{"total":82,"rows":[{"id":"2508.11987","title":"FutureX: An Advanced Live Benchmark for LLM Agents in Future Prediction","created":"2025-08-16","cited_by_count":59,"area":"agents"},{"id":"2509.25123","title":"From $f(x)$ and $g(x)$ to $f(g(x))$: LLMs Learn New Skills in RL by Composing Old Ones","created":"2025-09-29","cited_by_count":42,"area":null},{"id":"2509.16679","title":"Reinforcement Learning Meets Large Language Models: A Survey of Advancements and Applications Across the LLM Lifecycle","created":"2025-09-20","cited_by_count":35,"area":null},{"id":"2511.02734","title":"CostBench: Evaluating Multi-Turn Cost-Optimal Planning and Adaptation in Dynamic Environments for LLM Tool-Use Agents","created":"2025-11-04","cited_by_count":33,"area":"agents"},{"id":"2510.01624","title":"Quagmires in SFT-RL Post-Training: When High SFT Scores Mislead and What to Use Instead","created":"2025-10-02","cited_by_count":28,"area":"lr"},{"id":"2512.16912","title":"Exploration vs Exploitation: Rethinking RLVR through Clipping, Entropy, and Spurious Reward","created":"2025-12-18","cited_by_count":27,"area":"lr"},{"id":"2508.09303","title":"ParallelSearch: Train your LLMs to Decompose Query and Search Sub-queries in Parallel with Reinforcement Learning","created":"2025-08-12","cited_by_count":26,"area":null},{"id":"2511.16660","title":"Cognitive Foundations for Reasoning and Their Manifestation in LLMs","created":"2025-11-20","cited_by_count":26,"area":"lr"},{"id":"2603.19835","title":"FIPO: Eliciting Deep Reasoning with Future-KL Influenced Policy Optimization","created":"2026-03-20","cited_by_count":25,"area":"lr"},{"id":"2511.05993","title":"Revisiting Entropy in Reinforcement Learning for Large Reasoning Models","created":"2025-11-08","cited_by_count":21,"area":"lr"},{"id":"2603.02218","title":"Self-Play Only Evolves When Self-Synthetic Pipeline Ensures Learnable Information Gain","created":"2026-02-10","cited_by_count":17,"area":"synth"},{"id":"2509.13333","title":"Evaluation Awareness Scales Predictably in Open-Weights Large Language Models","created":"2025-09-10","cited_by_count":14,"area":null},{"id":"2601.11061","title":"Spurious Rewards Paradox: Mechanistically Understanding How RLVR Activates Memorization Shortcuts in LLMs","created":"2026-01-16","cited_by_count":14,"area":"lr"},{"id":"2602.04118","title":"Learning to Reason in 13 Parameters","created":"2026-02-04","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":"2510.00492","title":"Rethinking Reward Models for Multi-Domain Test-Time Scaling","created":"2025-10-01","cited_by_count":10,"area":"lr"},{"id":"2511.07979","title":"Benchmarking Multi-Step Legal Reasoning and Analyzing Chain-of-Thought Effects in Large Language Models","created":"2025-11-11","cited_by_count":10,"area":"lr"},{"id":"2511.23269","title":"OctoMed: Data Recipes for State-of-the-Art Multimodal Medical Reasoning","created":"2025-11-28","cited_by_count":10,"area":"lr"},{"id":"2508.03058","title":"VRPO: Rethinking Value Modeling for Robust RL under Noisy Supervision in LLM Post-Training","created":"2025-08-05","cited_by_count":9,"area":"lr"},{"id":"2510.02386","title":"On The Fragility of Benchmark Contamination Detection in Reasoning Models","created":"2025-09-30","cited_by_count":9,"area":"lr"},{"id":"2510.08325","title":"Beyond Pass@k: Breadth-Depth Metrics for Reasoning Boundaries","created":"2025-10-09","cited_by_count":9,"area":"lr"},{"id":"2509.24210","title":"BeyondBench: Contamination-Resistant Evaluation of Reasoning in Language Models","created":"2025-09-29","cited_by_count":8,"area":"lr"},{"id":"2510.08189","title":"R-Horizon: How Far Can Your Large Reasoning Model Really Go in Breadth and Depth?","created":"2025-10-09","cited_by_count":8,"area":"lr"},{"id":"2511.06221","title":"Tiny Model, Big Logic: Diversity-Driven Optimization Elicits Large-Model Reasoning Ability in VibeThinker-1.5B","created":"2025-11-09","cited_by_count":8,"area":"lr"},{"id":"2511.11881","title":"Better LLM Reasoning via Dual-Play","created":"2025-11-14","cited_by_count":8,"area":"lr"},{"id":"2601.05053","title":"Reinforced Efficient Reasoning via Semantically Diverse Exploration","created":"2026-01-08","cited_by_count":8,"area":"lr"},{"id":"2511.00602","title":"OpenSIR: Open-Ended Self-Improving Reasoner","created":"2025-11-01","cited_by_count":7,"area":"lr"},{"id":"2511.00794","title":"Efficient Reinforcement Learning for Large Language Models with Intrinsic