{"total":70,"rows":[{"id":"2509.08827","title":"A Survey of Reinforcement Learning for Large Reasoning Models","created":"2025-09-10","cited_by_count":180,"area":"lr"},{"id":"2505.22312","title":"Skywork Open Reasoner 1 Technical Report","created":"2025-05-28","cited_by_count":165,"area":"lr"},{"id":"2506.14965","title":"Revisiting Reinforcement Learning for LLM Reasoning from A Cross-Domain Perspective","created":"2025-06-17","cited_by_count":76,"area":"lr"},{"id":"2509.23653","title":"Don't Settle Too Early: Self-Reflective Remasking for Diffusion Language Models","created":"2025-09-28","cited_by_count":37,"area":"diffusion"},{"id":"2508.05988","title":"Pruning the Unsurprising: Efficient LLM Reasoning via First-Token Surprisal","created":"2025-08-08","cited_by_count":32,"area":"lr"},{"id":"2508.17281","title":"From Language to Action: A Review of Large Language Models as Autonomous Agents and Tool Users","created":"2025-08-24","cited_by_count":32,"area":"agents"},{"id":"2505.00551","title":"100 Days After DeepSeek-R1: A Survey on Replication Studies and More Directions for Reasoning Language Models","created":"2025-05-01","cited_by_count":30,"area":"lr"},{"id":"2510.18471","title":"CodeRL+: Improving Code Generation via Reinforcement with Execution Semantics Alignment","created":"2025-10-21","cited_by_count":24,"area":null},{"id":"2512.15699","title":"FrontierCS: Evolving Challenges for Evolving Intelligence","created":"2025-12-17","cited_by_count":23,"area":null},{"id":"2605.07725","title":"SOD: Step-wise On-policy Distillation for Small Language Model Agents","created":"2026-05-08","cited_by_count":21,"area":"agents"},{"id":"2507.17512","title":"Can One Domain Help Others? A Data-Centric Study on Multi-Domain Reasoning via Reinforcement Learning","created":"2025-07-23","cited_by_count":17,"area":"lr"},{"id":"2603.07084","title":"Countdown-Code: A Testbed for Studying The Emergence and Generalization of Reward Hacking in RLVR","created":"2026-03-07","cited_by_count":17,"area":"alignment"},{"id":"2511.18538","title":"From Code Foundation Models to Agents and Applications: A Comprehensive Survey and Practical Guide to Code Intelligence","created":"2025-11-23","cited_by_count":15,"area":"agents"},{"id":"2509.03059","title":"Loong: Synthesize Long Chain-of-Thoughts at Scale through Verifiers","created":"2025-09-03","cited_by_count":14,"area":"lr"},{"id":"2510.26374","title":"BOTS: A Unified Framework for Bayesian Online Task Selection in LLM Reinforcement Finetuning","created":"2025-10-30","cited_by_count":14,"area":"alignment"},{"id":"2512.11391","title":"Mitigating the Safety Alignment Tax with Null-Space Constrained Policy Optimization","created":"2025-12-12","cited_by_count":11,"area":"alignment"},{"id":"2603.19329","title":"Goedel-Code-Prover: Hierarchical Proof Search for Open State-of-the-Art Code Verification","created":"2026-03-18","cited_by_count":11,"area":null},{"id":"2510.04786","title":"Learning on the Job: Test-Time Curricula for Targeted Reinforcement Learning","created":"2025-10-06","cited_by_count":9,"area":"deeprl"},{"id":"2603.02045","title":"Expanding LLM Agent Boundaries with Strategy-Guided Exploration","created":"2026-03-02","cited_by_count":9,"area":"agents"},{"id":"2607.16051","title":"Loop the Loopies!","created":"2026-07-17","cited_by_count":8,"area":"moe"},{"id":"2510.06296","title":"VeriEquivBench: An Equivalence Score for Ground-Truth-Free Evaluation of Formally Verifiable Code","created":"2025-10-07","cited_by_count":7,"area":null},{"id":"2507.08068","title":"Quantile Reward Policy Optimization: Alignment with Pointwise Regression and Exact Partition Functions","created":"2025-07-10","cited_by_count":6,"area":"lr"},{"id":"2509.23061","title":"Local Success Does Not Compose: Benchmarking Large Language Models for Compositional Formal