{"total":64,"rows":[{"id":"2509.02547","title":"The Landscape of Agentic Reinforcement Learning for LLMs: A Survey","created":"2025-09-02","cited_by_count":205,"area":"agents"},{"id":"2507.16806","title":"Beyond Binary Rewards: Training LMs to Reason About Their Uncertainty","created":"2025-07-22","cited_by_count":117,"area":"lr"},{"id":"2508.19652","title":"Self-Rewarding Vision-Language Model via Reasoning Decomposition","created":"2025-08-27","cited_by_count":97,"area":"lr"},{"id":"2509.01055","title":"VerlTool: Towards Holistic Agentic Reinforcement Learning with Tool Use","created":"2025-09-01","cited_by_count":96,"area":"lr"},{"id":"2507.05255","title":"Open Vision Reasoner: Transferring Linguistic Cognitive Behavior for Visual Reasoning","created":"2025-07-07","cited_by_count":34,"area":"lr"},{"id":"2509.03516","title":"Easier Painting Than Thinking: Can Text-to-Image Models Set the Stage, but Not Direct the Play?","created":"2025-09-03","cited_by_count":34,"area":null},{"id":"2604.13602","title":"Reward Hacking in the Era of Large Models: Mechanisms, Emergent Misalignment, Challenges","created":"2026-04-15","cited_by_count":33,"area":"alignment"},{"id":"2509.03871","title":"A Comprehensive Survey on Trustworthiness in Reasoning with Large Language Models","created":"2025-09-04","cited_by_count":25,"area":"lr"},{"id":"2507.20849","title":"Latent Inter-User Difference Modeling for LLM Personalization","created":"2025-07-28","cited_by_count":21,"area":null},{"id":"2506.19807","title":"KnowRL: Exploring Knowledgeable Reinforcement Learning for Factuality","created":"2025-06-24","cited_by_count":20,"area":"lr"},{"id":"2511.18437","title":"Perceptual-Evidence Anchored Reinforced Learning for Multimodal Reasoning","created":"2025-11-23","cited_by_count":20,"area":"lr"},{"id":"2507.09662","title":"Towards Concise and Adaptive Thinking in Large Reasoning Models: A Survey","created":"2025-07-13","cited_by_count":18,"area":"lr"},{"id":"2603.09117","title":"Decoupling Reasoning and Confidence: Resurrecting Calibration in Reinforcement Learning from Verifiable Rewards","created":"2026-03-10","cited_by_count":14,"area":"lr"},{"id":"2604.02972","title":"NeuReasoner: Towards Explainable, Controllable, and Unified Reasoning via Mixture-of-Neurons","created":"2026-04-03","cited_by_count":14,"area":"lr"},{"id":"2604.17073","title":"Abstain-R1: Calibrated Abstention and Post-Refusal Clarification via Verifiable RL","created":"2026-04-18","cited_by_count":14,"area":"lr"},{"id":"2509.21882","title":"Position: The Hidden Costs and Measurement Gaps of Reinforcement Learning with Verifiable Rewards","created":"2025-09-26","cited_by_count":12,"area":null},{"id":"2603.13366","title":"Thinking in Uncertainty: Mitigating Hallucinations in MLRMs with Latent Entropy-Aware Decoding","created":"2026-03-09","cited_by_count":12,"area":"lr"},{"id":"2509.06861","title":"Test-Time Scaling in Reasoning Models Is Not Effective for Knowledge-Intensive Tasks Yet","created":"2025-09-08","cited_by_count":11,"area":"lr"},{"id":"2602.06570","title":"Baichuan-M3: Modeling Clinical Inquiry for Reliable Medical Decision-Making","created":"2026-02-06","cited_by_count":11,"area":null},{"id":"2508.21302","title":"Locus: Agentic Predicate Synthesis for Directed Fuzzing","created":"2025-08-29","cited_by_count":9,"area":"agents"},{"id":"2603.28618","title":"Seeing with You: Perception-Reasoning Coevolution for Multimodal