{"total":52,"rows":[{"id":"2602.02710","title":"Maximum Likelihood Reinforcement Learning","created":"2026-02-02","cited_by_count":36,"area":"deeprl"},{"id":"2510.10649","title":"Unlocking Exploration in RLVR: Uncertainty-aware Advantage Shaping for Deeper Reasoning","created":"2025-10-12","cited_by_count":34,"area":"lr"},{"id":"2601.02902","title":"Logical Phase Transitions: Understanding Collapse in LLM Logical Reasoning","created":"2026-01-06","cited_by_count":25,"area":"lr"},{"id":"2601.08605","title":"ExpSeek: Self-Triggered Experience Seeking for Web Agents","created":"2026-01-13","cited_by_count":23,"area":"agents"},{"id":"2512.16301","title":"Adaptation of Agentic AI: A Survey of Post-Training, Memory, and Skills","created":"2025-12-18","cited_by_count":22,"area":"agents"},{"id":"2511.06411","title":"SofT-GRPO: Surpassing Discrete-Token LLM Reinforcement Learning via Gumbel-Reparameterized Soft-Thinking Policy Optimization","created":"2025-11-09","cited_by_count":21,"area":"lr"},{"id":"2512.21625","title":"Rethinking Sample Polarity in Reinforcement Learning with Verifiable Rewards","created":"2025-12-25","cited_by_count":19,"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":"2510.24832","title":"Scheduling Your LLM Reinforcement Learning with Reasoning Trees","created":"2025-10-28","cited_by_count":12,"area":"lr"},{"id":"2602.06717","title":"F-GRPO: Don't Let Your Policy Learn the Obvious and Forget the Rare","created":"2026-02-06","cited_by_count":11,"area":"lr"},{"id":"2601.05053","title":"Reinforced Efficient Reasoning via Semantically Diverse Exploration","created":"2026-01-08","cited_by_count":8,"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":"2602.05548","title":"Unveiling Implicit Advantage Symmetry: Why GRPO Struggles with Exploration and Difficulty Adaptation","created":"2026-02-05","cited_by_count":7,"area":"lr"},{"id":"2601.07036","title":"Mid-Think: Training-Free Intermediate-Budget Reasoning via Token-Level Triggers","created":"2026-01-11","cited_by_count":6,"area":"lr"},{"id":"2604.25444","title":"One Refiner to Unlock Them All: Inference-Time Reasoning Elicitation via Reinforcement Query Refinement","created":"2026-04-28","cited_by_count":6,"area":"lr"},{"id":"2510.21978","title":"Beyond Reasoning Gains: Mitigating General-Capability Forgetting in Large Reasoning Models","created":"2025-10-24","cited_by_count":5,"area":"lr"},{"id":"2601.05607","title":"Orchestrating Tokens and Sequences: Dynamic Hybrid Policy Optimization for RLVR","created":"2026-01-09","cited_by_count":5,"area":"lr"},{"id":"2601.22776","title":"TSPO: Breaking the Double Homogenization Dilemma in Multi-turn Search Policy Optimization","created":"2026-01-30","cited_by_count":5,"area":"lr"},{"id":"2602.01365","title":"When Domains Interact: Asymmetric and Order-Sensitive Cross-Domain Effects in Reinforcement Learning for Reasoning","created":"2026-02-01","cited_by_count":5,"area":"lr"},{"id":"2602.09782","title":"Flexible Entropy Control in RLVR with a Gradient-Preserving Perspective","created":"2026-02-10","cited_by_count":4,"area":"lr"},{"id":"2604.12237","title":"MolMem: Memory-Augmented Agentic Reinforcement Learning for Sample-Efficient Molecular Optimization","created":"2026-04-14","cited_by_count":4,"area":"agents"},{"id":"2605.30159","title":"Meta-Cognitive Memory Policy Optimization for Long-Horizon LLM Agents","created":"2026-05-28","cited_by_count":4,"area":"agents"},{"id":"2511.14258","title":"Entropy-Guided Reasoning Compression","created":"2025-11-18","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":"2605.11491","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":"2606.31575","title":"Which Tokens Matter? Adaptive Token Selection for RLVR with the Relative Surprisal Index","created":"2026-06-30","cited_by_count":3,"area":"lr"},{"id":"2608.08176","title":"Matching