{"total":119,"rows":[{"id":"2507.20534","title":"Kimi K2: Open Agentic Intelligence","created":"2025-07-28","cited_by_count":567,"area":"agents"},{"id":"2504.12216","title":"d1: Scaling Reasoning in Diffusion Large Language Models via Reinforcement Learning","created":"2025-04-16","cited_by_count":186,"area":"lr"},{"id":"2509.08827","title":"A Survey of Reinforcement Learning for Large Reasoning Models","created":"2025-09-10","cited_by_count":180,"area":"lr"},{"id":"2509.24704","title":"MemGen: Weaving Generative Latent Memory for Self-Evolving Agents","created":"2025-09-29","cited_by_count":109,"area":"agents"},{"id":"2506.06122","title":"Reinforcement Learning Optimization for Large-Scale Learning: An Efficient and User-Friendly Scaling Library","created":"2025-06-06","cited_by_count":101,"area":"lr"},{"id":"2509.01142","title":"Dream-Coder 7B: An Open Diffusion Language Model for Code","created":"2025-09-01","cited_by_count":81,"area":"diffusion"},{"id":"2510.01179","title":"TOUCAN: Synthesizing 1.5M Tool-Agentic Data from Real-World MCP Environments","created":"2025-10-01","cited_by_count":69,"area":"agents"},{"id":"2507.01679","title":"Blending Supervised and Reinforcement Fine-Tuning with Prefix Sampling","created":"2025-07-02","cited_by_count":60,"area":"lr"},{"id":"2505.19914","title":"Enigmata: Scaling Logical Reasoning in Large Language Models with Synthetic Verifiable Puzzles","created":"2025-05-26","cited_by_count":56,"area":"lr"},{"id":"2505.10446","title":"Reinforcing the Diffusion Chain of Lateral Thought with Diffusion Language Models","created":"2025-05-15","cited_by_count":54,"area":"lr"},{"id":"2503.19633","title":"1.4 Million Open-Source Distilled Reasoning Dataset to Empower Large Language Model Training","created":"2025-03-25","cited_by_count":49,"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":"2505.24183","title":"QiMeng-CodeV-R1: Reasoning-Enhanced Verilog Generation","created":"2025-05-30","cited_by_count":35,"area":"lr"},{"id":"2509.21009","title":"RollPacker: Mitigating Long-Tail Rollouts for Fast, Synchronous RL Post-Training","created":"2025-09-25","cited_by_count":35,"area":"lr"},{"id":"2510.08554","title":"Improving Reasoning for Diffusion Language Models via Group Diffusion Policy Optimization","created":"2025-10-09","cited_by_count":33,"area":"lr"},{"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":"2512.09106","title":"Learning Unmasking Policies for Diffusion Language Models","created":"2025-12-09","cited_by_count":30,"area":"diffusion"},{"id":"2510.08529","title":"CoMAS: Co-Evolving Multi-Agent Systems via Interaction Rewards","created":"2025-10-09","cited_by_count":29,"area":"agents"},{"id":"2505.14464","title":"Not All Correct Answers Are Equal: Why Your Distillation Source Matters","created":"2025-05-20","cited_by_count":25,"area":"lr"},{"id":"2507.09075","title":"OpenCodeReasoning-II: A Simple Test Time Scaling Approach via Self-Critique","created":"2025-07-11","cited_by_count":25,"area":"lr"},{"id":"2509.21016","title":"RL Grokking Recipe: How Does RL Unlock and Transfer New Algorithms in LLMs?","created":"2025-09-25","cited_by_count":23,"area":null},{"id":"2504.14757","title":"SWE-Synth: Synthesizing Verifiable Bug-Fix Data to Enable Large Language Models in Resolving Real-World Bugs","created":"2025-04-20","cited_by_count":22,"area":null},{"id":"2504.17565","title":"DeepDistill: Enhancing LLM Reasoning Capabilities via Large-Scale Difficulty-Graded Data Training","created":"2025-04-24","cited_by_count":18,"area":"lr"},{"id":"2505.22338","title":"Text2Grad: Reinforcement Learning from Natural Language Feedback","created":"2025-05-28","cited_by_count":18,"area":"alignment"},{"id":"2507.19060","title":"PurpCode: Reasoning for Safer Code Generation","created":"2025-07-25","cited_by_count":18,"area":"lr"},{"id":"2509.17325","title":"Generalizable End-to-End Tool-Use RL with Synthetic