Consolidating RLVR Capabilities Across Domains: A Deep Dive into Fusion Paradigms

arXiv:2608.27409 · cs.CL · Submitted 2026-08-27 · Read on arXiv

cs.CL

Submitted: 2026-08-27

Updated: 2026-09-18

Code: https://github.com/huggingface/peft

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Benchmark — 29× in this paper · explained in 2 episodes
• Instruction Following — 18× in this paper
• Accuracy — 16× in this paper · explained in 1 episode
• Distillation — 14× in this paper · explained in 2 episodes
• Reinforcement Learning — 11× in this paper · explained in 4 episodes
• On-Policy Distillation — 10× in this paper · explained in 3 episodes
• Task Arithmetic — 7× in this paper
• GRPO — 6× in this paper · explained in 6 episodes
• Verifier — 6× in this paper · explained in 2 episodes
• Cosine Similarity — 5× in this paper · explained in 3 episodes
• Thinking mode — 4× in this paper · explained in 2 episodes
• Transformer — 4× in this paper · explained in 2 episodes
• Verifiable Rewards — 4× in this paper · explained in 2 episodes
• Adam — 3× in this paper · explained in 2 episodes
• Adaptation — 2× in this paper · explained in 1 episode
• Group Relative Policy Optimization — 2× in this paper
• Group Relative Policy Optimization (GRPO) — 2× in this paper · explained in 5 episodes
• Trace — 2× in this paper · explained in 2 episodes
• Agentic Reasoning — 1× in this paper · explained in 1 episode
• Fine-Tuning — 1× in this paper · explained in 5 episodes
• Generalization — 1× in this paper · explained in 13 episodes
• LLM judge — 1× in this paper · explained in 2 episodes
• Large Language Models (LLMs) — 1× in this paper · explained in 6 episodes
• Low-Rank Adaptation (LoRA) — 1× in this paper · explained in 9 episodes
• Parameter-Efficient Fine-Tuning — 1× in this paper · explained in 2 episodes
• Regret — 1× in this paper · explained in 3 episodes

Sources

• Nemotron 3 Nano: Open, Efficient Mixture-of-Experts Hybrid Mamba-Transformer Model for Agentic Reasoning
• Evaluating Large Language Models Trained on Code
• Weak-to-Strong Generalization via Direct On-Policy Distillation
• Co-Evolving Policy Distillation
• DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
• SimpleQA Verified: A Reliable Factuality Benchmark to Measure Parametric Knowledge
• Step 3.5 Flash: Open Frontier-Level Intelligence with 11B Active Parameters
• OpenAI o1 System Card
• Rethinking On-Policy Distillation of Large Language Models: Phenomenology, Mechanism, and Recipe
• Can One Domain Help Others? A Data-Centric Study on Multi-Domain Reasoning via Reinforcement Learning
• DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
• To Mix or To Merge: Toward Multi-Domain Reinforcement Learning for Large Language Models
• Cross-LoRA: A Data-Free LoRA Transfer Framework across Heterogeneous LLMs
• MiMo-V2-Flash Technical Report
• DeepSeek-V4: Towards Highly Efficient Million-Token Context Intelligence
• Qwen3 Technical Report
• Learning beyond Teacher: Generalized On-Policy Distillation with Reward Extrapolation
• Is One Layer Enough? Training A Single Transformer Layer Can Match Full-Parameter RL Training
• Instruction-Following Evaluation for Large Language Models

Related papers

• Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
• Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
• Subliminal Steering: Stronger Encoding of Hidden Signals
• MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
• The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
• Untangling the Mechanisms of Misleading Context in Medical Question Answering