2509.21128","title":"RL Squeezes, SFT Expands: A Comparative Study of Reasoning LLMs","created":"2025-09-25","cited_by_count":34,"area":"lr"},{"id":"2510.20817","title":"KL-Regularized Reinforcement Learning is Designed to Mode Collapse","created":"2025-10-23","cited_by_count":31,"area":"deeprl"},{"id":"2601.21590","title":"Scalable Power Sampling: Unlocking Efficient, Training-Free Reasoning for LLMs via Distribution Sharpening","created":"2026-01-29","cited_by_count":31,"area":"lr"},{"id":"2509.26209","title":"Diversity-Incentivized Exploration for Versatile Reasoning","created":"2025-09-30","cited_by_count":28,"area":"lr"},{"id":"2512.16912","title":"Exploration vs Exploitation: Rethinking RLVR through Clipping, Entropy, and Spurious Reward","created":"2025-12-18","cited_by_count":27,"area":"lr"},{"id":"2511.19942","title":"Differential Smoothing Mitigates Sharpening and Improves LLM Reasoning","created":"2025-11-25","cited_by_count":22,"area":"lr"},{"id":"2509.14234","title":"Compute as Teacher: Turning Inference Compute Into Reference-Free Supervision","created":"2025-09-17","cited_by_count":18,"area":null},{"id":"2510.14807","title":"Beyond the Sampled Token: Preserving Candidate Support in RLVR","created":"2025-10-16","cited_by_count":18,"area":null},{"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":"2601.18795","title":"Reuse your FLOPs: Scaling RL on Hard Problems by Conditioning on Very Off-Policy Prefixes","created":"2026-01-26","cited_by_count":16,"area":"lr"},{"id":"2605.10781","title":"Rebellious Student: Reversing Teacher Signals for Reasoning Exploration with Self-Distilled RLVR","created":"2026-05-11","cited_by_count":15,"area":"lr"},{"id":"2601.18778","title":"Teaching Models to Teach Themselves: Reasoning at the Edge of Learnability","created":"2026-01-26","cited_by_count":13,"area":"lr"},{"id":"2509.26114","title":"Clip-Low Increases Entropy and Clip-High Decreases Entropy in Reinforcement Learning of Large Language Models","created":"2025-09-30","cited_by_count":12,"area":"lr"},{"id":"2509.22611","title":"Quantile Advantage Estimation: Stabilizing RLVR for LLM Reasoning","created":"2025-09-26","cited_by_count":11,"area":"lr"},{"id":"2510.10959","title":"Revisiting Entropy Regularization: Adaptive Coefficient Unlocks Its Potential for LLM Reinforcement Learning","created":"2025-10-13","cited_by_count":11,"area":"lr"},{"id":"2601.18984","title":"Save the Good Prefix: Precise Error Penalization via Process-Supervised RL to Enhance LLM Reasoning","created":"2026-01-26","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":"2510.11653","title":"MATH-Beyond: A Benchmark for RL to Expand Beyond the Base Model","created":"2025-10-13","cited_by_count":10,"area":"lr"},{"id":"2512.15687","title":"Can LLMs Guide Their Own Exploration? Gradient-Guided Reinforcement Learning for LLM Reasoning","created":"2025-12-17","cited_by_count":10,"area":"lr"},{"id":"2510.07312","title":"h1: Bootstrapping LLMs to Reason over Longer Horizons via Reinforcement Learning","created":"2025-10-08","cited_by_count":9,"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":"2603.02045","title":"Expanding LLM Agent Boundaries with Strategy-Guided Exploration","created":"2026-03-02","cited_by_count":9,"area":"agents"},{"id":"2605.00365","title":"Uniform-Correct Policy Optimization: Breaking RLVR's Indifference to Diversity","created":"2026-05-01","cited_by_count":9,"area":null},{"id":"2510.08892","title":"Exploring Multi-Temperature Strategies for Token- and Rollout-Level Control in RLVR","created":"2025-10-10","cited_by_count":8,"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":"2510.04140","title":"Selective Expert Guidance for Effective and Diverse Exploration in Reinforcement Learning of