{"total":95,"rows":[{"id":"2604.13016","title":"Rethinking On-Policy Distillation of Large Language Models: Phenomenology, Mechanism, and Recipe","created":"2026-04-14","cited_by_count":299,"area":"lr"},{"id":"2606.11709","title":"RLCSD: Reinforcement Learning with Contrastive On-Policy Self-Distillation","created":"2026-06-10","cited_by_count":45,"area":"lr"},{"id":"2606.15007","title":"Nemotron 3 Ultra: Open, Efficient Mixture-of-Experts Hybrid Mamba-Transformer Model for Agentic Reasoning","created":"2026-06-12","cited_by_count":42,"area":"lr"},{"id":"2605.06387","title":"Asymmetric On-Policy Distillation: Bridging Exploitation and Imitation at the Token Level","created":"2026-05-07","cited_by_count":35,"area":"lr"},{"id":"2603.15726","title":"MiroThinker-1.7 & H1: Towards Heavy-Duty Research Agents via Verification","created":"2026-03-16","cited_by_count":32,"area":"lr"},{"id":"2605.07865","title":"KL for a KL: On-Policy Distillation with Control Variate Baseline","created":"2026-05-08","cited_by_count":26,"area":"lr"},{"id":"2605.10889","title":"Unmasking On-Policy Distillation: Where It Helps, Where It Hurts, and Why","created":"2026-05-11","cited_by_count":25,"area":"lr"},{"id":"2604.11753","title":"Agentic Aggregation for Parallel Scaling of Long-Horizon Agentic Tasks","created":"2026-04-13","cited_by_count":18,"area":"lr"},{"id":"2606.05806","title":"When Tools Fail: Benchmarking Dynamic Replanning and Anomaly Recovery in LLM Agents","created":"2026-06-04","cited_by_count":17,"area":"lr"},{"id":"2605.12400","title":"OGLS-SD: On-Policy Self-Distillation with Outcome-Guided Logit Steering for LLM Reasoning","created":"2026-05-12","cited_by_count":16,"area":"lr"},{"id":"2603.06638","title":"HEARTS: Benchmarking LLM Reasoning on Health Time Series","created":"2026-02-25","cited_by_count":11,"area":"lr"},{"id":"2609.04108","title":"Sequential Beats Joint: On the Interplay between On-Policy Distillation and RLVR","created":"2026-09-03","cited_by_count":11,"area":"lr"},{"id":"2605.08741","title":"Training with Harnesses: On-Policy Harness Self-Distillation for Complex Reasoning","created":"2026-05-09","cited_by_count":10,"area":"lr"},{"id":"2606.05152","title":"Reinforcement Learning from Rich Feedback with Distributional DAgger","created":"2026-06-03","cited_by_count":10,"area":"lr"},{"id":"2605.25480","title":"Retrieval as Reasoning: Self-Evolving Agent-Native Retrieval via LLM-Wiki","created":"2026-05-25","cited_by_count":9,"area":"lr"},{"id":"2606.28436","title":"Dockerless: Environment-Free Program Verifier for Coding Agents","created":"2026-06-26","cited_by_count":9,"area":"lr"},{"id":"2605.14392","title":"Learning to Build the Environment: Self-Evolving Reasoning RL via Verifiable Environment Synthesis","created":"2026-05-14","cited_by_count":8,"area":"lr"},{"id":"2604.24432","title":"Kwai Summary Attention Technical Report","created":"2026-04-27","cited_by_count":7,"area":"lr"},{"id":"2605.05835","title":"Evaluation Awareness in Language Models Has Limited Effect on Behaviour","created":"2026-05-07","cited_by_count":7,"area":"lr"},{"id":"2605.09725","title":"On-Policy Distillation with Best-of-N Teacher Rollout Selection","created":"2026-05-10","cited_by_count":7,"area":"lr"},{"id":"2607.18955","title":"H$^2$SD: Hybrid Hindsight Self-Distillation","created":"2026-07-21","cited_by_count":7,"area":"lr"},{"id":"2604.11778","title":"General365: Benchmarking General Reasoning in Large Language Models Across Diverse and Challenging Tasks","created":"2026-04-13","cited_by_count":6,"area":"lr"},{"id":"2606.15079","title":"Ling and Ring 2.6 Technical Report: Efficient and Instant Agentic Intelligence at Trillion-Parameter Scale","created":"2026-06-13","cited_by_count":6,"area":"lr"},{"id":"2608.14277","title":"SimpleOPD: Simple Tokenizer-Agnostic On-Policy Distillation for Long-Context Reasoning","created":"2026-08-14","cited_by_count":6,"area":"lr"},{"id":"2609.05198","title":"What