Don’t miss the Expo Talk by Alex Piché & Dzmitry Bahdanau at #COLM2025! 📢 Fast On-Policy RL for Long Sequence Generation 📍Oct 9 | 1–2:30 PM | Room 523A-B They’ll present PipelineRL: ⚡2x faster learning on long-form reasoning (128 H100s) ⚡Fresh, on-policy data

🚀 New Research Blog Live! Our latest post is out: Unifying autoregressive & diffusion language models by Nima Fathi, Torsten Scholak, and Pierre-André Noël. 𝗔𝘂𝘁𝗼𝗿𝗲𝗴𝗿𝗲𝘀𝘀𝗶𝘃𝗲 and 𝗱𝗶𝗳𝗳𝘂𝘀𝗶𝗼𝗻 𝗺𝗼𝗱𝗲𝗹𝘀 have each driven major advances in generative AI — but

Ivan Titov (Ivan Titov) on faithful and privacy-preserving LLMs -- CoTs are unfaithful -- Preference optimization increases unfaithfulness -- incorporating interpretability through counterfactuals into reward models improve faithfulness -- people share private information in LLM

🚀 The RL community keeps pushing boundaries — from better on-policy data and partial rollouts to in-flight weight updates that mix KV caches across models during inference. Continuing inference while weights change and KV states stay stale sounds wild — but that’s exactly what

Very excited to see vLLM supports Pipeline RL’s in-flight weight updates! It allowed our team to quickly and reliably train Qwen base 7B to reason from scratch! Want to hear more? Join us at our Pipeline RL expo talk at CoLM this Thursday 1PM room 524C.

🎉 It’s CoLM week! The Conference on Language Modeling (CoLM 2025) kicks off tomorrow in Montréal 🇨🇦🍁 Proud that ServiceNow AI Research is a main sponsor — and that our team will present 5 papers on: 📊 Multimodal reasoning 🔄 Unified AR & diffusion models 🔍 Dense retrieval

🧠 Don’t miss it at #COLM2025! SOCIAL: “Reasoning LLMs – Tips & Tricks Discussion” 📅 Tue, Oct 7 | 🕐 1:00–2:30 PM | 📍 Room 517BC Co-presented by ServiceNow AI Research + NVIDIA with Torsten Scholak (ServiceNow) & Olivier Delalleau (NVIDIA). Join the discussion on advancing

📢 Excited to share our COLM 2025 paper: BigCharts-R1 📊 We introduce a new dataset and training framework that push the boundaries of chart reasoning in VLMs. 🗓️ Join us at Poster Session 4 on Wednesday, 4:30 PM! 🧵 Thread below 👇 arxiv.org/abs/2508.09804

✨ What if we could tune Frontier LLM agents without touching any weights? Meet JEF-Hinter, an agent capable of analyzing multiple offline trajectories to extract auditable and timely hints💡 In our new paper 📄 , we show significant performance gains on downstream tasks ⚡ with

📢 Don’t miss it tomorrow at #COLM2025! Our researcher Arjun Ashok will present 🧩 “Context is Key: A Benchmark for Forecasting with Essential Textual Information”⏳ 🕓 4:45 PM at the XTempLLMs 2025 workshop 🔗 xtempllms.github.io/2025/program.h… #AIresearch #ServiceNowResearch #XTempLLMs

Very excited to be presenting Pipeline RL this afternoon at CoLM. Join us if you are interested in fast on policy RL training for LLMs 🚀

🚀 Releasing DRBench, an Enterprise-Grade Deep Research Benchmark Paper! 📄 Paper: lnkd.in/gpRXbb7K 💻 Code: lnkd.in/g4-x5EDc We’re excited to introduce DRBench, the first benchmark designed to evaluate deep research agents on open-ended enterprise research tasks,

What a night! 🧠 Last week, ServiceNow AI Research & lawrence hosted a special social event on AI safety & security alongside the #CoLM2025 conference in Montreal. Key takeaways: • System-level design matters • Real-world > benchmark risks • Balancing short- & long-term safety

🚀 Internship Opportunities in AI Agents! At ServiceNow AI Research, we have 4 internship positions on AI Agents — exploring robustness, privacy & collaboration. 🧠 Applicants must be registered students at a Canadian university. 👇 Thread with details & links to apply:

Had a great time talking about how to train LLM agents at The AI Alliance, awesome questions from the crowd! 📷: youtube.com/watch?v=zTI4kF…