LLMs","created":"2025-10-05","cited_by_count":7,"area":"lr"},{"id":"2602.01705","title":"LaDi-RL: Latent Diffusion Reasoning Prevents Entropy Collapse in Reinforcement Learning","created":"2026-02-02","cited_by_count":7,"area":"lr"},{"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":"2510.09259","title":"Detecting Data Contamination from Reinforcement Learning Post-training for Large Language Models","created":"2025-10-10","cited_by_count":6,"area":null},{"id":"2601.19928","title":"Towards a Mechanistic Understanding of Large Reasoning Models: A Survey of Training, Inference, and Failures","created":"2026-01-11","cited_by_count":6,"area":"lr"},{"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":"2605.19461","title":"Beyond Mode Collapse: Distribution Matching for Diverse Reasoning","created":"2026-05-19","cited_by_count":6,"area":"lr"},{"id":"2510.01444","title":"Dual-Uncertainty Guided Policy Learning for Multimodal Reasoning","created":"2025-10-01","cited_by_count":5,"area":"lr"},{"id":"2601.21669","title":"Expected Return Causes Outcome-Level Mode Collapse in Reinforcement Learning and How to Fix It with Inverse Probability Scaling","created":"2026-01-29","cited_by_count":5,"area":"deeprl"},{"id":"2604.17654","title":"Poly-EPO: Training Exploratory Reasoning Models","created":"2026-04-19","cited_by_count":5,"area":"lr"},{"id":"2605.01428","title":"Hallucinations Undermine Trust; Metacognition is a Way Forward","created":"2026-05-02","cited_by_count":5,"area":null},{"id":"2510.08539","title":"On the optimization dynamics of RLVR: Gradient gap and step size thresholds","created":"2025-10-09","cited_by_count":4,"area":null},{"id":"2601.15609","title":"When Sharpening Becomes Collapse: Sampling Bias and Semantic Coupling in RL with Verifiable Rewards","created":"2026-01-22","cited_by_count":4,"area":null},{"id":"2606.27359","title":"When are likely answers right? On Sequence Probability and Correctness in LLMs","created":"2026-06-25","cited_by_count":4,"area":null},{"id":"2510.11121","title":"Refining Hybrid Genetic Search for CVRP via Reinforcement Learning-Finetuned LLM","created":"2025-10-13","cited_by_count":3,"area":null},{"id":"2510.26109","title":"Do Not Step Into the Same River Twice: Learning to Reason from Trial and Error","created":"2025-10-30","cited_by_count":3,"area":"lr"},{"id":"2603.20046","title":"Experience is the Best Teacher: Motivating Effective Exploration in Reinforcement Learning for LLMs","created":"2026-03-20","cited_by_count":3,"area":"lr"},{"id":"2603.21877","title":"P^2O: Joint Policy and Prompt Optimization","created":"2026-03-23","cited_by_count":3,"area":"lr"},{"id":"2605.30327","title":"Reasoning with Sampling: Cutting at Decision Points","created":"2026-05-28","cited_by_count":3,"area":"lr"},{"id":"2609.02987","title":"Tail-Likelihood Reinforcement Learning","created":"2026-09-02","cited_by_count":3,"area":"deeprl"},{"id":"2510.17045","title":"Video Reasoning without Training","created":"2025-10-19","cited_by_count":2,"area":"lr"},{"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":"2605.28295","title":"Where Rollouts Begin: Low-Load, High-Leverage First-Token Diversification for RLVR","created":"2026-05-27","cited_by_count":2,"area":"lr"},{"id":"2606.06080","title":"On Advantage Estimates for Max@K Policy Gradients","created":"2026-06-04","cited_by_count":2,"area":"lr"},{"id":"2606.06096","title":"OrderGrad: Optimizing Beyond the Mean with Order-Statistic Policy Gradient Estimation","created":"2026-06-04","cited_by_count":2,"area":"deeprl"},{"id":"2606.10346","title":"Reasoning or Memorization? Direction-Aware Diversity Exploration in LLM Reinforcement Learning","created":"2026-06-09","cited_by_count":2,"area":"lr"},{"id":"2608.02087","title":"Instruction-Conditioned Exploration for