Reasoning","created":"2026-03-30","cited_by_count":9,"area":"lr"},{"id":"2604.03216","title":"BAS: A Decision-Theoretic Approach to Evaluating Large Language Model Confidence","created":"2026-04-03","cited_by_count":7,"area":null},{"id":"2508.05928","title":"Mitigating Think-Answer Mismatch in LLM Reasoning Through Noise-Aware Advantage Reweighting","created":"2025-08-08","cited_by_count":6,"area":"lr"},{"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":"2510.17733","title":"Train for Truth, Keep the Skills: Binary Retrieval-Augmented Reward Mitigates Hallucinations","created":"2025-10-20","cited_by_count":5,"area":"rag"},{"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":"2511.11500","title":"Honesty over Accuracy: Trustworthy Language Models through Reinforced Hesitation","created":"2025-11-14","cited_by_count":5,"area":null},{"id":"2512.11143","title":"Automated Penetration Testing with LLM Agents and Classical Planning","created":"2025-12-11","cited_by_count":5,"area":"agents"},{"id":"2601.02170","title":"Streaming Hallucination Detection in Long Chain-of-Thought Reasoning","created":"2026-01-05","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":"2510.24794","title":"MR-Align: Meta-Reasoning Informed Factuality Alignment for Large Reasoning Models","created":"2025-10-27","cited_by_count":4,"area":"lr"},{"id":"2512.14944","title":"PuzzleCraft: Exploration-Aware Curriculum Learning for Puzzle-Based RLVR in VLMs","created":"2025-12-16","cited_by_count":4,"area":"lr"},{"id":"2602.05897","title":"Stop Rewarding Hallucinated Steps: Faithfulness-Aware Step-Level Reinforcement Learning for Small Reasoning Models","created":"2026-02-05","cited_by_count":4,"area":"lr"},{"id":"2510.08964","title":"Unleashing Perception-Time Scaling to Multimodal Reasoning Models","created":"2025-10-10","cited_by_count":3,"area":"lr"},{"id":"2601.06224","title":"Ground What You See: Hallucination-Resistant MLLMs via Caption Feedback, Diversity-Aware Sampling, and Conflict Regularization","created":"2026-01-09","cited_by_count":3,"area":"mllm"},{"id":"2607.05861","title":"Mitigating Factual Hallucination in Large Reasoning Models via Mixed-Mode Advantage Regularization","created":"2026-07-07","cited_by_count":3,"area":"lr"},{"id":"2602.00085","title":"CARE-RFT: Confidence-Anchored Reinforcement Finetuning for Reliable Reasoning in Large Language Models","created":"2026-01-22","cited_by_count":2,"area":"lr"},{"id":"2602.11166","title":"Small Updates, Big Doubts: Does Parameter-Efficient Fine-tuning Enhance Hallucination Detection ?","created":"2026-01-17","cited_by_count":2,"area":null},{"id":"2605.28301","title":"Better Accuracies, Worse Reasoning: A Step-Level Audit of Medical Chain-of-Thought Distillation","created":"2026-05-27","cited_by_count":2,"area":"lr"},{"id":"2606.11105","title":"PhantomBench: Benchmarking the Non-existential Threat of Language Models","created":"2026-06-09","cited_by_count":2,"area":null},{"id":"2511.00588","title":"Diagnosing Hallucination Risk in AI Surgical Decision-Support: A Sequential Framework for Sequential Validation","created":"2025-11-01","cited_by_count":1,"area":"lr"},{"id":"2601.03630","title":"Reasoning Model Is Superior LLM-Judge, Yet Suffers from Biases","created":"2026-01-07","cited_by_count":1,"area":"lr"},{"id":"2601.22648","title":"UCPO: Uncertainty-Aware Policy Optimization","created":"2026-01-30","cited_by_count":1,"area":null},{"id":"2601.22735","title":"MM-THEBench: Do Reasoning MLLMs Think Reasonably?","created":"2026-01-30","cited_by_count":1,"area":"lr"},{"id":"2603.26556","title":"When Perplexity Lies: Generation-Focused Distillation of Hybrid Sequence Models","created":"2026-03-27","cited_by_count":1,"area":null},{"id":"2604.10189","title":"FAITH: Factuality Alignment through Integrating Trustworthiness and Honestness","created":"2026-04-11","cited_by_count":1,"area":null},{"id":"2604.27859","title":"Rethinking Agentic Reinforcement Learning In Large Language Models","created":"2026-04-30","cited_by_count":1,"area":"lr"},{"id":"2605.03050","title":"Evaluating Reasoning Models for Queries with Presuppositions","created":"2026-05-04","cited_by_count":1,"area":"lr"},{"id":"2605.22072","title":"Faithful-MR1: Faithful Multimodal Reasoning via Anchoring and Reinforcing Visual Attention","created":"2026-05-21","cited_by_count":1,"area":"lr"},{"id":"2606.00869","title":"Enhancing LLM Metacognition via Cognitive Pairwise Training","created":"2026-05-30","cited_by_count":1,"area":"lr"},{"id":"2607.11881","title":"Metacognition in LLMs: Foundations, Progress, and Opportunities","created":"2026-07-13","cited_by_count":1,"area":null},{"id":"2607.22098","title":"Reasoning Denoiser: Denoising Reasoning Traces for Hallucination Detection in Large Reasoning Models","created":"2026-07-24","cited_by_count":1,"area":"lr"},{"id":"2608.12337","title":"From Refuse to Richness: Rubric Rewards for Long-Form Hallucination Reinforcement Learning","created":"2026-06-03","cited_by_count":1,"area":"lr"},{"id":"2510.18619","title":"Visual Attention Reasoning via Hierarchical Search and Self-Verification","created":"2025-10-21","cited_by_count":0,"area":"lr"},{"id":"2512.00552","title":"Catch Me If You Can: How Smaller Reasoning Models Pretend to Reason with Mathematical Fidelity","created":"2025-11-29","cited_by_count":0,"area":"lr"},{"id":"2512.08944","title":"Enhancing Reliability across Short and Long-Form QA via Reinforcement Learning","created":"2025-11-19","cited_by_count":0,"area":"lr"},{"id":"2601.17467","title":"Harnessing Reasoning Trajectories for Hallucination Detection via Answer-agreement Representation Shaping","created":"2026-01-24","cited_by_count":0,"area":"lr"},{"id":"2604.08124","title":"Beyond Stochastic Exploration: What Makes Training Data Valuable for Agentic Search","created":"2026-04-09","cited_by_count":0,"area":"lr"},{"id":"2607.02262","title":"CheckRLM: Effective Knowledge-Thought Coherence Checking in Retrieval-Augmented Reasoning","created":"2026-07-02","cited_by_count":0,"area":"lr"},{"id":"2607.08268","title":"Different Teachers, Different Capabilities: Sub-1B On-Device Distillation for Structured Text Enrichment","created":"2026-07-09","cited_by_count":0,"area":null},{"id":"2607.18915","title":"Reasoning Error from Known Fact: Step-Level Self-Consistency Group Relative Policy Optimization for LLM","created":"2026-07-21","cited_by_count":0,"area":"lr"},{"id":"2608.28435","title":"Linear Temporal Logic Translation via Human-Inspired Self-Constrained Reasoning for Robot Task Specification","created":"2026-08-28","cited_by_count":0,"area":"lr"},{"id":"2609.30130","title":"Multimodal Thinking with Renderable Programs","created":"2026-09-24","cited_by_count":0,"area":"lr"},{"id":"2610.07894","title":"Rethinking Faithfulness in LLMs: A Pairwise Context-Sensitive Perspective","created":"2026-10-06","cited_by_count":0,"area":"lr"}],"next_cursor":null}