arXiv 2610.08430 · cs.DC · 2026-10-06
NeMo-DCR: Bit-Exact Delta-Compressed Refit for Scalable Agentic RL at Trillion-Parameter Scale
Songlin Jiang, Zhiyu Li, Terry Kong, Yu Yao, Youngeun Kwon, Bernard Nguyen, Ashwath Aithal, Mario Di Francesco
NVIDIA
In latest · #100 Added on 2026-10-21
One-line takeaway
NeMo-DCR syncs only the ~1% of weights that change per step, bit-exactly, to speed trillion-parameter agentic RL refits.
NeMo-DCR 只传输每步变化的约 1% 权重并保证比特级一致，加速万亿参数 Agent RL 的权重同步。
Read on arXiv PDF Hugging Face discussion Code Project page
Topics & disciplines
More on Efficient training & inference
- The Teacher Is a Direction, Not a Destination: Extrapolating RL-Induced Representation Residuals in On-Policy Distillation ▲511
- Scaling Properties of Same-Family On-Policy Distillation ▲327
- Beyond Domain-Routed Supervision: Cross-Teacher Guarding for Multi-Teacher On-Policy Distillation ▲250
- On-Policy or Off-Policy Learning? A Systematic Study of Distillation Dynamics ▲205
- Beyond Teacher Assignment: Domain-Normalized Multi-Teacher On-Policy Distillation ▲181
More on Reinforcement learning
- False Frontiers: Diagnosing and Mitigating Co-Cheating in Self-Evolving Search Agents 2026-09-30 · ▲642
- Player-1: Learning to Play from Synthetic Experience 2026-10-14 · ▲347
- DiffusionART: Efficient, Stable and Scalable Reinforcement of Diffusion Models 2026-10-08 · ▲325
- Waypoint-OPD: Transferring RL-Induced Policy Shifts via Gated On-Policy Distillation 2026-10-15 · ▲219
- Agent-Reflex: Teaching Language Agents to Act Reflectively 2026-10-13 · ▲214
More from NVIDIA
- Joints, Camera, Action! Co-Generating 3D Motion and Video for Arbitrary Rigs 2026-10-20
- Long-WAM: Scaling the Context of World-Action Models 2026-10-07
- LoGRA: Scaling LLM Reinforcement Learning with Low-Rank Gradient Sketches 2026-10-05
- Mid-Harness: Scaling Actions Between Model and Harness for Terminal Agents 2026-09-30
- PixelUMM: Encoder-Free Unified Image and Video Understanding and Generation 2026-09-29
About this data
Metadata from the arXiv API (verified); upvotes from Hugging Face Daily Papers; citations from Semantic Scholar. Last refreshed 2026-10-23.
The takeaway is written by AIMap from the abstract; the abstract itself is not reproduced — read the original.