Verification","created":"2025-09-27","cited_by_count":6,"area":null},{"id":"2601.03525","title":"Beyond Binary: Turning Partial Success into Dense Verifiable Rewards for Reinforcement Learning in Code Generation","created":"2026-01-07","cited_by_count":5,"area":"alignment"},{"id":"2601.19001","title":"FROST: Filtering Reasoning Outliers with Attention for Efficient Reasoning","created":"2026-01-26","cited_by_count":5,"area":null},{"id":"2606.25178","title":"Transferability for General Reasoning: An Automated Curriculum for Multi-Domain RLVR","created":"2026-06-23","cited_by_count":5,"area":null},{"id":"2507.18671","title":"Innovator: Scientific Continued Pretraining with Fine-grained MoE Upcycling","created":"2025-07-24","cited_by_count":4,"area":"moe"},{"id":"2510.08720","title":"How Many Code and Test Cases Are Enough? Evaluating Test Cases Generation from a Binary-Matrix Perspective","created":"2025-10-09","cited_by_count":4,"area":null},{"id":"2604.12268","title":"CodeSpecBench: Benchmarking LLMs for Executable Behavioral Specification Generation","created":"2026-04-14","cited_by_count":4,"area":null},{"id":"2507.07498","title":"Teaching LLM to Reason: Reinforcement Learning from Algorithmic Problems without Code","created":"2025-07-10","cited_by_count":3,"area":"lr"},{"id":"2602.02751","title":"Scaling Small Agents Through Strategy Auctions","created":"2026-02-02","cited_by_count":3,"area":"agents"},{"id":"2602.06098","title":"A Theoretical Analysis of Test-Driven Code Generation","created":"2026-02-05","cited_by_count":3,"area":null},{"id":"2511.01104","title":"HarnessLLM: Automatic Testing Harness Generation via Reinforcement Learning","created":"2025-11-02","cited_by_count":2,"area":"lr"},{"id":"2604.03922","title":"ACES: Who Tests the Tests? Leave-One-Out AUC Consistency for Code Generation","created":"2026-04-05","cited_by_count":2,"area":null},{"id":"2604.05963","title":"QiMeng-PRepair: Precise Code Repair via Edit-Aware Reward Optimization","created":"2026-04-07","cited_by_count":2,"area":null},{"id":"2505.23598","title":"LLM Performance for Code Generation on Noisy Tasks","created":"2025-05-29","cited_by_count":1,"area":null},{"id":"2507.15868","title":"Small Edits, Big Consequences: Telling Good from Bad Robustness in Large Language Models","created":"2025-07-15","cited_by_count":1,"area":null},{"id":"2509.19681","title":"Calibrated Reasoning: An Explanatory Verifier for Dynamic and Efficient Problem-Solving","created":"2025-09-24","cited_by_count":1,"area":"lr"},{"id":"2601.00575","title":"InfoSynth: Information-Guided Benchmark Synthesis for LLMs","created":"2026-01-02","cited_by_count":1,"area":null},{"id":"2601.04996","title":"AlgBench: To What Extent Do Large Reasoning Models Understand Algorithms?","created":"2026-01-08","cited_by_count":1,"area":"lr"},{"id":"2603.00724","title":"RLAR: An Agentic Reward System for Multi-task Reinforcement Learning on Large Language Models","created":"2026-02-28","cited_by_count":1,"area":"agents"},{"id":"2603.29957","title":"Think Anywhere in Code Generation","created":"2026-03-31","cited_by_count":1,"area":"lr"},{"id":"2604.16322","title":"Steerable Instruction Following Coding Data Synthesis with Actor-Parametric Schema Co-Evolution","created":"2026-02-27","cited_by_count":1,"area":"synth"},{"id":"2604.23488","title":"Do Prompt-Elicited Trajectories Reflect Training-Time Reward Hacking? A Systematic Study on Monitoring Training-Time Reward Hacking in Code Generation","created":"2026-04-26","cited_by_count":1,"area":"lr"},{"id":"2605.13280","title":"Characterizing Readability Issue Patterns and the Role of Prompt Design in LLM-Generated Code","created":"2026-05-13","cited_by_count":1,"area":null},{"id":"2605.17958","title":"Enhancing the Code Reasoning Capabilities of LLMs via Consistency-based Reinforcement Learning","created":"2026-05-18","cited_by_count":1,"area":"lr"},{"id":"2606.12373","title":"Verifiable