Exploration","created":"2025-11-02","cited_by_count":7,"area":"lr"},{"id":"2511.04800","title":"Explore Data Left Behind in Reinforcement Learning for Reasoning Language Models","created":"2025-11-06","cited_by_count":7,"area":"lr"},{"id":"2512.23631","title":"BOAD: Discovering Hierarchical Software Engineering Agents via Bandit Optimization","created":"2025-12-29","cited_by_count":7,"area":"lr"},{"id":"2602.09305","title":"Reward Modeling for Reinforcement Learning-Based LLM Reasoning: Design, Challenges, and Evaluation","created":"2026-02-10","cited_by_count":7,"area":"lr"},{"id":"2508.21188","title":"Mirage or Method? How Model-Task Alignment Induces Divergent RL Conclusions","created":"2025-08-28","cited_by_count":6,"area":null},{"id":"2510.09259","title":"Detecting Data Contamination from Reinforcement Learning Post-training for Large Language Models","created":"2025-10-10","cited_by_count":6,"area":null},{"id":"2602.04811","title":"SE-Bench: Benchmarking Self-Evolution with Knowledge Internalization","created":"2026-02-04","cited_by_count":6,"area":null},{"id":"2602.16742","title":"DeepVision-103K: A Visually Diverse, Broad-Coverage, and Verifiable Mathematical Dataset for Multimodal Reasoning","created":"2026-02-18","cited_by_count":6,"area":"lr"},{"id":"2603.02091","title":"Learning from Synthetic Data Improves Multi-hop Reasoning","created":"2026-03-02","cited_by_count":6,"area":"lr"},{"id":"2508.01174","title":"RSPO: Risk-Seeking Policy Optimization for Pass@k and Max@k Metrics in Large Language Models","created":"2025-08-02","cited_by_count":5,"area":null},{"id":"2510.05152","title":"A Single Character can Make or Break Your LLM Evals","created":"2025-10-02","cited_by_count":5,"area":null},{"id":"2510.06915","title":"LongRM: Revealing and Unlocking the Context Boundary of Reward Modeling","created":"2025-10-08","cited_by_count":5,"area":"alignment"},{"id":"2603.10101","title":"CLIPO: Contrastive Learning in Policy Optimization Generalizes RLVR","created":"2026-03-10","cited_by_count":5,"area":"lr"},{"id":"2608.31075","title":"Scaling Large Reasoning Models beyond Human Supervision: A Path toward Superintelligence","created":"2026-08-31","cited_by_count":5,"area":"lr"},{"id":"2511.12429","title":"Tailored Primitive Initialization is the Secret Key to Reinforcement Learning","created":"2025-11-16","cited_by_count":4,"area":"lr"},{"id":"2512.14391","title":"RePo: Language Models with Context Re-Positioning","created":"2025-12-16","cited_by_count":4,"area":null},{"id":"2601.13244","title":"Do Instruction-Tuned Models Always Perform Better Than Base Models? Evidence from Math and Domain-Shifted Benchmarks","created":"2026-01-19","cited_by_count":4,"area":null},{"id":"2602.01523","title":"A Relative-Budget Theory for Reinforcement Learning with Verifiable Rewards in Large Language Model Reasoning","created":"2026-02-02","cited_by_count":4,"area":"lr"},{"id":"2605.30451","title":"VeriGate: Verifier-Gated Step-Level Supervision for GRPO","created":"2026-05-28","cited_by_count":4,"area":"lr"},{"id":"2508.13003","title":"EvolMathEval: Towards Evolvable Benchmarks for Mathematical Reasoning via Evolutionary Testing","created":"2025-08-18","cited_by_count":3,"area":"lr"},{"id":"2508.19996","title":"ReSURE: Regularizing Supervision Unreliability for Multi-turn Dialogue Fine-tuning","created":"2025-08-27","cited_by_count":3,"area":null},{"id":"2510.08977","title":"Breaking the Self-Confirming Loop: Diagnosing and Mitigating Systemic Reward Bias in Self-Rewarding RL","created":"2025-10-10","cited_by_count":3,"area":"lr"},{"id":"2510.26109","title":"Do Not Step Into the Same River Twice: Learning to Reason from Trial and Error","created":"2025-10-30","cited_by_count":3,"area":"lr"},{"id":"2511.01409","title":"LiveSearchBench: An Automatically Constructed Benchmark for Retrieval and Reasoning over Dynamic Knowledge","created":"2025-11-03","cited_by_count":3,"area":"lr"},{"id":"2604.04648","title":"From Curiosity to Caution: Mitigating Reward Hacking for Best-of-N with Pessimism","created":"2026-04-06","cited_by_count":3,"area":"lr"},{"id":"2604.10332","title":"From GPT-3 to GPT-5: Mapping their capabilities, scope, limitations, and consequences","created":"2026-04-11","cited_by_count":3,"area":null},{"id":"2605.21856","title":"The Illusion of Reasoning: Exposing Evasive Data Contamination in LLMs via Zero-CoT Truncation","created":"2026-05-21","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":"2509.20909","title":"LogitTrace: