{"total":85,"rows":[{"id":"2505.22617","title":"The Entropy Mechanism of Reinforcement Learning for Reasoning Language Models","created":"2025-05-28","cited_by_count":485,"area":"lr"},{"id":"2601.20802","title":"Reinforcement Learning via Self-Distillation","created":"2026-01-28","cited_by_count":332,"area":"lr"},{"id":"2504.14945","title":"Learning to Reason under Off-Policy Guidance","created":"2025-04-21","cited_by_count":281,"area":"lr"},{"id":"2506.14758","title":"Reasoning with Exploration: An Entropy Perspective","created":"2025-06-17","cited_by_count":281,"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":"2405.10292","title":"Fine-Tuning Large Vision-Language Models as Decision-Making Agents via Reinforcement Learning","created":"2024-05-16","cited_by_count":158,"area":"lr"},{"id":"2505.23399","title":"GAM-Agent: Game-Theoretic and Uncertainty-Aware Collaboration for Complex Visual Reasoning","created":"2025-05-29","cited_by_count":58,"area":"lr"},{"id":"2412.16145","title":"Offline Reinforcement Learning for LLM Multi-Step Reasoning","created":"2024-12-20","cited_by_count":54,"area":"lr"},{"id":"2510.10150","title":"Rethinking Entropy Interventions in RLVR: An Entropy Change Perspective","created":"2025-10-11","cited_by_count":52,"area":"lr"},{"id":"2509.15207","title":"FlowRL: Matching Reward Distributions for LLM Reasoning","created":"2025-09-18","cited_by_count":40,"area":"lr"},{"id":"2309.06553","title":"Query-Dependent Prompt Evaluation and Optimization with Offline Inverse RL","created":"2023-09-13","cited_by_count":37,"area":"lr"},{"id":"2207.09081","title":"Generalizing Goal-Conditioned Reinforcement Learning with Variational Causal Reasoning","created":"2022-07-19","cited_by_count":34,"area":"lr"},{"id":"2501.17974","title":"Think Smarter not Harder: Adaptive Reasoning with Inference Aware Optimization","created":"2025-01-29","cited_by_count":29,"area":"lr"},{"id":"2509.09675","title":"CDE: Curiosity-Driven Exploration for Efficient Reinforcement Learning in Large Language Models","created":"2025-09-11","cited_by_count":29,"area":"lr"},{"id":"2509.26209","title":"Diversity-Incentivized Exploration for Versatile Reasoning","created":"2025-09-30","cited_by_count":28,"area":"lr"},{"id":"2301.00355","title":"Second Thoughts are Best: Learning to Re-Align With Human Values from Text Edits","created":"2023-01-01","cited_by_count":27,"area":"lr"},{"id":"2410.15595","title":"A Comprehensive Survey of Direct Preference Optimization: Datasets, Theories, Variants, and Applications","created":"2024-10-21","cited_by_count":27,"area":"lr"},{"id":"2509.20712","title":"CE-GPPO: Coordinating Entropy via Gradient-Preserving Clipping Policy Optimization in Reinforcement Learning","created":"2025-09-25","cited_by_count":23,"area":"lr"},{"id":"2410.09302","title":"Enhancing Multi-Step Reasoning Abilities of Language Models through Direct Q-Function Optimization","created":"2024-10-11","cited_by_count":22,"area":"lr"},{"id":"2507.04136","title":"A Technical Survey of Reinforcement Learning Techniques for Large Language Models","created":"2025-07-05","cited_by_count":21,"area":"lr"},{"id":"2508.02260","title":"Decomposing the Entropy-Performance Exchange: The Missing Keys to Unlocking Effective Reinforcement Learning","created":"2025-08-04","cited_by_count":21,"area":"lr"},{"id":"2505.16826","title":"KTAE: A Model-Free Algorithm to Key-Tokens Advantage Estimation in Mathematical Reasoning","created":"2025-05-22","cited_by_count":19,"area":"lr"},{"id":"2508.04349","title":"GTPO and GRPO-S: Token and Sequence-Level Reward Shaping with Policy Entropy","created":"2025-08-06","cited_by_count":18,"area":"lr"},{"id":"2505.23363","title":"Discriminative Policy Optimization for Token-Level Reward Models","created":"2025-05-29","cited_by_count":16,"area":"lr"},{"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":"2502.20548","title":"$Q\\sharp$: Provably Optimal Distributional RL for LLM Post-Training","created":"2025-02-27","cited_by_count":15,"area":"lr"},{"id":"2507.06892","title":"Squeeze the Soaked Sponge: Efficient Off-policy Reinforcement Finetuning for Large Language Model","created":"2025-07-09","cited_by_count":14,"area":"lr"},{"id":"2507.08182","title":"CTRLS: Chain-of-Thought Reasoning via Latent State-Transition","created":"2025-07-10","cited_by_count":14,"area":"lr"},{"id":"2602.19208","title":"How to