CodeGym","created":"2025-09-22","cited_by_count":17,"area":"agents"},{"id":"2504.13828","title":"Generative AI Act II: Test Time Scaling Drives Cognition Engineering","created":"2025-04-18","cited_by_count":15,"area":"lr"},{"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":"2602.03036","title":"LatentMem: Customizing Latent Memory for Multi-Agent Systems","created":"2026-02-03","cited_by_count":15,"area":"agents"},{"id":"2504.14560","title":"ReasoningV: Efficient Verilog Code Generation with Adaptive Hybrid Reasoning Model","created":"2025-04-20","cited_by_count":12,"area":"lr"},{"id":"2505.13893","title":"InfiGFusion: Graph-on-Logits Distillation via Efficient Gromov-Wasserstein for Model Fusion","created":"2025-05-20","cited_by_count":12,"area":null},{"id":"2507.14683","title":"MiroMind-M1: An Open-Source Advancement in Mathematical Reasoning via Context-Aware Multi-Stage Policy Optimization","created":"2025-07-19","cited_by_count":12,"area":"lr"},{"id":"2605.07711","title":"SimCT: Recovering Lost Supervision for Cross-Tokenizer On-Policy Distillation","created":"2026-05-08","cited_by_count":12,"area":"distill"},{"id":"2508.09883","title":"Beyond Scaling Law: A Data-Efficient Distillation Framework for Reasoning","created":"2025-08-13","cited_by_count":11,"area":"lr"},{"id":"2510.16476","title":"NP-Engine: Empowering Optimization Reasoning in Large Language Models with Verifiable Synthetic NP Problems","created":"2025-10-18","cited_by_count":11,"area":"lr"},{"id":"2606.06712","title":"Data-Efficient Autoregressive-to-Diffusion Language Models via On-Policy Distillation","created":"2026-06-04","cited_by_count":11,"area":"diffusion"},{"id":"2510.04081","title":"Scaling Code-Assisted Chain-of-Thoughts and Instructions for Model Reasoning","created":"2025-10-05","cited_by_count":10,"area":"lr"},{"id":"2601.07470","title":"Learning How to Remember: A Meta-Cognitive Management Method for Structured and Transferable Agent Memory","created":"2026-01-12","cited_by_count":10,"area":"agents"},{"id":"2602.10314","title":"Stop Training for the Worst: Progressive Unmasking Accelerates Masked Diffusion Training","created":"2026-02-10","cited_by_count":10,"area":"diffusion"},{"id":"2509.19894","title":"PromptCoT 2.0: Scaling Prompt Synthesis for Large Language Model Reasoning","created":"2025-09-24","cited_by_count":9,"area":"lr"},{"id":"2510.23538","title":"JanusCoder: Towards a Foundational Visual-Programmatic Interface for Code Intelligence","created":"2025-10-27","cited_by_count":9,"area":null},{"id":"2605.17734","title":"Harnessing LLM Agents with Skill Programs","created":"2026-05-18","cited_by_count":9,"area":"agents"},{"id":"2505.13878","title":"InfiFPO: Implicit Model Fusion via Preference Optimization in Large Language Models","created":"2025-05-20","cited_by_count":8,"area":"alignment"},{"id":"2601.05505","title":"FlashMem: Distilling Intrinsic Latent Memory via Computation Reuse","created":"2026-01-09","cited_by_count":8,"area":null},{"id":"2603.15611","title":"Code-A1: Adversarial Evolving of Code LLM and Test LLM via Reinforcement Learning","created":"2026-03-16","cited_by_count":8,"area":null},{"id":"2607.22334","title":"Cross-Tokenizer On-Policy Distillation via Byte-Prefix Marginalization","created":"2026-07-24","cited_by_count":8,"area":"distill"},{"id":"2509.22824","title":"Critique-Coder: Enhancing Coder Models by Critique Reinforcement Learning","created":"2025-09-26","cited_by_count":7,"area":"lr"},{"id":"2602.01705","title":"LaDi-RL: Latent Diffusion Reasoning Prevents Entropy Collapse in Reinforcement Learning","created":"2026-02-02","cited_by_count":7,"area":"lr"},{"id":"2603.11226","title":"ExecVerify: White-Box RL with Verifiable Stepwise Rewards for Code Execution Reasoning","created":"2026-03-11","cited_by_count":6,"area":"lr"},{"id":"2511.07833","title":"MURPHY: Feedback-Aware GRPO with Retrospective Credit Assignment for Multi-Turn Code Generation","created":"2025-11-11","cited_by_count":5,"area":"lr"},{"id":"2601.22642","title":"Pushing