arXiv:2510.17843v1 Announce Type: new Abstract: Despite remarkable advances in Large Language Model capabilities, tool retrieval for agent-based systems remains fundamentally limited by reliance on semantic similarity, which fails to capture functional viability. Current methods often retrieve textually relevant but functionally…
arXiv:2510.18053v1 Announce Type: new Abstract: Balancing exploration and exploitation during reinforcement learning fine-tuning of generative models presents a critical challenge, as existing approaches rely on fixed divergence regularization that creates an inherent dilemma: strong regularization preserves model capabilities but limits…
arXiv:2510.18724v1 Announce Type: cross Abstract: Despite achieving impressive results on standard benchmarks, large foundational models still struggle against code-switching test cases. When data scarcity cannot be used as the usual justification for poor performance, the reason may lie in the…
arXiv:2510.18060v1 Announce Type: new Abstract: Developing autonomous vehicles (AVs) requires not only safety and efficiency, but also realistic, human-like behaviors that are socially aware and predictable. Achieving this requires sim agent policies that are human-like, fast, and scalable in multi-agent…
arXiv:2510.18830v1 Announce Type: cross Abstract: The adoption of long context windows has become a standard feature in Large Language Models (LLMs), as extended contexts significantly enhance their capacity for complex reasoning and broaden their applicability across diverse scenarios. Dynamic sparse…
arXiv:2510.18072v1 Announce Type: new Abstract: Flow-based generative models have shown remarkable success in text-to-image generation, yet fine-tuning them with intermediate feedback remains challenging, especially for continuous-time flow matching models. Most existing approaches solely learn from outcome rewards, struggling with the…
Researchers find that design elements of data visualizations influence viewers’ assumptions about the source of the information and its trustworthiness.
arXiv:2509.05542v2 Announce Type: replace Abstract: Training multimodal process reward models (PRMs) is hard due to (i) distribution shift between training set and test set and (ii) quality imbalance across training data samples. While domain-level reweighting (e.g., DreamPRM) aligns training with…
arXiv:2504.08277v2 Announce Type: replace Abstract: Physics-informed neural operators offer a powerful framework for learning solution operators of partial differential equations (PDEs) by combining data and physics losses. However, these physics losses rely on derivatives. Computing these derivatives remains challenging, with…
arXiv:2506.03725v3 Announce Type: replace Abstract: Quite recently, large language models have made a significant breakthrough across various disciplines. However, training them is an extremely resource-intensive task, even for major players with vast computing resources. One of the methods gaining popularity…
