| SonicVerse: Multi-Task Learning for Music Feature-Informed Captioning | Jun 18, 2025 | Caption GenerationDescriptive | CodeCode Available | 2 |
| SEC-bench: Automated Benchmarking of LLM Agents on Real-World Software Security Tasks | Jun 13, 2025 | BenchmarkingLarge Language Model | CodeCode Available | 2 |
| AutoMind: Adaptive Knowledgeable Agent for Automated Data Science | Jun 12, 2025 | Code GenerationLarge Language Model | CodeCode Available | 2 |
| Learning What Reinforcement Learning Can't: Interleaved Online Fine-Tuning for Hardest Questions | Jun 9, 2025 | Large Language ModelReinforcement Learning (RL) | CodeCode Available | 2 |
| CyberGym: Evaluating AI Agents' Cybersecurity Capabilities with Real-World Vulnerabilities at Scale | Jun 3, 2025 | Large Language Model | CodeCode Available | 2 |
| Reasoning-Table: Exploring Reinforcement Learning for Table Reasoning | Jun 2, 2025 | Fact VerificationLanguage Modeling | CodeCode Available | 2 |
| Compiler Optimization via LLM Reasoning for Efficient Model Serving | Jun 2, 2025 | Compiler OptimizationLarge Language Model | CodeCode Available | 2 |
| FusionAudio-1.2M: Towards Fine-grained Audio Captioning with Multimodal Contextual Fusion | Jun 1, 2025 | Audio captioningCaption Generation | CodeCode Available | 2 |
| GeoVision Labeler: Zero-Shot Geospatial Classification with Vision and Language Models | May 30, 2025 | ClassificationDisaster Response | CodeCode Available | 2 |
| ML-Agent: Reinforcing LLM Agents for Autonomous Machine Learning Engineering | May 29, 2025 | Large Language ModelPrompt Engineering | CodeCode Available | 2 |
