Quality follows upgrading
All Articles
arXiv:2603.13173v1 Announce Type: new Abstract: Large Language Models (LLMs) increasingly serve as autonomous reasoning agents in decision support, scientific problem-solving, and multi-agent coordination systems. However, …
arXiv:2603.13168v1 Announce Type: new Abstract: The ability to provide trustworthy maternal health information using phone-based chatbots can have a significant impact, particularly in low-resource settings …
arXiv:2603.12733v1 Announce Type: new Abstract: Catastrophic failures of marine engines imply severe loss of functionality and destroy or damage the systems irreversibly. Being sudden and …
arXiv:2603.12740v1 Announce Type: new Abstract: Large Language Model (LLM) agents are increasingly applied to complex, multi-step tasks that require interaction with diverse external tools across …
arXiv:2603.12324v1 Announce Type: cross Abstract: Connections between statistical mechanics and machine learning have repeatedly proven fruitful, providing insight into optimization, generalization, and representation learning. In …
arXiv:2603.12273v1 Announce Type: cross Abstract: Multi-turn user interactions are among the most abundant data produced by language models, yet we lack effective methods to learn …
arXiv:2603.12288v1 Announce Type: cross Abstract: Tabular machine learning presents a paradox: modern models achieve state-of-the-art performance using high-dimensional (high-D), collinear, error-prone data, defying the "Garbage …
arXiv:2603.13099v1 Announce Type: new Abstract: We introduce **CRYSTAL** (*__C__lear __R__easoning via __Y__ielded __S__teps, __T__raceability and __L__ogic*), a diagnostic benchmark with 6,372 instances that evaluates multimodal …
arXiv:2603.12296v1 Announce Type: cross Abstract: Deep learning has achieved transformative performance across diverse domains, largely driven by the large-scale, high-quality training data. In contrast, the …
arXiv:2603.12483v1 Announce Type: new Abstract: Across many domains (e.g., IoT, observability, telecommunications, cybersecurity), there is an emerging adoption of conversational data analysis agents that enable …
arXiv:2603.12325v1 Announce Type: cross Abstract: Efficient exploration remains a central challenge in reinforcement learning, serving as a useful pretraining objective for data collection, particularly when …