Matters in On-Policy Distillation? A Perspective on Data Efficiency and Data Selection","created":"2026-09-04","cited_by_count":6,"area":"lr"},{"id":"2607.05943","title":"SearchEyes: Towards Frontier Multimodal Deep Search Intelligence via Search World Simulation","created":"2026-07-07","cited_by_count":5,"area":"lr"},{"id":"2607.22925","title":"Not All LLM Reasoning is Visible in the Chain-of-Thought","created":"2026-07-24","cited_by_count":5,"area":"lr"},{"id":"2604.03144","title":"InCoder-32B-Thinking: Industrial Code World Model for Thinking","created":"2026-04-03","cited_by_count":4,"area":"lr"},{"id":"2606.13473","title":"MaxProof: Scaling Mathematical Proof with Generative-Verifier RL and Population-Level Test-Time Scaling","created":"2026-06-11","cited_by_count":4,"area":"lr"},{"id":"2603.11193","title":"DeReason: A Difficulty-Aware Curriculum Improves Decoupled SFT-then-RL Training for General Reasoning","created":"2026-03-11","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":"2606.31986","title":"CoLT: Teaching Multi-Modal Models to Think with Chain of Latent Thoughts","created":"2026-06-30","cited_by_count":3,"area":"lr"},{"id":"2602.19517","title":"Classroom Final Exam: An Instructor-Tested Reasoning Benchmark","created":"2026-02-23","cited_by_count":2,"area":"lr"},{"id":"2603.06271","title":"Agentic retrieval-augmented reasoning reshapes collective reliability under model variability in radiology question answering","created":"2026-03-06","cited_by_count":2,"area":"lr"},{"id":"2605.27765","title":"Restoring the Sweet Spot: Pass-Rate Weighted Self-Distillation for LLM Reasoning","created":"2026-05-26","cited_by_count":2,"area":"lr"},{"id":"2605.28184","title":"Joint Training of Multi-Token Prediction in Reinforcement Learning via Optimal Coefficient Calibration","created":"2026-05-27","cited_by_count":2,"area":"lr"},{"id":"2606.16140","title":"VibeThinker-3B: Exploring the Frontier of Verifiable Reasoning in Small Language Models","created":"2026-06-15","cited_by_count":2,"area":"lr"},{"id":"2607.19331","title":"ISO: An RLVR-Native Optimization Stack","created":"2026-07-21","cited_by_count":2,"area":"lr"},{"id":"2607.26977","title":"TREK: A Travel Reasoning and Evaluation Kit for LLM Agents in Complex Trip Planning","created":"2026-07-29","cited_by_count":2,"area":"lr"},{"id":"2607.27703","title":"SpatialCLI: Learning to Reason With Spatial Tools, Then Without Them","created":"2026-07-30","cited_by_count":2,"area":"lr"},{"id":"2608.01292","title":"CrossLex: A Source-Grounded Benchmark for Cross-Jurisdictional Legal Reasoning in Large Language Models","created":"2026-08-02","cited_by_count":2,"area":"lr"},{"id":"2608.27448","title":"TTPO: Test-Time Policy Optimization","created":"2026-08-27","cited_by_count":2,"area":"lr"},{"id":"2604.16972","title":"MCPO: Mastery-Consolidated Policy Optimization for Large Reasoning Models","created":"2026-04-18","cited_by_count":1,"area":"lr"},{"id":"2604.21454","title":"Reasoning Primitives in Hybrid and Non-Hybrid LLMs: Do Architectural Differences Yield Advantages in State-Tracking and Recall?","created":"2026-04-23","cited_by_count":1,"area":"lr"},{"id":"2606.10532","title":"ActiveMem: Distributed Active Memory for Long-Horizon LLM Reasoning","created":"2026-06-09","cited_by_count":1,"area":"lr"},{"id":"2606.13663","title":"HyperTool: Beyond Step-Wise Tool Calls for Tool-Augmented Agents","created":"2026-06-11","cited_by_count":1,"area":"lr"},{"id":"2607.27919","title":"Memory Decoder at Scale: A Pretrained, Parametric Long-Term Memory","created":"2026-07-30","cited_by_count":1,"area":"lr"},{"id":"2608.29464","title":"Chain-of-Thought Faithfulness of Reasoning Models Varies with Where and How Preference Cues Are Delivered","created":"2026-08-29","cited_by_count":1,"area":"lr"},{"id":"2609.02702","title":"Trace as State: Reasoning Traces as Conditional