Allocate, How to Learn? Dynamic Rollout Allocation and Advantage Modulation for Policy Optimization","created":"2026-02-22","cited_by_count":14,"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":"2510.08141","title":"SCOPE-RL: Stable and Quantitative Control of Policy Entropy in RL Post-Training","created":"2025-10-09","cited_by_count":12,"area":"lr"},{"id":"2506.05850","title":"Cross-lingual Collapse: How Language-Centric Foundation Models Shape Reasoning in Large Language Models","created":"2025-06-06","cited_by_count":11,"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":"2603.11682","title":"Entropy-Preserving Reinforcement Learning","created":"2026-03-12","cited_by_count":11,"area":"lr"},{"id":"2510.05251","title":"Let it Calm: Exploratory Annealed Decoding for Verifiable Reinforcement Learning","created":"2025-10-06","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":"2602.01288","title":"EDIS: Diagnosing LLM Reasoning via Entropy Dynamics","created":"2026-02-01","cited_by_count":10,"area":"lr"},{"id":"2505.20561","title":"Beyond Markovian: Reflective Exploration via Bayes-Adaptive RL for LLM Reasoning","created":"2025-05-26","cited_by_count":9,"area":"lr"},{"id":"2505.18917","title":"Behavior Injection: Preparing Language Models for Reinforcement Learning","created":"2025-05-25","cited_by_count":8,"area":"lr"},{"id":"2512.04601","title":"Natural Language Actor-Critic: Scalable Off-Policy Learning in Language Space","created":"2025-12-04","cited_by_count":8,"area":"lr"},{"id":"2512.04748","title":"Model Whisper: Steering Vectors Unlock Large Language Models' Potential in Test-time","created":"2025-12-04","cited_by_count":7,"area":"lr"},{"id":"2512.23515","title":"Alpha-R1: Alpha Screening with LLM Reasoning via Reinforcement Learning","created":"2025-12-29","cited_by_count":7,"area":"lr"},{"id":"2508.16129","title":"Bridging the Gap in Ophthalmic AI: MM-Retinal-Reason Dataset and OphthaReason Model toward Dynamic Multimodal Reasoning","created":"2025-08-22","cited_by_count":6,"area":"lr"},{"id":"2512.04359","title":"Efficient Reinforcement Learning with Semantic and Token Entropy for LLM Reasoning","created":"2025-12-04","cited_by_count":6,"area":"lr"},{"id":"2601.03320","title":"Ratio-Variance Regularized Policy Optimization for Efficient LLM Fine-tuning","created":"2026-01-06","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":"2509.12718","title":"EvoEmpirBench: Dynamic Spatial Reasoning with Agent-ExpVer","created":"2025-09-16","cited_by_count":5,"area":"lr"},{"id":"2602.04417","title":"EMA Policy Gradient: Taming Reinforcement Learning for LLMs with EMA Anchor and Top-k KL","created":"2026-02-04","cited_by_count":5,"area":"lr"},{"id":"2604.17654","title":"Poly-EPO: Training Exploratory Reasoning Models","created":"2026-04-19","cited_by_count":5,"area":"lr"},{"id":"2512.16824","title":"Tiny Recursive Control: Iterative Reasoning for Efficient Optimal Control","created":"2025-12-18","cited_by_count":4,"area":"lr"},{"id":"2505.11175","title":"Real-Time Verification of Embodied Reasoning for Generative Skill Acquisition","created":"2025-05-16","cited_by_count":3,"area":"lr"},{"id":"2507.20150","title":"The Policy Cliff: A Theoretical Analysis of Reward-Policy Maps in Large Language Models","created":"2025-07-27","cited_by_count":3,"area":"lr"},{"id":"2509.23183","title":"ZeroSiam: An Efficient Asymmetry for Test-Time Entropy Optimization without Collapse","created":"2025-09-27","cited_by_count":3,"area":"lr"},{"id":"2510.09369","title":"Token-Level Policy Optimization: Linking Group-Level Rewards to Token-Level Aggregation via Markov Likelihood","created":"2025-10-10","cited_by_count":3,"area":"lr"},{"id":"2602.22751","title":"Know What You Know: Metacognitive Entropy Calibration for Verifiable RL Reasoning","created":"2026-02-26","cited_by_count":3,"area":"lr"},{"id":"2604.14646","title":"Targeted Exploration via Unified Entropy Control for Reinforcement Learning","created":"2026-04-16","cited_by_count":3,"area":"lr"},{"id":"2605.06139","title":"Listwise Policy Optimization: Group-based RLVR as Target-Projection on the LLM Response Simplex","created":"2026-05-07","cited_by_count":3,"area":"lr"},{"id":"2605.11491","title":"Understanding and Preventing Entropy Collapse in RLVR with On-Policy Entropy Flow Optimization","created":"2026-05-12","cited_by_count":3,"area":"lr"},{"id":"2606.19236","title":"STARE: Surprisal-Guided Token-Level Advantage Reweighting for Policy Entropy Stability","created":"2026-06-17","cited_by_count":3,"area":"lr"},{"id":"2210.06766","title":"Policy Gradient With Serial Markov Chain Reasoning","created":"2022-10-13","cited_by_count":2,"area":"lr"},{"id":"2408.14855","title":"Enhancing Analogical Reasoning in the Abstraction and Reasoning Corpus via Model-Based RL","created":"2024-08-27","cited_by_count":2,"area":"lr"},{"id":"2601.19620","title":"R^3: Replay, Reflection, and Ranking Rewards for LLM Reinforcement Learning","created":"2026-01-27","cited_by_count":2,"area":"lr"},{"id":"2606.08543","title":"PAEC: Position-Aware Entropy Calibration for LLM Reasoning in RLVR","created":"2026-06-07","cited_by_count":2,"area":"lr"},{"id":"2505.10992","title":"ReaCritic: Reasoning Transformer-based DRL Critic-model Scaling For Wireless Networks","created":"2025-05-16","cited_by_count":1,"area":"lr"},{"id":"2506.01623","title":"MAGIK: Mapping to Analogous Goals via Imagination-enabled Knowledge Transfer","created":"2025-06-02","cited_by_count":1,"area":"lr"},{"id":"2507.02256","title":"Uncertainty-aware Reward Design Process","created":"2025-07-03","cited_by_count":1,"area":"lr"},{"id":"2512.24555","title":"From Perception to Punchline: Empowering VLM with the Art of In-the-wild Meme","created":"2025-12-31","cited_by_count":1,"area":"lr"},{"id":"2601.03895","title":"All-Quadrant Bounded Clipping GRPO: Closing the Unbounded Blind Spot for Stable and Generalizable Training","created":"2026-01-07","cited_by_count":1,"area":"lr"},{"id":"2601.22478","title":"Transformation-Augmented GRPO for Enhancing Exploration in Reasoning of Large Language Models","created":"2026-01-30","cited_by_count":1,"area":"lr"},{"id":"2604.04894","title":"Asymmetric Advantage Modulation Calibrates Entropy Dynamics in RLVR","created":"2026-04-06","cited_by_count":1,"area":"lr"},{"id":"2604.12736","title":"Token-Level Policy Optimization: Linking Group-Level Rewards to Token-Level Aggregation via Sequence-Level Likelihood","created":"2026-04-14","cited_by_count":1,"area":"lr"},{"id":"2507.16473","title":"Learning Temporal Abstractions via Variational Homomorphisms in Option-Induced Abstract MDPs","created":"2025-07-22","cited_by_count":0,"area":"lr"},{"id":"2512.10414","title":"Boosting RL-Based Visual Reasoning with Selective Adversarial Entropy Intervention","created":"2025-12-11","cited_by_count":0,"area":"lr"},{"id":"2601.12212","title":"Speculative Sampling with Reinforcement Learning","created":"2026-01-18","cited_by_count":0,"area":"lr"},{"id":"2603.23355","title":"Off-Policy Value-Based Reinforcement Learning for Large Language Models","created":"2026-03-24","cited_by_count":0,"area":"lr"},{"id":"2603.23964","title":"From Pixels to Digital Agents: An Empirical Study on the Taxonomy and Technological Trends of Reinforcement Learning Environments","created":"2026-03-25","cited_by_count":0,"area":"lr"},{"id":"2604.09676","title":"A Comparative Theoretical Analysis of Entropy Control Methods in Reinforcement Learning","created":"2026-04-02","cited_by_count":0,"area":"lr"},{"id":"2605.12058","title":"Holder Policy Optimisation","created":"2026-05-12","cited_by_count":0,"area":"lr"},{"id":"2605.27846","title":"EAPO: Entropy-Driven Adaptive Positive-Negative Sample Weighting for Policy Optimization in Open-Ended QA","created":"2026-05-27","cited_by_count":0,"area":"lr"},{"id":"2606.05434","title":"Selective-Advantage Entropy-Adaptive Horizon GRPO: Asymmetric Token-Level Discounting for Efficient Reinforcement Learning of Language Models","created":"2026-06-03","cited_by_count":0,"area":"lr"},{"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":"2607.21626","title":"Discrete Action Space as a Prerequisite for GRPO Convergence in Small-Model Continuous Control","created":"2026-07-07","cited_by_count":0,"area":"lr"},{"id":"2609.28625","title":"RLVR landscapes for iterated multiplications can be benign: Insights from spin-glass theory","created":"2026-09-23","cited_by_count":0,"area":"lr"},{"id":"2610.02478","title":"Tropical Reinforcement Learning","created":"2026-10-01","cited_by_count":0,"area":"lr"},{"id":"2610.03361","title":"Follow the Winners: Conservative Policy Improvement with the Cross-Entropy Method for Critic-Free RFT","created":"2026-10-02","cited_by_count":0,"area":"lr"}],"next_cursor":null}