{"total":66,"rows":[{"id":"2602.05547","title":"Multi-Task GRPO: Reliable LLM Reasoning Across Tasks","created":"2026-02-05","cited_by_count":14,"area":"lr"},{"id":"2601.10201","title":"Future-KL Regularized GRPO: Process-Level Credit Assignment from $f$-Divergence Regularization","created":"2026-01-15","cited_by_count":12,"area":"lr"},{"id":"2602.03048","title":"CoBA-RL: Capability-Oriented Budget Allocation for Reinforcement Learning in LLMs","created":"2026-02-03","cited_by_count":12,"area":"lr"},{"id":"2602.10560","title":"When to Memorize and When to Stop: Gated Recurrent Memory for Long-Context Reasoning","created":"2026-02-11","cited_by_count":9,"area":"lr"},{"id":"2604.02869","title":"Multi-Turn Reinforcement Learning for Tool-Calling Agents with Iterative Reward Calibration","created":"2026-04-03","cited_by_count":7,"area":"lr"},{"id":"2605.26958","title":"Tournament-GRPO: Group-Wise Tournament Rewards for Reinforcement Learning in Open-Ended Long-Form Generation","created":"2026-05-26","cited_by_count":7,"area":"lr"},{"id":"2604.08476","title":"Faithful GRPO: Improving Visual Spatial Reasoning in Multimodal Language Models via Constrained Policy Optimization","created":"2026-04-09","cited_by_count":6,"area":"lr"},{"id":"2606.15441","title":"Defending against Adaptive Prompt Injection Attacks via Reasoning-enabled Task Alignment","created":"2026-06-13","cited_by_count":6,"area":"lr"},{"id":"2606.09701","title":"Learning to Attack and Defend: Adaptive Red Teaming of Language Models via GRPO","created":"2026-06-08","cited_by_count":5,"area":"lr"},{"id":"2607.21273","title":"The Dark Room in the Reward Channel: Dense Prediction Rewards Collapse GRPO-Trained LLM Agents -- and The Channel, Not the Content, Decides What Works","created":"2026-07-23","cited_by_count":5,"area":"lr"},{"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":"2602.13407","title":"On-Policy Supervised Fine-Tuning for Efficient Reasoning","created":"2026-02-13","cited_by_count":4,"area":"lr"},{"id":"2608.20492","title":"Annotations as Rollouts: Efficient and Scalable Reinforcement Learning for Video MLLMs","created":"2026-08-20","cited_by_count":4,"area":"lr"},{"id":"2602.01034","title":"Discovering Process-Outcome Credit in Multi-Step LLM Reasoning","created":"2026-02-01","cited_by_count":3,"area":"lr"},{"id":"2606.17362","title":"DriveJudge: Rethinking Autonomous Driving Evaluation with Vision-Language Models","created":"2026-06-15","cited_by_count":3,"area":"lr"},{"id":"2606.18216","title":"Zone of Proximal Policy Optimization: Teacher in Prompts, Not Gradients","created":"2026-06-16","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":"2607.01191","title":"Perceive-to-Reason: Decoupling Perception and Reasoning for Fine-Grained Visual Reasoning","created":"2026-07-01","cited_by_count":3,"area":"lr"},{"id":"2602.05863","title":"Constrained Group Relative Policy Optimization","created":"2026-02-05","cited_by_count":2,"area":"lr"},{"id":"2603.18118","title":"Insight-V++: Towards Advanced Long-Chain Visual Reasoning with Multimodal Large Language Models","created":"2026-03-18","cited_by_count":2,"area":"lr"},{"id":"2605.25443","title":"Harmony in Diversity: Multi-domain Contrastive Policy Optimization for Large Reasoning Models","created":"2026-05-25","cited_by_count":2,"area":"lr"},{"id":"2606.21943","title":"Modularized Reinforcement Learning on LLMs: From MDP Creation to Exploration and Learning","created":"2026-06-20","cited_by_count":2,"area":"lr"},{"id":"2606.29296","title":"Process Advantage Signal Shaping: A Paradigm-Agnostic Middleware for Process-Supervised RL in LLM Reasoners","created":"2026-06-28","cited_by_count":2,"area":"lr"},{"id":"2606.31825","title":"Breaking