the Boundaries of Natural Reasoning: Interleaved Bonus from Formal-Logic Verification","created":"2026-01-30","cited_by_count":5,"area":"lr"},{"id":"2602.17684","title":"CodeScaler: Scaling Code LLM Training and Test-Time Inference via Reward Models","created":"2026-02-04","cited_by_count":5,"area":"alignment"},{"id":"2603.12698","title":"EvolveCoder: Evolving Test Cases via Adversarial Verification for Code Reinforcement Learning","created":"2026-03-13","cited_by_count":5,"area":"lr"},{"id":"2503.05860","title":"Benchmarking AI Models in Software Engineering: A Review, Search Tool, and Unified Approach for Elevating Benchmark Quality","created":"2025-03-07","cited_by_count":4,"area":null},{"id":"2505.23060","title":"Self-Correcting Code Generation Using Small Language Models","created":"2025-05-29","cited_by_count":4,"area":null},{"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":"2602.09003","title":"Data Science and Technology Towards AGI Part I: Tiered Data Management","created":"2026-02-09","cited_by_count":4,"area":null},{"id":"2605.24812","title":"CoRe-Code: Collaborative Reinforcement Learning for Code Generation","created":"2026-05-24","cited_by_count":4,"area":null},{"id":"2606.06447","title":"Latent Reasoning with Normalizing Flows","created":"2026-06-04","cited_by_count":4,"area":"lr"},{"id":"2606.08501","title":"Back on Track: Aligning Rewards and States for Reasoning in Diffusion Large Language Models","created":"2026-06-07","cited_by_count":4,"area":"lr"},{"id":"2510.07000","title":"Pragyaan: Designing and Curating High-Quality Cultural Post-Training Datasets for Indian Languages","created":"2025-10-08","cited_by_count":3,"area":null},{"id":"2605.13935","title":"Beyond Mode-Seeking RL: Trajectory-Balance Post-Training for Diffusion Language Models","created":"2026-05-13","cited_by_count":3,"area":"diffusion"},{"id":"2605.22939","title":"Learnability-Informed Fine-Tuning of Diffusion Language Models","created":"2026-05-21","cited_by_count":3,"area":"lr"},{"id":"2607.15200","title":"Mask-Aware Policy Gradients for Diffusion Language Models","created":"2026-07-16","cited_by_count":3,"area":"lr"},{"id":"2505.19502","title":"CODE-DITING: A Reasoning-Based Metric for Functional Alignment in Code Evaluation","created":"2025-05-26","cited_by_count":2,"area":"lr"},{"id":"2602.23258","title":"MASRubric: Auditing Information Flow in Multi-Agent Systems with Failure-Distilled Pitfall Rubrics","created":"2026-02-26","cited_by_count":2,"area":null},{"id":"2603.07777","title":"Breaking Training Bottlenecks: Effective and Stable Reinforcement Learning for Coding Models","created":"2026-03-08","cited_by_count":2,"area":"lr"},{"id":"2603.07779","title":"Scaling Data Difficulty: Improving Coding Models via Reinforcement Learning on Fresh and Challenging Problems","created":"2026-03-08","cited_by_count":2,"area":"lr"},{"id":"2605.09536","title":"TAD: Temporal-Aware Trajectory Self-Distillation for Fast and Accurate Diffusion LLM","created":"2026-05-10","cited_by_count":2,"area":null},{"id":"2606.08702","title":"ConMem: Structured Memory-Guided Adaptation in Training-Free Multi-Agent Systems","created":"2026-06-07","cited_by_count":2,"area":"agents"},{"id":"2607.14522","title":"A Continuous-Time Reinforcement Learning Framework for Fine-Tuning Discrete Diffusion Models","created":"2026-07-16","cited_by_count":2,"area":"diffusion"},{"id":"2607.19450","title":"REGEN: Replay-recycling for Expert-to-Generalist distillation with Offline Reinforcement Learning","created":"2026-07-21","cited_by_count":2,"area":"agents"},{"id":"2608.22788","title":"TailSieve: Partial-Rollout-Guided Tail Routing for LLM Rollouts","created":"2026-08-24","cited_by_count":2,"area":"distill"},{"id":"2609.23697","title":"Distill What You Trust: Reliability-Aware Multi-Teacher On-Policy Distillation","created":"2026-09-20","cited_by_count":2,"area":"distill"},{"id":"2505.02142","title":"Exploring