| HALO: Hierarchical Autonomous Logic-Oriented Orchestration for Multi-Agent LLM Systems | May 17, 2025 | Arithmetic ReasoningCode Generation | CodeCode Available | 1 |
| Reinforcing the Diffusion Chain of Lateral Thought with Diffusion Language Models | May 15, 2025 | Code GenerationGSM8K | —Unverified | 0 |
| Rethinking Repetition Problems of LLMs in Code Generation | May 15, 2025 | Code GenerationHumanEval | CodeCode Available | 1 |
| AttentionInfluence: Adopting Attention Head Influence for Weak-to-Strong Pretraining Data Selection | May 12, 2025 | GSM8KHumanEval | —Unverified | 0 |
| Enhancing Code Generation via Bidirectional Comment-Level Mutual Grounding | May 12, 2025 | Code GenerationComment Generation | CodeCode Available | 0 |
| Web-Bench: A LLM Code Benchmark Based on Web Standards and Frameworks | May 12, 2025 | Code Generation | CodeCode Available | 3 |
| CodeMixBench: Evaluating Large Language Models on Code Generation with Code-Mixed Prompts | May 8, 2025 | Code CompletionCode Generation | —Unverified | 0 |
| The Art of Repair: Optimizing Iterative Program Repair with Instruction-Tuned Models | May 5, 2025 | HumanEvalProgram Repair | —Unverified | 0 |
| Memorization or Interpolation ? Detecting LLM Memorization through Input Perturbation Analysis | May 5, 2025 | ArticlesHumanEval | —Unverified | 0 |
| Rewriting Pre-Training Data Boosts LLM Performance in Math and Code | May 5, 2025 | Code GenerationGSM8K | CodeCode Available | 1 |
