{"total":56,"rows":[{"id":"2602.05842","title":"Reinforcement World Model Learning for LLM-based Agents","created":"2026-02-05","cited_by_count":24,"area":"wm"},{"id":"2609.04172","title":"Rethinking On-Policy Distillation of Large Language Models II: One Training Example","created":"2026-09-03","cited_by_count":24,"area":"distill"},{"id":"2603.22446","title":"Sparse but Critical: A Token-Level Analysis of Distributional Shifts in RLVR Fine-Tuning of LLMs","created":"2026-03-23","cited_by_count":20,"area":"lr"},{"id":"2606.07082","title":"On the Geometry of On-Policy Distillation","created":"2026-06-05","cited_by_count":19,"area":"lr"},{"id":"2603.26666","title":"VLA-OPD: Bridging Offline SFT and Online RL for Vision-Language-Action Models via On-Policy Distillation","created":"2026-03-27","cited_by_count":13,"area":"vla"},{"id":"2512.23165","title":"Evaluating Parameter Efficient Methods for RLVR","created":"2025-12-29","cited_by_count":12,"area":null},{"id":"2602.01058","title":"Good SFT Optimizes for SFT, Better SFT Prepares for Reinforcement Learning","created":"2026-02-01","cited_by_count":11,"area":"lr"},{"id":"2602.12566","title":"To Mix or To Merge: Toward Multi-Domain Reinforcement Learning for Large Language Models","created":"2026-02-13","cited_by_count":11,"area":"lr"},{"id":"2606.13657","title":"Dense Supervision, Sparse Updates: On the Sparsity and Geometry of On-Policy Distillation","created":"2026-06-11","cited_by_count":10,"area":"distill"},{"id":"2602.00173","title":"Learning Robust Reasoning through Guided Adversarial Self-Play","created":"2026-01-30","cited_by_count":8,"area":"lr"},{"id":"2605.19282","title":"Rethinking Muon Beyond Pretraining: Spectral Failures and High-Pass Remedies for VLA and RLVR","created":"2026-05-19","cited_by_count":8,"area":"lr"},{"id":"2602.03839","title":"Understanding and Exploiting Weight Update Sparsity for Communication-Efficient Distributed RL","created":"2026-02-03","cited_by_count":7,"area":null},{"id":"2602.07729","title":"Do We Need Adam? Surprisingly Strong and Sparse Reinforcement Learning with SGD in LLMs","created":"2026-02-07","cited_by_count":7,"area":null},{"id":"2607.01763","title":"Denser $\\neq$ Better: Limits of On-Policy Self-Distillation for Continual Post-Training","created":"2026-07-02","cited_by_count":7,"area":"distill"},{"id":"2603.01228","title":"Towards Policy-Adaptive Image Guardrail: Benchmark and Method","created":"2026-03-01","cited_by_count":6,"area":"safety"},{"id":"2604.05306","title":"LLMs Should Express Uncertainty Explicitly","created":"2026-04-07","cited_by_count":6,"area":null},{"id":"2605.12492","title":"Pion: A Spectrum-Preserving Optimizer via Orthogonal Equivalence Transformation","created":"2026-05-12","cited_by_count":6,"area":null},{"id":"2512.17375","title":"AdvJudge-Zero: Binary Decision Flips in LLM-as-a-Judge via Adversarial Control Tokens","created":"2025-12-19","cited_by_count":4,"area":"alignment"},{"id":"2601.04537","title":"Linear Dynamics in the RLVR Training of Large Language Models","created":"2026-01-08","cited_by_count":4,"area":"lr"},{"id":"2601.09361","title":"GeoRA: Geometry-Aware Low-Rank Adaptation for RLVR","created":"2026-01-14","cited_by_count":4,"area":"lr"},{"id":"2601.11258","title":"Knowledge is Not Enough: Injecting RL Skills for Continual Adaptation","created":"2026-01-16","cited_by_count":4,"area":null},{"id":"2602.12395","title":"What does RL improve for Visual Reasoning? A Frankenstein-Style Analysis","created":"2026-02-12","cited_by_count":4,"area":"lr"},{"id":"2601.18832","title":"The Geometric Reasoner: Manifold-Informed Latent Foresight Search for Long-Context Reasoning","created":"2026-01-25","cited_by_count":3,"area":"lr"},{"id":"2602.01599","title":"The Multiple Ticket Hypothesis: Random Sparse Subnetworks Suffice for RLVR","created":"2026-02-02","cited_by_count":3,"area":null},{"id":"2605.10973","title":"Rotation-Preserving Supervised Fine-Tuning","created":"2026-05-08","cited_by_count":3,"area":null},{"id":"2605.21468","title":"You Only Need Minimal RLVR Training: Extrapolating LLMs via Rank-1 Trajectories","created":"2026-05-20","cited_by_count":3,"area":"lr"},{"id":"2605.28819","title":"PEFT-Arena: Understanding Parameter-Efficient Finetuning from a Stability-Plasticity Perspective","created":"2026-05-27","cited_by_count":3,"area":null},{"id":"2606.02437","title":"On the Scaling of PEFT: Towards Million Personal Models of Trillion Parameters","created":"2026-06-01","cited_by_count":3,"area":null},{"id":"2601.18129","title":"Typhoon-S: Minimal Open Post-Training for Sovereign Large Language Models","created":"2026-01-26","cited_by_count":2,"area":null},{"id":"2607.19331","title":"ISO: An RLVR-Native Optimization Stack","created":"2026-07-21","cited_by_count":2,"area":"lr"},{"id":"2608.03573","title":"SFT Conflicts, RL Coexists: A Theoretical and Empirical Analysis of Multi-Task Learning for LLMs","created":"2026-08-04","cited_by_count":2,"area":"lr"},{"id":"2512.06533","title":"Beyond Token-level Supervision: Unlocking the Potential of Decoding-based Regression via Reinforcement Learning","created":"2025-12-06","cited_by_count":1,"area":"deeprl"},{"id":"2604.04231","title":"Subspace Control: Turning Constrained Model Steering into Controllable Spectral Optimization","created":"2026-04-05","cited_by_count":1,"area":"safety"},{"id":"2605.00610","title":"Decouple before Integration: Test-time Synthesis of SFT and RLVR Task Vectors","created":"2026-05-01","cited_by_count":1,"area":null},{"id":"2605.07330","title":"SparseRL-Sync: Lossless Weight Synchronization with ~100x Less Communication","created":"2026-05-08","cited_by_count":1,"area":"deeprl"},{"id":"2606.05145","title":"Failed Reasoning Traces Tell You What Is Fixable (But Not by Reading Them)","created":"2026-06-03","cited_by_count":1,"area":"lr"},{"id":"2607.18985","title":"Athena-Brain Technical Report: An Efficient Robot Brain for General Intelligence and Embodied Interaction","created":"2026-07-21","cited_by_count":1,"area":null},{"id":"2607.22676","title":"How LLM Task-Adaptation Reshapes Alignment: A Multi-dimensional Study of Behavioral and Representational Drift","created":"2026-07-10","cited_by_count":1,"area":null},{"id":"2609.36484","title":"The Teacher Is a Direction, Not a Destination: Extrapolating RL-Induced Representation Residuals in On-Policy Distillation","created":"2026-09-29","cited_by_count":1,"area":"distill"},{"id":"2601.21192","title":"Do Reasoning Models Enhance Embedding Models?","created":"2026-01-29","cited_by_count":0,"area":"lr"},{"id":"2602.11717","title":"Beyond Parameter Arithmetic: Sparse Complementary Fusion for Distribution-Aware Model Merging","created":"2026-02-12","cited_by_count":0,"area":null},{"id":"2606.19222","title":"Mechanism-Guided Selective Unlearning for RLVR-Induced Reasoning","created":"2026-06-17","cited_by_count":0,"area":"safety"},{"id":"2606.19750","title":"Manifold Bandits: Bayesian Curriculum Learning over the Latent Geometry of Large Language Models","created":"2026-06-18","cited_by_count":0,"area":"lr"},{"id":"2606.31813","title":"Geometry-Preserving Orthonormal Initialization for Low-Rank Adaptation in RLVR","created":"2026-06-30","cited_by_count":0,"area":null},{"id":"2607.18532","title":"Reasoning Fine-Tuning Induces Persistent Latent Policy States","created":"2026-07-20","cited_by_count":0,"area":"lr"},{"id":"2608.07786","title":"Who Built This Model? Tracing LLM Lineage via Spectral Fingerprints in Weight Space","created":"2026-08-07","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":"2609.22146","title":"GRRR: The Geometry of Reshaping, Rotation, and Routing in Decoder LLM post-training","created":"2026-08-26","cited_by_count":0,"area":null},{"id":"2609.32996","title":"Oracle Gaps in Reliability Coverage: Sampling Noise or Policy Specialization?","created":"2026-09-26","cited_by_count":0,"area":null},{"id":"2609.33780","title":"Selecting Diverse SFT Traces Improves Post-RL Generalization","created":"2026-09-27","cited_by_count":0,"area":"lr"},{"id":"2609.34344","title":"Learning to Steer, Steering to See: Unveiling the Geometry of RLVR in Large Language Models via Trainable Vectors","created":"2026-09-28","cited_by_count":0,"area":"lr"},{"id":"2609.36262","title":"Understanding LLM Parameter Update Sparsity through the Lens of Fisher","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2609.36659","title":"On-Policy Parameter Update Direction Underlies Generalization in LLM Post-Training","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2610.11247","title":"Why On-Policy Distillation Sometimes Fails: Vanishing Learning Signals","created":"2026-10-08","cited_by_count":0,"area":"distill"},{"id":"2610.14270","title":"The Thinking Leakage in Reinforcement Learning for LLMs","created":"2026-10-09","cited_by_count":0,"area":"lr"},{"id":"2610.18634","title":"Geometric Calibration of Supervised Fine-Tuning","created":"2026-10-13","cited_by_count":0,"area":null}],"next_cursor":null}