Detecting Benchmark Contamination via Layerwise Logit Trajectories","created":"2025-09-25","cited_by_count":2,"area":null},{"id":"2510.08569","title":"ArenaBencher: Automatic Benchmark Evolution via Multi-Model Competitive Evaluation","created":"2025-10-09","cited_by_count":2,"area":null},{"id":"2601.03111","title":"One Sample to Rule Them All: Extreme Data Efficiency in Multidiscipline Reasoning with Reinforcement Learning","created":"2026-01-06","cited_by_count":2,"area":"lr"},{"id":"2604.20835","title":"Parallel-SFT: Improving Zero-Shot Cross-Programming-Language Transfer for Code RL","created":"2026-04-22","cited_by_count":2,"area":null},{"id":"2508.05909","title":"Beyond Perplexity: Let the Reader Select Retrieval Summaries via Spectrum Projection Score","created":"2025-08-08","cited_by_count":1,"area":"rag"},{"id":"2510.05962","title":"MatheMagic: Generating Dynamic Mathematics Benchmarks Robust to Memorization","created":"2025-10-07","cited_by_count":1,"area":null},{"id":"2511.04120","title":"RIDE: Difficulty Evolving Perturbation with Item Response Theory for Mathematical Reasoning","created":"2025-11-06","cited_by_count":1,"area":"lr"},{"id":"2603.12826","title":"Rethinking Multiple-Choice Questions for RLVR: Unlocking Potential via Distractor Design","created":"2026-03-13","cited_by_count":1,"area":"lr"},{"id":"2608.09805","title":"Parameter Exploration for RLVR via Variational Learning","created":"2026-08-10","cited_by_count":1,"area":null},{"id":"2510.25065","title":"Rewarding Structural Conformance of Reasoning using Process Mining","created":"2025-10-29","cited_by_count":0,"area":"lr"},{"id":"2511.00808","title":"Do Math Reasoning LLMs Help Predict the Impact of Public Transit Events?","created":"2025-11-02","cited_by_count":0,"area":"lr"},{"id":"2512.14735","title":"PyFi: Toward Pyramid-like Financial Image Understanding for VLMs via Adversarial Agents","created":"2025-12-11","cited_by_count":0,"area":"mllm"},{"id":"2512.18857","title":"CORE: Concept-Oriented Reinforcement for Bridging the Definition-Application Gap in Mathematical Reasoning","created":"2025-12-21","cited_by_count":0,"area":"lr"},{"id":"2602.08548","title":"How Do Language Models Understand Tables? A Mechanistic Analysis of Cell Location","created":"2026-02-09","cited_by_count":0,"area":null},{"id":"2603.17832","title":"Text-to-Stage: Spatial Layouts from Long-form Narratives","created":"2026-03-18","cited_by_count":0,"area":"lr"},{"id":"2603.27226","title":"Rethinking Easy-to-Hard: Limits of Curriculum Learning in Post-Training for Deductive Reasoning","created":"2026-03-28","cited_by_count":0,"area":"lr"},{"id":"2605.13595","title":"Inducing Artificial Uncertainty in Language Models","created":"2026-05-13","cited_by_count":0,"area":null},{"id":"2605.29888","title":"LaRA: Layer-wise Representation Analysis for Detecting Data Contamination in RL Post-Training","created":"2026-05-28","cited_by_count":0,"area":"lr"},{"id":"2606.27103","title":"The Riddle Riddle: Testing Flexible Reasoning in Large Language Models and Humans","created":"2026-06-25","cited_by_count":0,"area":"lr"},{"id":"2606.29481","title":"To Reason or to Fabricate: Reasoning Without Shortcuts via Hint-Anchored Pairwise Aggregation","created":"2026-06-28","cited_by_count":0,"area":"lr"},{"id":"2607.23440","title":"Reasoning or Memorization: Can LLMs Understand and Generate Chinese Xiehouyu Riddles?","created":"2026-07-26","cited_by_count":0,"area":"lr"},{"id":"2608.25936","title":"One Symptom, Three Levers: A Critical Review of On-Policy Self-Distillation","created":"2026-08-26","cited_by_count":0,"area":"lr"},{"id":"2609.16639","title":"ReDraft, Don't Just Distill: Reference-Driven Revision for Continual VLLM Post-Training","created":"2026-09-15","cited_by_count":0,"area":"mllm"},{"id":"2609.27166","title":"Scaling of Capability and Efficiency at Inference Time in Large Reasoning Models","created":"2026-09-22","cited_by_count":0,"area":"lr"},{"id":"2609.36587","title":"Learned Reporting Preferences in RLVR Can Conflict with the Current Request","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2609.37236","title":"Asking for What Was Never Requested: Horizontal and Vertical Proactivity in Agents","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2610.17824","title":"Checking the Checkers: A Synthesis of Verifier Noise and Robustness in RLVR","created":"2026-10-13","cited_by_count":0,"area":"lr"}],"next_cursor":null}