Nemotron-Cascade 2: Post-Training LLMs with Cascade RL and Multi-Domain On-Policy Distillation
Paper • 2603.19220 • Published • 69
Post training
-
-
Not Every Rubric Teaches Equally: Policy-Aware Rubric Rewards for RLVR
Paper • 2605.20164 • Published • 6 -
GoLongRL: Capability-Oriented Long Context Reinforcement Learning with Multitask Alignment
Paper • 2605.19577 • Published • 58 -
EnvFactory: Scaling Tool-Use Agents via Executable Environments Synthesis and Robust RL
Paper • 2605.18703 • Published • 50 -
Mid-Training with Self-Generated Data Improves Reinforcement Learning in Language Models
Paper • 2605.08472 • Published • 5 -
Self-Distilled Agentic Reinforcement Learning
Paper • 2605.15155 • Published • 112 -
Learning to Build the Environment: Self-Evolving Reasoning RL via Verifiable Environment Synthesis
Paper • 2605.14392 • Published • 8 -
RewardHarness: Self-Evolving Agentic Post-Training
Paper • 2605.08703 • Published • 10 -
RubricEM: Meta-RL with Rubric-guided Policy Decomposition beyond Verifiable Rewards
Paper • 2605.10899 • Published • 79 -
Towards On-Policy Data Evolution for Visual-Native Multimodal Deep Search Agents
Paper • 2605.10832 • Published • 22 -
Missing Old Logits in Asynchronous Agentic RL: Semantic Mismatch and Repair Methods for Off-Policy Correction
Paper • 2605.12070 • Published • 16 -
Reward Hacking in Rubric-Based Reinforcement Learning
Paper • 2605.12474 • Published • 5 -
AutoLLMResearch: Training Research Agents for Automating LLM Experiment Configuration -- Learning from Cheap, Optimizing Expensive
Paper • 2605.11518 • Published • 4 -
DeltaRubric: Generative Multimodal Reward Modeling via Joint Planning and Verification
Paper • 2605.09269 • Published • 6 -
DeepRefine: Agent-Compiled Knowledge Refinement via Reinforcement Learning
Paper • 2605.10488 • Published • 3 -
Flow-OPD: On-Policy Distillation for Flow Matching Models
Paper • 2605.08063 • Published • 101 -
OpenSeeker-v2: Pushing the Limits of Search Agents with Informative and High-Difficulty Trajectories
Paper • 2605.04036 • Published • 69 -
QUEST: Training Frontier Deep Research Agents with Fully Synthetic Tasks
Paper • 2605.24218 • Published • 42 -
Claw-Anything: Benchmarking Always-On Personal Assistants with Broader Access to User's Digital World
Paper • 2605.26086 • Published • 24 -
RUBRIC-ARROW: Alternating Pointwise Rubric Reward Modeling for LLM Post-training in Non-verifiable Domains
Paper • 2605.29156 • Published • 14 -
Verifiable Rewards Beyond Math and Code: Lightweight Corpus-Grounded Process Supervision for Factual Question Answering
Paper • 2605.29648 • Published • 10 -
LongTraceRL: Learning Long-Context Reasoning from Search Agent Trajectories with Rubric Rewards
Paper • 2605.31584 • Published • 41 -
GrepSeek: Training Search Agents for Direct Corpus Interaction
Paper • 2605.29307 • Published • 106 -
SAAS: Self-Aware Reinforcement Learning for Over-Search Mitigation in Agentic Search
Paper • 2605.29796 • Published • 25 -
OpenWebRL: Demystifying Online Multi-turn Reinforcement Learning for Visual Web Agents
Paper • 2606.02031 • Published • 20 -
When Does Multi-Agent RL Improve LLM Workflows? Workflow, Scale, and Policy-Sharing Tradeoffs
Paper • 2605.24202 • Published • 17 -
PaddleOCR-VL-1.6: Expanding the Frontier of Document Parsing with Under-Optimized Region Refinement and Progressive Post-Training
Paper • 2606.03264 • Published • 16 -
Reproducing, Analyzing, and Detecting Reward Hacking in Rubric-Based Reinforcement Learning
Paper • 2606.04923 • Published • 37 -
Reinforcement Learning from Rich Feedback with Distributional DAgger
Paper • 2606.05152 • Published • 3 -
Compress-Distill: Reasoning Trace Compression for Efficient Knowledge Distillation
Paper • 2606.05988 • Published • 2 -
Critic-R: Improving Agentic Search using Instruction-tuned Retrievers with Natural Language Introspective Feedback
Paper • 2606.00590 • Published -
SearchSwarm: Towards Delegation Intelligence in Agentic LLMs for Long-Horizon Deep Research
Paper • 2606.09730 • Published • 49 -
FORT-Searcher: Synthesizing Shortcut-Resistant Search Tasks for Training Deep Search Agents
Paper • 2606.12087 • Published • 71 -
EvoBrowseComp: Benchmarking Search Agents on Evolving Knowledge
Paper • 2606.13120 • Published • 4