arXiv:2602.16802v1 Announce Type: new Abstract: While Reinforcement Learning with Verifiable Rewards (RLVR) has shown strong effectiveness in reasoning tasks, it cannot be directly applied to non-verifiable domains lacking ground-truth verifiers, such as LLM alignment. In this work, we investigate whether reference-guided LLM-evaluators can bridge this gap by serving as soft “verifiers”. First, we design evaluation protocols that enhance LLM-based evaluators for LLM alignment using reference outputs. Through comprehensive experiments, we show that a reference-guided approach substantially improves the […]

Ver mais

Language models are revolutionizing the biochemistry domain, assisting scientists in drug design and chemical synthesis with high efficiency. Yet current approaches struggle between small language models prone to hallucination and limited knowledge retention, and large cloud-based language models plagued by privacy risks and high inference costs. To bridge this gap, we introduce ChemCRAFT, a novel framework leveraging agentic reinforcement learning to decouple chemical reasoning from knowledge storage. Instead of forcing the model to memorize vast chemical data, our […]

Ver mais

arXiv:2603.08713v1 Announce Type: new Abstract: Large Language Models (LLMs) have intensified the need for low-precision formats that enable efficient, large-scale inference. The Open Compute Project (OCP) Microscaling (MX) standard is attractive due to its favorable hardware efficiency, but its 4-bit variant (MXFP4) lags behind NVIDIA’s NVFP4 in accuracy, limiting adoption. We introduce two software-only techniques, Overflow-Aware Scaling (OAS) and Macro Block Scaling (MBS), that improve MXFP4 quantization fidelity without requiring hardware changes. OAS reduces overall errors by increasing […]

Ver mais

arXiv:2604.07380v1 Announce Type: new Abstract: We decompose the spectral edge — the dominant direction of the Gram matrix of parameter updates — into its gradient and weight-decay components during grokking in two sequence tasks (Dyck-1 and SCAN). We find a sharp two-phase lifecycle: before grokking the edge is gradient-driven and functionally active; at grokking, gradient and weight decay align, and the edge becomes a compression axis that is perturbation-flat yet ablation-critical (>4000x more impactful than random directions). Three […]

Ver mais

Hi all, Tara here, The Markup’s education reporter. You may have read my story about how college students are tracked by one system or another near constantly as they study and move around campus. I focused on a community college in Southern California and a student there who is particularly troubled by the digital privacy sacrifices required to pursue a degree. One part of campus I barely touched on was the library, and that’s why I’m back in your inboxes […]

Ver mais

Effective exploration is a key challenge in reinforcement learning for large language models: discovering high-quality trajectories within a limited sampling budget from the vast natural language sequence space. Existing methods face notable limitations: GRPO samples exclusively from the root, saturating high-probability trajectories while leaving deep, error-prone states under-explored. Tree-based methods blindly disperse budgets across trivial or unrecoverable states, causing sampling dilution that fails to uncover rare correct suffixes and destabilizes local baselines. To address this, we propose Deep […]

Ver mais

arXiv:2601.03430v1 Announce Type: new Abstract: Open Source Software for Social Good (OSS4SG) projects aim to address critical societal challenges, such as healthcare access and community safety. Understanding the community dynamics and contributor patterns in these projects is essential for ensuring their sustainability and long-term impact. However, while extensive research has focused on conventional Open Source Software (OSS), little is known about how the mission-driven nature of OSS4SG influences its development practices. To address this gap, we conduct a […]

Ver mais