Arian Hosseini (@arianTBD) header
Arian Hosseini (@arianTBD) profile picture

Research Scientist @GoogleDeepMind - LLM post-training - prev: @Google @MSFTResearch

Montréal, Québec
Joined March 2011
After nearly two years, I’ve decided to leave GDM. It was an incredible journey working on post-training, distillation and agentic reasoning for Gemini and Gemma. But the people made it special. Feeling lucky to have worked alongside so many brilliant minds.
13
127
5,421
Arian Hosseini retweeted
Want to train your SWE agents 2× faster 🏎️💨? We introduce KV-streams, which, rather than flushing the KV cache on agentic compaction, we preserve it and keep generating. This avoids the re-prefill cost on both the inference engine and the trainer. Unlike other works that assume a fixed compaction strategy, we show that KV-streams can work with any compaction method in agentic tasks. Using what we learn from experiments in text-based games. We scale KV-streams to SWE tasks, where we match the performance of re-prefill compaction and full context in half the time 🚀 arxiv.org/pdf/2609.35750 🧵
11
49
17
304
55,674
So proud of my Montrealer 🇨🇦 collaborators @BahareFatemi , @kazemi_sm , and our whole team for the contributions to the agentic capabilities behind this release. Huge milestone today! 🚀
Introducing Gemini 4 Argon – our new frontier model. It’s built for complex workflows across coding, enterprise knowledge work, and cybersecurity defense – rolling out today to a set of trusted testers through our Fairwind Program.
2
5
54
2,684
I’m in Seoul for ICML 🇰🇷 I’ll be at the Google DeepMind booth. Our team in Mountain View is hiring researchers. Come by if you’re interested or just want to chat 👋🏼
5
2
125
7,386
Our team at Google DeepMind is hiring a Research Scientist in Mountain View! Focus is on bridging foundational research & practical GenAI deployments. ✅ PhD in CS/ML ✅ LLMs & diffusion expertise ✅ Top-tier ML pubs ✅ Python/JAX/PyTorch Apply : google.com/about/careers/app…
3
11
136
13,710
Our team at GDM is hiring a Student Researcher (SR) next year 🧠 If you’re a PhD student working on LLMs please apply. I’d love to hear from you. Please fill out this form: forms.gle/bxTEkrDPacn6jSxi6
4
29
3
280
66,052
The new Gemini is out and the reasoning capabilities are next level 🧠 fun one to be a part of. Congrats to the whole team!
1
6
3,438
Come by ScaleR #COLM2025. Nishad and I will be presenting this work!
Want to know how to optimally scale test-time compute with generative verifiers? Come to our poster at #COLM2025 🇨🇦. hmu if you want to chat about LLM reasoning and agents! :) Poster session 1 (Tuesday Morning 11 AM - 1 PM), Poster number: 24.
1
17
2,098
Introducing linear scaling of reasoning: 𝐓𝐡𝐞 𝐌𝐚𝐫𝐤𝐨𝐯𝐢𝐚𝐧 𝐓𝐡𝐢𝐧𝐤𝐞𝐫 Reformulate RL so thinking scales 𝐎(𝐧) 𝐜𝐨𝐦𝐩𝐮𝐭𝐞, not O(n^2), with O(1) 𝐦𝐞𝐦𝐨𝐫𝐲, architecture-agnostic. Train R1-1.5B into a markovian thinker with 96K thought budget, ~2X accuracy 🧵
14
196
29
899
208,286
Come by # 82 at #COLM2025
Presenting this tomorrow at COLM :) Come say hello @ 4:30 #82
1
14
2,251
Arian Hosseini retweeted
Our new work probes LLMs’ multi-turn reasoning and planning capabalities via five challenging games. Check it out!
LLMs are great at single-shot problems, but in the era of experience, interactive environments are key 🔑 Introducing * Multi-Turn Puzzles (MTP) * , a new benchmark to test multi-turn reasoning and strategizing 🔗 Paper: huggingface.co/papers/2508.1… 🫙Data: huggingface.co/datasets/aria…
2
13
1,297
LLMs are great at single-shot problems, but in the era of experience, interactive environments are key 🔑 Introducing * Multi-Turn Puzzles (MTP) * , a new benchmark to test multi-turn reasoning and strategizing 🔗 Paper: huggingface.co/papers/2508.1… 🫙Data: huggingface.co/datasets/aria…
1
9
4
46
6,811
Our analysis shows stronger models don't just guess better. they build coherent plans, ask complex questions, and re-evaluate their own conclusions based on new info. Weaker models jump to conclusions and ask less or questions. It's simple Q&A vs strategic dialogue. 7/n
1
4
354