Reinforcement Learning with Self-Distillation to an Unconditioned Policy","created":"2026-08-03","cited_by_count":2,"area":"lr"},{"id":"2602.16833","title":"VAM: Verbalized Action Masking for Controllable Exploration in RL Post-Training -- A Chess Case Study","created":"2026-02-18","cited_by_count":1,"area":null},{"id":"2604.11297","title":"The Past Is Not Past: Memory-Enhanced Dynamic Reward Shaping","created":"2026-04-13","cited_by_count":1,"area":null},{"id":"2604.14564","title":"MARS$^2$: Scaling Multi-Agent Tree Search via Reinforcement Learning for Code Generation","created":"2026-04-16","cited_by_count":1,"area":null},{"id":"2605.11813","title":"Automated Reformulation of Robust Optimization via Memory-Augmented Large Language Models","created":"2026-05-12","cited_by_count":1,"area":null},{"id":"2606.03608","title":"Exploiting Verification-Generation Gap: Test-Time Reinforcement Learning with Confidence-Conditioned Verification","created":"2026-06-02","cited_by_count":1,"area":"lr"},{"id":"2606.09926","title":"Sample Where You Struggle: Sharpening Base Model Reasoning via Entropy-Guided Power Sampling","created":"2026-06-07","cited_by_count":1,"area":"lr"},{"id":"2606.31484","title":"Fork-Think with Confidence","created":"2026-06-30","cited_by_count":1,"area":"lr"},{"id":"2607.09693","title":"Depth-Entropy Guided Sampling for Training-Free LLM Reasoning","created":"2026-06-19","cited_by_count":1,"area":"lr"},{"id":"2607.16205","title":"It Takes 8 Tokens: Weak-to-Strong Off-Policy RL via Auxiliary Branches","created":"2026-05-07","cited_by_count":1,"area":"lr"},{"id":"2510.03771","title":"OptAgent: Optimizing Query Rewriting for E-commerce via Multi-Agent Simulation","created":"2025-10-04","cited_by_count":0,"area":"agents"},{"id":"2602.14169","title":"Deep Dense Exploration for LLM Reinforcement Learning via Pivot-Driven Resampling","created":"2026-02-15","cited_by_count":0,"area":"lr"},{"id":"2604.13902","title":"DiPO: Disentangled Perplexity Policy Optimization for Fine-grained Exploration-Exploitation Trade-Off","created":"2026-04-15","cited_by_count":0,"area":"lr"},{"id":"2606.17024","title":"ExpRL: Exploratory RL for LLM Mid-Training","created":"2026-06-15","cited_by_count":0,"area":"lr"},{"id":"2608.29188","title":"Locked at the Entrance, Open Inside: Where RLVR Narrows the Solution Space","created":"2026-08-29","cited_by_count":0,"area":"lr"},{"id":"2608.30345","title":"Answer Probing-Guided Search for Diverse Solution Exploration of LLMs","created":"2026-08-31","cited_by_count":0,"area":null},{"id":"2609.06671","title":"Tracking the Moving Frontier: Long-Short Term Advantage Estimator","created":"2026-09-06","cited_by_count":0,"area":null},{"id":"2609.12317","title":"Sampling via Decision-Flow: Training-Free Extraction of Improved Latent Reasoning Paths in Large Language Models","created":"2026-09-11","cited_by_count":0,"area":"lr"},{"id":"2609.33781","title":"Surprising Success, Repeated Failure: Entropy-Guided Credit Assignment for Exploration in LLM Reasoning","created":"2026-09-27","cited_by_count":0,"area":"lr"},{"id":"2610.01509","title":"Sharpening Tax in Post-Training","created":"2026-10-01","cited_by_count":0,"area":"agents"},{"id":"2610.08563","title":"Adaptive Power Sampling for LLM Reasoning","created":"2026-10-06","cited_by_count":0,"area":"lr"},{"id":"2610.10536","title":"Decoupling Exploration from Optimization in RLVR","created":"2026-10-07","cited_by_count":0,"area":null},{"id":"2610.11064","title":"Measuring and Mitigating Solution Mode Collapse in RLVR","created":"2026-10-08","cited_by_count":0,"area":null},{"id":"2610.19133","title":"TRACER: Trace-Regularized Training Against Indirect Prompt Injection","created":"2026-10-13","cited_by_count":0,"area":"safety"}],"next_cursor":null}