States for Long-Context Transformers","created":"2026-09-02","cited_by_count":1,"area":"lr"},{"id":"2609.09928","title":"Structural Process Supervision for Latent Chain-of-Thought Reasoning","created":"2026-09-09","cited_by_count":1,"area":"lr"},{"id":"2609.26637","title":"Capable yet Parsimonious: Extracting and Characterizing Hidden Chain-of-Thought in Frontier Models","created":"2026-09-22","cited_by_count":1,"area":"lr"},{"id":"2609.35210","title":"Understanding On-Policy Distillation: A Mechanistic Interpretability Perspective via Sparse Crosscoders","created":"2026-09-28","cited_by_count":1,"area":"lr"},{"id":"2604.02007","title":"Apriel-Reasoner: RL Post-Training for General-Purpose and Efficient Reasoning","created":"2026-04-02","cited_by_count":0,"area":"lr"},{"id":"2604.03374","title":"CresOWLve: Benchmarking Creative Problem-Solving Over Real-World Knowledge","created":"2026-04-03","cited_by_count":0,"area":"lr"},{"id":"2605.09860","title":"When to Re-Commit: Temporal Abstraction Discovery for Long-Horizon Vision-Language Reasoning","created":"2026-05-11","cited_by_count":0,"area":"lr"},{"id":"2605.23384","title":"Metacognition as Reward: Reinforcing LLM Reasoning via Knowledge and Regulation Signals","created":"2026-05-22","cited_by_count":0,"area":"lr"},{"id":"2606.01145","title":"Reasoning4Sciences: Bridging Reasoning Language Models to All Scientific Branches","created":"2026-05-31","cited_by_count":0,"area":"lr"},{"id":"2606.10479","title":"ComBench: A Benchmark for Rigorous Proof Reasoning and Constructive Realization in Olympiad-Level Combinatorics","created":"2026-06-09","cited_by_count":0,"area":"lr"},{"id":"2606.24937","title":"The Hitchhiker's Guide to Agentic AI: From Foundations to Systems","created":"2026-06-22","cited_by_count":0,"area":"lr"},{"id":"2607.19358","title":"LISA: Linear-Indexed Sparse Attention for Efficient Long-Context Reasoning","created":"2026-05-29","cited_by_count":0,"area":"lr"},{"id":"2607.25554","title":"Distilling Temporal Search and Reasoning: Evolving LLMs for Future Prediction via Harness-Assisted Efficient Data Synthesis","created":"2026-07-28","cited_by_count":0,"area":"lr"},{"id":"2607.28478","title":"Would You Walk to the Car Wash? Revealing the Salience Bias of Large Language Models in Commonsense Reasoning","created":"2026-07-30","cited_by_count":0,"area":"lr"},{"id":"2608.02101","title":"Cross-Domain Hybrid OPD for Generalizable Search Agents","created":"2026-08-03","cited_by_count":0,"area":"lr"},{"id":"2608.02217","title":"VC-Tooler: Learning Compositional and Adaptive Visual Tool Use","created":"2026-08-03","cited_by_count":0,"area":"lr"},{"id":"2608.05245","title":"Search2Skill: Skill Distillation Beyond Knowledge Boundaries Via Rubric-Based Reinforcement Learning","created":"2026-08-05","cited_by_count":0,"area":"lr"},{"id":"2608.12585","title":"Reasoning Jury: Multi-Model Consensus for Evaluating Reasoning Traces","created":"2026-08-12","cited_by_count":0,"area":"lr"},{"id":"2608.18581","title":"From Storage to Access: Verifiable Activation of Parametric Knowledge in LLMs via Explicit Priming and Implicit Reasoning","created":"2026-08-19","cited_by_count":0,"area":"lr"},{"id":"2608.24024","title":"Beyond Confidence: Test-Time Scaling for Multi-Turn Search Agents via Retrieval Grounding","created":"2026-08-25","cited_by_count":0,"area":"lr"},{"id":"2608.24086","title":"EMRB: A Multi-Level Benchmark for Evaluating LLM Reasoning over Raw Electromagnetic Signals","created":"2026-08-25","cited_by_count":0,"area":"lr"},{"id":"2608.26832","title":"RuleWeaver: Benchmarking Rule-Centered Scenario Reasoning for Large Language Models","created":"2026-08-27","cited_by_count":0,"area":"lr"},{"id":"2608.27953","title":"The Illusion of $\\textit{What If}$: Evaluating the Breakdown of Counterfactual Reasoning in LLMs","created":"2026-08-28","cited_by_count":0,"area":"lr"},{"id":"2609.08156","title":"When