Supervision to the Student's Learning Capacity: A Unified Framework for On-Policy Self-Distillation","created":"2026-08-08","cited_by_count":3,"area":"lr"},{"id":"2608.20810","title":"When Images Look Right and Retrieve Wrong: Coverage-Guided Cross-Scale Re-Indexing for Knowledge-Faithful Generative Perception","created":"2026-08-21","cited_by_count":3,"area":null},{"id":"2605.29310","title":"Rubric-Guided Process Reward for Stepwise Model Routing","created":"2026-05-28","cited_by_count":2,"area":"lr"},{"id":"2608.02867","title":"BODHI: Do LLMs Branch Out and Discover Heterogeneous Inferences?","created":"2026-08-03","cited_by_count":2,"area":"lr"},{"id":"2609.06161","title":"All for 1-Bit: Towards Genuine 1-Bit Post-Training Quantization for LLMs","created":"2026-09-05","cited_by_count":2,"area":null},{"id":"2511.04439","title":"CoRPO: Adding a Correctness Bias to GRPO Improves Generalization","created":"2025-11-06","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":"2605.22703","title":"Clipping Bottleneck: Stabilizing RLVR via Stochastic Recovery of Near-Boundary Signals","created":"2026-05-21","cited_by_count":1,"area":"lr"},{"id":"2605.30789","title":"Smaller Models are Natural Explorers for Policy-Level Diversity in GRPO","created":"2026-05-29","cited_by_count":1,"area":"lr"},{"id":"2606.19771","title":"Beyond Entropy: Learning from Token-Level Distributional Deviations for LLM Reasoning","created":"2026-06-18","cited_by_count":1,"area":"lr"},{"id":"2606.28589","title":"Search for Truth from Reasoning: A Dynamic Representation Editing Framework for Steering LLM Trajectories","created":"2026-06-26","cited_by_count":1,"area":"lr"},{"id":"2607.14614","title":"Beyond Entropy: Correctness-Aware Advantage Shaping via Contrastive Policy Optimization","created":"2026-07-16","cited_by_count":1,"area":null},{"id":"2609.40115","title":"Unlearnable, or Unmeasured? On the Reliability of Difficulty Labels in RLVR","created":"2026-09-30","cited_by_count":1,"area":null},{"id":"2510.21830","title":"GAPO: Robust Advantage Estimation for Real-World Code LLMs","created":"2025-10-22","cited_by_count":0,"area":"lr"},{"id":"2605.11538","title":"Taming Extreme Tokens: Covariance-Aware GRPO with Gaussian-Kernel Advantage Reweighting","created":"2026-05-12","cited_by_count":0,"area":"lr"},{"id":"2605.26893","title":"GeoFaith: A Spatio-Temporal Dual View of Faithful Chain-of-Thought","created":"2026-05-26","cited_by_count":0,"area":"lr"},{"id":"2606.21911","title":"The Pitfall of Scaling Up: Uncovering and Mitigating Popularity Bias Amplification in Scaling Transformer-based Recommenders","created":"2026-06-20","cited_by_count":0,"area":null},{"id":"2606.28707","title":"BV-Blend: Uncertainty-Weighted Historical Baselines for Stable Critic-Free RL with Verifiable Rewards","created":"2026-06-27","cited_by_count":0,"area":"lr"},{"id":"2607.03126","title":"ACPO: Asymmetric Credit Policy Optimization via Mode-Local Entropy Surrogate","created":"2026-07-03","cited_by_count":0,"area":"lr"},{"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":"2609.33398","title":"COEVO: Co-Evolving Context and Parameters for Recursive Self-Improvement","created":"2026-09-27","cited_by_count":0,"area":"synth"},{"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":"2610.05048","title":"E$^2$-OPSD: Taming Entropy Overshoot in On-Policy Self-Distillation","created":"2026-10-04","cited_by_count":0,"area":"distill"},{"id":"2610.07342","title":"Rationale-Guided Policy Optimization: Learning to Reason with Adaptive Rationale Scaffolding","created":"2026-10-05","cited_by_count":0,"area":"lr"},{"id":"2610.11854","title":"GRPODropout: Less is More for Online Reinforcement Learning Rollouts","created":"2026-10-08","cited_by_count":0,"area":"lr"}],"next_cursor":null}