Model Releases
Great paper from NVIDIA sharing an open midtraining recipe for agentic coding. NVIDIA kept SFT identical and added one midtraining stage. SW…
Great paper from NVIDIA sharing an open midtraining recipe for agentic coding. NVIDIA kept SFT identical and added one midtraining stage. SWE-bench Multilingual went from 55.8 to 62.8 on Nemotron 3.5
Great paper from NVIDIA sharing an open midtraining recipe for agentic coding. NVIDIA kept SFT identical and added one midtraining stage. SWE-bench Multilingual went from 55.8 to 62.8 on Nemotron 3.5 Lightning. The stage sits between pretraining and post-training. It trains at 256K context on 500B tokens of natural software-engineering data, such as packed repositories, pull requests, commit histories and build logs, plus a small share of agent traces. On the same model, SWE-bench Verified rose from 60.7 to 64.5 and SWE-bench Pro from 32.0 to 35.5. On the larger Nemotron 3.5 Super, DeepSWE rose from 11.7 to 15.7. They also explain how they evaluated the recipe. Base-model proxy metrics did not predict post-training results, so every data choice was scored with short fixed SFT runs. If you train coding agents, the recipe and its ablations are published. https://arxiv.org/abs/2610.22019 Chat with Paper: https://academy.dair.ai/papers/priming-base-models-for-agentic-post-training-an-open-midtraining-recipe-2610.22019
Related
- Cool new paper from NVIDIA. Looks like agentic coding is moving into hardware design. HORIZON treats hardware design as repository-level cod…
- Banger paper from NVIDIA. Agentic reasoning needs models that are not just capable, but efficient at long-context inference. The agent model…
- Banger compression paper from NVIDIA. (bookmark it) Bigger MoE models keep winning on quality, but serving them at interactive latency is st…
- Banger paper from NVIDIA on test-time compute for terminal agents. The finding is that you should sample several candidate shell commands, v…
Source: DAIR.AI (X) | 2026-10-17