Metrics Reward the Worst Translations: Internalizing Cultural Reasoning for Social Media Translation Evaluation","created":"2026-09-08","cited_by_count":0,"area":"lr"},{"id":"2609.13134","title":"Rethinking Heterogeneous System Disaggregation for Subquadratic Attention","created":"2026-09-11","cited_by_count":0,"area":"lr"},{"id":"2609.18723","title":"Beyond Truncation: Rethinking LLM Decoding as Ensemble Pruning","created":"2026-09-16","cited_by_count":0,"area":"lr"},{"id":"2609.27156","title":"Giving Credit Where It's Due: Redundancy-Aware Learning for Efficient Reasoning","created":"2026-09-22","cited_by_count":0,"area":"lr"},{"id":"2609.31571","title":"Strategically Diverse Sampling for Self-Training","created":"2026-09-25","cited_by_count":0,"area":"lr"},{"id":"2609.32722","title":"Scaling Properties of Same-Family On-Policy Distillation","created":"2026-09-26","cited_by_count":0,"area":"lr"},{"id":"2609.32852","title":"ARSM: Auto-Regressive State Machine for Agentic Reasoning Compression","created":"2026-09-26","cited_by_count":0,"area":"lr"},{"id":"2609.33290","title":"Calibration, Not Answer Selection: Distilling Internal Confidence in Reasoning Models","created":"2026-09-27","cited_by_count":0,"area":"lr"},{"id":"2609.33463","title":"Rethinking Token Reweighting for SFT: Suppress, Reverse, and Extrapolate Learned Features","created":"2026-09-27","cited_by_count":0,"area":"lr"},{"id":"2609.33585","title":"IVT-Guard: All-in-One Reasoning Model for AI-Generated Content Detection","created":"2026-09-27","cited_by_count":0,"area":"lr"},{"id":"2609.37304","title":"MetaCtrl: Your Large Language Models Can Reason Better and More Concisely with a Metacognitive Controller","created":"2026-09-29","cited_by_count":0,"area":"lr"},{"id":"2609.38137","title":"LongHarness Bench: Stress-Testing Language Model Harnesses for Long-Context Reasoning","created":"2026-09-29","cited_by_count":0,"area":"lr"},{"id":"2609.39578","title":"Thinking Outside the Box: Can Language Models Rely on External Guidance Selectively?","created":"2026-09-30","cited_by_count":0,"area":"lr"},{"id":"2609.39801","title":"RATIO: Reasoning Analysis and Token-level Inference Optimization for Quantized Reasoning Models","created":"2026-09-30","cited_by_count":0,"area":"lr"},{"id":"2609.39838","title":"Learning Steganography Is Easy, Learning Steganographic Reasoning Is Hard","created":"2026-09-30","cited_by_count":0,"area":"lr"},{"id":"2610.01896","title":"Asynchronous LLM Post-Training: Group-Mass Capping and Convergence Analysis","created":"2026-10-01","cited_by_count":0,"area":"lr"},{"id":"2610.04882","title":"ResOPD: Tail Residualization for Sparse On-Policy Distillation","created":"2026-10-04","cited_by_count":0,"area":"lr"},{"id":"2610.06269","title":"Evolving in Thought Space: Training a Small Model at Test Time Unlocks Better Discoveries","created":"2026-10-05","cited_by_count":0,"area":"lr"},{"id":"2610.06366","title":"Correct Verdicts, Flawed Reasoning: Structured Auditing of LLM-based Vulnerability Reasoning","created":"2026-10-05","cited_by_count":0,"area":"lr"},{"id":"2610.09914","title":"RollVerify: Bridging Efficiency and Accuracy in Long-Tail Rollout Reinforcement Learning","created":"2026-10-07","cited_by_count":0,"area":"lr"},{"id":"2610.12061","title":"When Should Agents Think? Adaptive Reasoning via Cross-Turn Estimation","created":"2026-10-08","cited_by_count":0,"area":"lr"},{"id":"2610.12961","title":"MVGraph: Benchmarking LVLMs on Evidence Composition across Multi-View Visual Graph","created":"2026-10-09","cited_by_count":0,"area":"lr"},{"id":"2610.16593","title":"Double-Rollout Reinforcement Learning with Sampling-based Reward Estimation","created":"2026-10-12","cited_by_count":0,"area":"lr"},{"id":"2610.19698","title":"RuleTrek: Benchmarking Agentic Rule Reasoning in Complex Scenarios","created":"2026-10-14","cited_by_count":0,"area":"lr"}],"next_cursor":null}