the Potential of Offline RL for Reasoning in LLMs: A Preliminary Study","created":"2025-05-04","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":"2601.06953","title":"X-Coder: Advancing Competitive Programming with Synthetic Tasks, Solutions, and Tests","created":"2026-01-11","cited_by_count":1,"area":null},{"id":"2601.21115","title":"Multi-task Code LLMs: Data Mix or Model Merge?","created":"2026-01-28","cited_by_count":1,"area":"agents"},{"id":"2602.00851","title":"Persuasion Propagation: Does Persuasion Change AI Agent Behavior?","created":"2026-01-31","cited_by_count":1,"area":null},{"id":"2603.29292","title":"Self-Improving Code Generation via Semantic Entropy and Behavioral Consensus","created":"2026-03-31","cited_by_count":1,"area":"alignment"},{"id":"2604.03587","title":"SecPI: Secure Code Generation with Reasoning Models via Security Reasoning Internalization","created":"2026-04-04","cited_by_count":1,"area":"lr"},{"id":"2605.02263","title":"Break the Block: Dynamic-size Reasoning Blocks for Diffusion Large Language Models via Monotonic Entropy Descent with Reinforcement Learning","created":"2026-05-04","cited_by_count":1,"area":"lr"},{"id":"2605.06183","title":"Rethinking Adapter Placement: A Dominant Adaptation Module Perspective","created":"2026-05-07","cited_by_count":1,"area":null},{"id":"2605.08472","title":"Mid-Training with Self-Generated Data Improves Reinforcement Learning in Language Models","created":"2026-05-08","cited_by_count":1,"area":"synth"},{"id":"2605.16342","title":"DACA-GRPO: Denoising-Aware Credit Assignment for Reinforcement Learning in Diffusion Language Models","created":"2026-05-08","cited_by_count":1,"area":"lr"},{"id":"2605.24697","title":"The Path Matters: Learning a Token-Commitment Policy for Diffusion Language Models","created":"2026-05-23","cited_by_count":1,"area":"diffusion"},{"id":"2605.31058","title":"Combinatorial Synthesis: Scaling Code RLVR via Atomic Decomposition and Recombination","created":"2026-05-29","cited_by_count":1,"area":null},{"id":"2606.02113","title":"A Primer in Post-Training Reasoning Data: What We Know About How It Works","created":"2026-06-01","cited_by_count":1,"area":"lr"},{"id":"2606.18487","title":"SFT Overtraining Predicts Rank Inversion via Entropy Collapse Under RLVR","created":"2026-06-16","cited_by_count":1,"area":null},{"id":"2607.14506","title":"Non-vacuous Generalization Bounds for Reinforcement Learning with Verifiable Rewards","created":"2026-07-16","cited_by_count":1,"area":"lr"},{"id":"2607.26504","title":"From Interface to Inference: Eliciting Any-Order Inference from Any-Order Models","created":"2026-07-29","cited_by_count":1,"area":"diffusion"},{"id":"2608.02026","title":"HPFA: Hypergraph-Based Paired Failure Attribution for LLM Reasoning","created":"2026-08-03","cited_by_count":1,"area":"lr"},{"id":"2609.38987","title":"Smaller Models, Better Rejects: Preference Distillation Scaling","created":"2026-09-30","cited_by_count":1,"area":"distill"},{"id":"2509.14281","title":"SCoGen: Scenario-Centric Graph-Based Synthesis of Real-World Code Problems","created":"2025-09-16","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":"2604.09741","title":"ExecTune: Effective Steering of Black-Box LLMs with Guide Models","created":"2026-04-09","cited_by_count":0,"area":null},{"id":"2605.06755","title":"Gradient Extrapolation-Based Policy Optimization","created":"2026-05-07","cited_by_count":0,"area":"lr"},{"id":"2605.08905","title":"Forge: Quality-Aware Reinforcement Learning for NP-Hard Optimization in LLMs","created":"2026-05-09","cited_by_count":0,"area":null},{"id":"2605.13839","title":"Good Agentic Friends Do Not Just Give Verbal Advice: They Can Update Your Weights","created":"2026-05-13","cited_by_count":0,"area":"agents"},{"id":"2605.18597","title":"Latent Action Reparameterization for Efficient Agent Inference","created":"2026-05-18","cited_by_count":0,"area":"agents"}],"next_cursor":"100"}