Failure Cascades: Step-Aware Reinforcement Learning for Medical Multimodal Reasoning","created":"2026-06-30","cited_by_count":2,"area":"lr"},{"id":"2607.25659","title":"CoRT: Counterfactual Replay for Token-Level Rubric-Guided Policy Optimization","created":"2026-07-28","cited_by_count":2,"area":"lr"},{"id":"2608.16072","title":"Learn What's Left, Not What's Mastered: Saturation Aware Advantage Reweighting for Multi-Reward Policy Optimization","created":"2026-08-17","cited_by_count":2,"area":"lr"},{"id":"2601.14686","title":"IB-GRPO: Aligning LLM-based Learning Path Recommendation with Educational Objectives via Indicator-Based Group Relative Policy Optimization","created":"2026-01-21","cited_by_count":1,"area":"lr"},{"id":"2602.03190","title":"PrAg-PO: Prompt Augmented Policy Optimization for Robust and Diverse Mathematical Reasoning","created":"2026-02-03","cited_by_count":1,"area":"lr"},{"id":"2604.16893","title":"EasyVideoR1: Easier RL for Video Understanding","created":"2026-04-18","cited_by_count":1,"area":"lr"},{"id":"2604.18187","title":"Audio-DeepThinker: Progressive Reasoning-Aware Reinforcement Learning for High-Quality Chain-of-Thought Emergence in Audio Language Models","created":"2026-04-20","cited_by_count":1,"area":"lr"},{"id":"2605.06650","title":"Beyond Negative Rollouts: Positive-Only Policy Optimization with Implicit Negative Gradients","created":"2026-05-07","cited_by_count":1,"area":"lr"},{"id":"2605.18843","title":"TEMPO: Temporal Enforcement via Mode-Separated Policy Optimization for Trustworthy LLM Backtesting","created":"2026-05-13","cited_by_count":1,"area":"lr"},{"id":"2605.27820","title":"EgoBench: An Interactive Egocentric Multimodal Benchmark for Tool-Using Agents","created":"2026-05-27","cited_by_count":1,"area":"lr"},{"id":"2606.09290","title":"Visual Para-Thinker++: A Single-Policy Multi-Agent Framework for Visual Reasoning","created":"2026-06-08","cited_by_count":1,"area":"lr"},{"id":"2608.08009","title":"Evidence-Grounded Forensic Reasoning for Detecting and Grounding Multi-Modal Media Manipulation","created":"2026-08-08","cited_by_count":1,"area":"lr"},{"id":"2608.30632","title":"GMTS: Gradient Magnitude-based Token Selection Improves RLVR Training for LLM Reasoning","created":"2026-08-31","cited_by_count":1,"area":"lr"},{"id":"2603.12166","title":"LatentGeo: Learnable Auxiliary Constructions in Latent Space for Multimodal Geometric Reasoning","created":"2026-03-12","cited_by_count":0,"area":"lr"},{"id":"2605.04499","title":"Pen-Strategist: A Reasoning Framework for Penetration Testing Strategy Formation and Analysis","created":"2026-05-06","cited_by_count":0,"area":"lr"},{"id":"2605.07276","title":"Signal Reshaping for GRPO in Weak-Feedback Agentic Code Repair","created":"2026-05-08","cited_by_count":0,"area":"lr"},{"id":"2605.09806","title":"LEAD: Length-Efficient Adaptive and Dynamic Reasoning for Large Language Models","created":"2026-05-10","cited_by_count":0,"area":"lr"},{"id":"2605.13534","title":"Scaling Retrieval-Augmented Reasoning with Parallel Search and Explicit Merging","created":"2026-05-13","cited_by_count":0,"area":"lr"},{"id":"2605.22620","title":"Two is better than one: A Collapse-free Multi-Reward RLIF Training Framework","created":"2026-05-21","cited_by_count":0,"area":"lr"},{"id":"2605.25511","title":"CRPO: Character-centric Group Relative Policy Optimization for Role-aware Reasoning in Role-playing Agents","created":"2026-05-25","cited_by_count":0,"area":"lr"},{"id":"2605.29076","title":"Structured Prompt Optimization Meets Reinforcement Learning for Global and Local Interpretability over Complex Text","created":"2026-05-27","cited_by_count":0,"area":"lr"},{"id":"2606.08088","title":"ConSteer-RL: Steering Reasoning Capabilities in Large Language Models via Confidence-Aware Reinforcement Learning","created":"2026-06-06","cited_by_count":0,"area":"lr"},{"id":"2606.08875","title":"Can the Environment Speak for Itself? $T^{2}$-GRPO: A Turn-Trajectory Group Relative Policy Optimization for Caregiver Agents","created":"2026-06-07","cited_by_count":0,"area":"lr"},{"id":"2606.10931","title":"It Takes One to Bias Them All: Breaking Bad with One-Shot GRPO","created":"2026-06-09","cited_by_count":0,"area":"lr"},{"id":"2606.14694","title":"AdaSR: Adaptive Streaming Reasoning with Hierarchical Relative Policy Optimization","created":"2026-06-12","cited_by_count":0,"area":"lr"},{"id":"2607.01927","title":"TUDUM: A Turkish-Thinking Reasoning Pipeline for Qwen3.5-27B","created":"2026-07-02","cited_by_count":0,"area":"lr"},{"id":"2607.06522","title":"Bridging Physical Reasoning and Task Generalization via Visual Action Outcome Reasoning Alignment","created":"2026-07-07","cited_by_count":0,"area":"lr"},{"id":"2607.13539","title":"ThinkBLOX: 3D Indoor Scene Generation with Progressive Reasoning","created":"2026-07-15","cited_by_count":0,"area":"lr"},{"id":"2608.15594","title":"TRACE: Trajectory Aware Reasoning for Multi-Turn Adversarial Conversation Evaluation","created":"2026-08-16","cited_by_count":0,"area":"lr"},{"id":"2608.27982","title":"Learning from Hard Prompts: Difficulty-aware Advantage Amplification in Dynamic Sampling","created":"2026-08-28","cited_by_count":0,"area":"lr"},{"id":"2608.28771","title":"ERR+: Sequential Entropy Resolution for Efficient and Decisive LLM Reasoning","created":"2026-08-28","cited_by_count":0,"area":"lr"},{"id":"2609.08867","title":"SeGDeP: Semantic- and Geometric-Aware Decoupled Prompts for Reasoning Segmentation","created":"2026-09-08","cited_by_count":0,"area":"lr"},{"id":"2609.10815","title":"BodyCam-VQA: Enhanced Body-Worn Camera Video Captioning via Multimodal Reasoning and Probe Question Generation","created":"2026-09-09","cited_by_count":0,"area":"lr"},{"id":"2609.30906","title":"ToolSearcher: Optimizing Tool Selection at Scale via Reinforcement Learning","created":"2026-09-25","cited_by_count":0,"area":"lr"},{"id":"2609.33119","title":"MedRouter: Demystifying Knowledge Differences Across Medical LLMs for Routing-Based Reasoning","created":"2026-09-27","cited_by_count":0,"area":"lr"},{"id":"2609.35942","title":"Question-Specific Knowledge Graphs for Efficient Visual Reasoning","created":"2026-09-28","cited_by_count":0,"area":"lr"},{"id":"2609.36820","title":"CorrGRPO: Correlation-Normalized GRPO for Multi-Reward Learning","created":"2026-09-29","cited_by_count":0,"area":"lr"},{"id":"2610.08923","title":"AdaGuard: Enhancing Safety and Policy Compliance with Reasoning-Enabled LLM-As-A-Judge Guardrails","created":"2026-10-06","cited_by_count":0,"area":"lr"},{"id":"2610.11502","title":"Fed-GRPO: Reward-Signal-Driven Federated Group Relative Policy Optimization","created":"2026-10-08","cited_by_count":0,"area":"lr"},{"id":"2610.13594","title":"MENTOR: Learning from Failure with On-Policy Pedagogical Intervention","created":"2026-10-09","cited_by_count":0,"area":"lr"},{"id":"2610.16533","title":"Spectral-Driven Adaptive-Rank Optimizer for Large Language Model Reinforcement Learning with Verifiable Rewards","created":"2026-10-12","cited_by_count":0,"area":"lr"},{"id":"2610.18755","title":"PreciseCoder: Faithful and Generalizable Debugging Beyond Unit-Test Rewards","created":"2026-10-13","cited_by_count":0,"area":"lr"},{"id":"2610.19695","title":"C3: Rethinking Process Supervision via Confidence-Guided Credit Correction in Multi-Turn Reinforcement Learning","created":"2026-10-14","cited_by_count":0,"area":"lr"}],"next_cursor":null}