{"total":34,"rows":[{"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":"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":"2510.23538","title":"JanusCoder: Towards a Foundational Visual-Programmatic Interface for Code Intelligence","created":"2025-10-27","cited_by_count":9,"area":null},{"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":"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":"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":"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":"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":"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":"2602.00851","title":"Persuasion Propagation: Does Persuasion Change AI Agent Behavior?","created":"2026-01-31","cited_by_count":1,"area":null},{"id":"2605.06183","title":"Rethinking Adapter Placement: A Dominant Adaptation Module Perspective","created":"2026-05-07","cited_by_count":1,"area":null},{"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":"2606.18487","title":"SFT Overtraining Predicts Rank Inversion via Entropy Collapse Under RLVR","created":"2026-06-16","cited_by_count":1,"area":null},{"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":"2605.08905","title":"Forge: Quality-Aware Reinforcement Learning for NP-Hard Optimization in LLMs","created":"2026-05-09","cited_by_count":0,"area":null},{"id":"2605.19357","title":"SciCustom: A Framework for Custom Evaluation of Scientific Capabilities in Large Language Models","created":"2026-05-19","cited_by_count":0,"area":null},{"id":"2606.25450","title":"The Generalization Spectrum: A Chromatographic Approach to Evaluating Learning Algorithms","created":"2026-06-24","cited_by_count":0,"area":null},{"id":"2608.01804","title":"LEAP: Lean Environment-Feedback via Adaptive Pruning for Code RL in GPU Kernel Generation","created":"2026-08-03","cited_by_count":0,"area":null},{"id":"2608.05148","title":"Reasoning Core: Designing Broad Procedural Data for Completion-Supervised Reasoning Training","created":"2026-08-05","cited_by_count":0,"area":null},{"id":"2608.17268","title":"Understanding Curriculum Learning in Large Language Models via Cross-Difficulty Optimization Dynamics","created":"2026-08-18","cited_by_count":0,"area":null},{"id":"2609.22409","title":"Contextual Causality with Large Language Models: A Survey","created":"2026-09-18","cited_by_count":0,"area":null},{"id":"2609.33725","title":"Reliable Replay through Spatial Coherence in Online Continual Learning","created":"2026-09-27","cited_by_count":0,"area":null},{"id":"2609.33845","title":"How code helps different tasks? A decompositional lens on LLM post-training","created":"2026-09-27","cited_by_count":0,"area":null},{"id":"2610.15894","title":"Make Every Expansion Count: Learning to Search Efficiently in LLM Code Repair","created":"2026-10-11","cited_by_count":0,"area":null},{"id":"2610.20538","title":"PrismaCoder: Pushing the Boundaries of Open Multimodal Code Intelligence through Decomposed Rubric Synthesis","created":"2026-10-14","cited_by_count":0,"area":null}],"next_cursor":null}