·
DataBubble
  • Home
  • Models
  • News
  • Compare
  • Boards
  • Pricing
  • About
  • Newsletter
  • Methodology
  • Contact
Latest
Svarna: An Open Corpus Workbench for Modern Greek6h◆PLURAL: A Global Dataset for Value Alignment6h◆Validating LLMs in social science: Epistemic threats and emerging norms6h◆How Do I Know What to Say Next? Barenholtz's Autogenerative Theory as an Enrichment of Harrisean Integrationism6h◆WebSwarm: Recursive Multi-Agent Orchestration for Deep-and-Wide Web Search6h◆Temporal Preference Concepts and their Functions in a Large Language Model6h◆UniClawBench: A Universal Benchmark for Proactive Agents on Real-World Tasks6h◆When Synthetic Speech Is All You Have: Better Call GRPO6h◆ParamMute: Suppressing Knowledge-Critical FFNs for Faithful Retrieval-Augmented Generation6h◆Towards Isolated Interventions via Almost Orthogonal Features in Language Models6h◆MASTE: A Multi-Agent Pipeline for Zero-Shot Aspect Sentiment Triplet Extraction6h◆Peer-Predictive Self-Training for Language Model Reasoning6h◆DeepTutor: Towards Agentic Personalized Tutoring6h◆COBART: Controlled, Optimized, Bidirectional and Auto-Regressive Transformer for Ad Headline Generation6h◆Hallucination Self-Play: Bootstrapping Reinforced Detector via Evolved Generator6h◆CausalDS: Benchmarking Causal Reasoning in Data-Science Agents6h◆Towards Efficient Large Language Model Serving: A Survey on System-Aware KV Cache Optimization6h◆Large-Language-Models-as-a-Judge in Theory-Agnostic Adaptive Metric-Alignment for Prototypical Networks in Personality Recognition6h◆Where do LLMs Fall Short in CBT-Guided Affective Reasoning?6h◆Holographic Neural PCFG for Unsupervised Parsing6h◆Svarna: An Open Corpus Workbench for Modern Greek6h◆PLURAL: A Global Dataset for Value Alignment6h◆Validating LLMs in social science: Epistemic threats and emerging norms6h◆How Do I Know What to Say Next? Barenholtz's Autogenerative Theory as an Enrichment of Harrisean Integrationism6h◆WebSwarm: Recursive Multi-Agent Orchestration for Deep-and-Wide Web Search6h◆Temporal Preference Concepts and their Functions in a Large Language Model6h◆UniClawBench: A Universal Benchmark for Proactive Agents on Real-World Tasks6h◆When Synthetic Speech Is All You Have: Better Call GRPO6h◆ParamMute: Suppressing Knowledge-Critical FFNs for Faithful Retrieval-Augmented Generation6h◆Towards Isolated Interventions via Almost Orthogonal Features in Language Models6h◆MASTE: A Multi-Agent Pipeline for Zero-Shot Aspect Sentiment Triplet Extraction6h◆Peer-Predictive Self-Training for Language Model Reasoning6h◆DeepTutor: Towards Agentic Personalized Tutoring6h◆COBART: Controlled, Optimized, Bidirectional and Auto-Regressive Transformer for Ad Headline Generation6h◆Hallucination Self-Play: Bootstrapping Reinforced Detector via Evolved Generator6h◆CausalDS: Benchmarking Causal Reasoning in Data-Science Agents6h◆Towards Efficient Large Language Model Serving: A Survey on System-Aware KV Cache Optimization6h◆Large-Language-Models-as-a-Judge in Theory-Agnostic Adaptive Metric-Alignment for Prototypical Networks in Personality Recognition6h◆Where do LLMs Fall Short in CBT-Guided Affective Reasoning?6h◆Holographic Neural PCFG for Unsupervised Parsing6h◆
News/Nemotron-Cascade: Scaling Cascaded Reinforcement Learning for General-Purpose Reasoning Models
arxiv
PublishedMarch 30, 2026 at 4:00 AM

Nemotron-Cascade: Scaling Cascaded Reinforcement Learning for General-Purpose Reasoning Models

Source
arxiv.orgfull article ↗
Read on arxiv→
Publisher summary· verbatim

arXiv:2512.13607v2 Announce Type: replace-cross Abstract: Building general-purpose reasoning models with reinforcement learning (RL) entails substantial cross-domain heterogeneity, including large variation in inference-time response lengths and verification latency. Such variability complicates the

Stay posted· Newsletter

A 5-min weekly brief — top movers, price watch, story of the week.

// no spam · unsubscribe one-click · free forever

Discussion
Source
↗
arxiv
Read original ↗All from arxiv →

No replies yet. Be first.

Source
↗
arxiv
Read original ↗All from arxiv →

Related coverage

More from ARXIV
arxivSvarna: An Open Corpus Workbench for Modern Greek6harxivPLURAL: A Global Dataset for Value Alignment6harxivValidating LLMs in social science: Epistemic threats and emerging norms6harxivHow Do I Know What to Say Next? Barenholtz's Autogenerative Theory as an Enrichment of Harrisean Integrationism6h
The Bubble Brief
WEEKLY

Read AI insights every Tuesday — top movers, new releases, story of the week.

// no spam · unsubscribe one-click · free forever

Originally published on arxiv ↗
HomeModelsNews