Environments Are LEGO Bricks: Recursive Composition for Reasoning Generalization","created":"2026-06-10","cited_by_count":1,"area":"lr"},{"id":"2607.21971","title":"Teaching LLMs to Self-Evolve: Cultivating Core Meta-Skills with Reinforcement Learning","created":"2026-07-24","cited_by_count":1,"area":"lr"},{"id":"2608.07147","title":"DiDPO: Diff-in-Diff Policy Optimization for Coding Agent Training","created":"2026-08-07","cited_by_count":1,"area":"agents"},{"id":"2609.37633","title":"RLTL;DR: Self-improvement by Internalizing Self-generated Feedback","created":"2026-09-29","cited_by_count":1,"area":null},{"id":"2510.11104","title":"Enhancing LLM Reasoning via Non-Human-Like Reasoning Path Preference Optimization","created":"2025-10-13","cited_by_count":0,"area":"lr"},{"id":"2512.18131","title":"Holistic Evaluation of State-of-the-Art LLMs for Code Generation","created":"2025-12-19","cited_by_count":0,"area":null},{"id":"2601.13995","title":"From Tags to Trees: Structuring Fine-Grained Knowledge for Controllable Data Selection in LLM Instruction Tuning","created":"2026-01-20","cited_by_count":0,"area":null},{"id":"2602.01660","title":"CoDiQ: Test-Time Scaling for Controllable Difficult Question Generation","created":"2026-02-02","cited_by_count":0,"area":"lr"},{"id":"2603.04212","title":"Code Fingerprints: Disentangled Attribution of LLM-Generated Code","created":"2026-03-04","cited_by_count":0,"area":null},{"id":"2605.06111","title":"Schedule-and-Calibrate: Utility-Guided Multi-Task Reinforcement Learning for Code LLMs","created":"2026-05-07","cited_by_count":0,"area":null},{"id":"2605.14539","title":"Learning from Failures: Correction-Oriented Policy Optimization with Verifiable Rewards","created":"2026-05-14","cited_by_count":0,"area":"lr"},{"id":"2605.18822","title":"Hybrid-LoRA: Bridging Full Fine-Tuning and Low-Rank Adaptation for Post-Training","created":"2026-05-12","cited_by_count":0,"area":null},{"id":"2605.26842","title":"MONA: Muon Optimizer with Nesterov Acceleration for Scalable Language Model Training","created":"2026-05-26","cited_by_count":0,"area":"moe"},{"id":"2606.05486","title":"Localizing Prompt Ambiguity in Large Language Models with Probe-Targeted Attribution","created":"2026-06-03","cited_by_count":0,"area":null},{"id":"2607.09366","title":"Diversifying to Verify: When Task-Equivalent Programs Differ in Verifiability","created":"2026-07-10","cited_by_count":0,"area":null},{"id":"2607.20764","title":"ArbiGraph: Arbitrarily Scalable Verifiable Task Graphs for Evaluating Context Management","created":"2026-07-22","cited_by_count":0,"area":null},{"id":"2609.24826","title":"OPBackdoor: Opportunistic Backdoors via Alibi-Aligned Reasoning","created":"2026-09-21","cited_by_count":0,"area":"safety"},{"id":"2609.33816","title":"Dual-Vocabulary Language Model for Cross-Tokenizer Distillation","created":"2026-09-27","cited_by_count":0,"area":"distill"},{"id":"2609.36820","title":"CorrGRPO: Correlation-Normalized GRPO for Multi-Reward Learning","created":"2026-09-29","cited_by_count":0,"area":"lr"},{"id":"2609.37405","title":"Complexity-Aware Evaluation of LLM Comprehension","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2610.00991","title":"Adapter Thickets: Splitting an RLVR Budget Beats Concentrating It","created":"2026-10-01","cited_by_count":0,"area":"lr"},{"id":"2610.02571","title":"Improving the Energy-Efficiency of the Code Generated by LLMs through Effective Prompting","created":"2026-10-01","cited_by_count":0,"area":null},{"id":"2610.06671","title":"Learning What to Imitate: Entropy-Aware Distribution Mixing","created":"2026-10-05","cited_by_count":0,"area":"lr"},{"id":"2610.17062","title":"Gradient Routing Localizes and Removes Unintended Behaviors in RL","created":"2026-10-12","cited_by_count":0,"area":"alignment"}],"next_cursor":null}