Seungone Kim

#NLProc New paper on "evaluation-time scaling", a new dimension to leverage test-time compute! We replicate the test-time scaling behaviors observed in generators (e.g., o1, r1, s1) with evaluators by enforcing to generate additional reasoning tokens. arxiv.org/abs/2503.19877

I’ll be presenting our LLM-as-an-Interviewer work at #ACL2025! 📅 When: July 30 (wed) 11:00-12:30 📍 Where: Hall 4/5 arxiv.org/abs/2412.10424 Feel free to stop by ! Looking forward to discussing (m)LLM evaluation and more!

Can LLMs self-improve on code generation? Check out our work AlphaVerus where model generates provably correct code and self-improves without any weight updates! At #ICML2025 today: 📆: 11:00 AM - 1:30 PM 📷: Poster #East-2912 alphaverus.github.io w/ Bryan, @wellecks

Some updates 🚨 I finished my Ph.D at @uwcse in June 2025! After a year at AI2 as a Research Scientist, I am joining CMU @LTIatCMU & @mldcmu (courtesy) as an Assistant Professor in Fall 2026. The journey, acknowledgments & recruiting in 🧵

Tokenization has been the final barrier to truly end-to-end language models. We developed the H-Net: a hierarchical network that replaces tokenization with a dynamic chunking process directly inside the model, automatically discovering and operating over meaningful units of data

People are racing to push math reasoning performance in #LLMs—but have we really asked why? The common assumption is that improving math reasoning should transfer to broader capabilities in other domains. But is that actually true? In our study (arxiv.org/pdf/2507.00432), we…

We've always been excited about self-play unlocking continuously improving agents. Our insight: RL selects generalizable CoT patterns from pretrained LLMs. Games provide perfect testing grounds with cheap, verifiable rewards. Self-play automatically discovers and reinforces…

New preprint on web agents🚨 Go-Browse: Training Web Agents with Structured Exploration Problem: LLMs lack prior understanding of the websites that web agents will be deployed on. Solution: Go-Browse is an unsupervised method for automatically collecting diverse and realistic…

👆 OpenAI recently rolled back its GPT- 4o update due to Sycophancy—being overly flattering and agreeable. 🧐 However, can we measure sycophancy in these Real-World failure cases? 🤗 Introducing SYCON-Bench, a benchmark that quantifies sycophancy in multi-turn dialogues! 📑 1/5

New paper by Andre He: Rewarding the Unlikely: Lifting GRPO Beyond Distribution Sharpening arxiv.org/abs/2506.02355 Tired of sharpening the distribution? Try unlikeliness reward to learn new things from the roads less traveled

Using LLMs to build AI scientists is all the rage now (e.g., Google’s AI co-scientist [1] and Sakana’s Fully Automated Scientist [2]), but how much do we understand about their core scientific abilities? We know how LLMs can be vastly useful (solving complex math problems) yet…

🚨 @frimelle and I are looking for a junior collaborator to research the Open Model Ecosystem! 🤖 Ideally, someone w/ AI/ML background, who can help w/ annotation pipeline + analysis. docs.google.com/forms/d/e/1FAI…

Thrilled to announce that I will be joining @UTAustin @UTCompSci as an assistant professor in fall 2026! I will continue working on language models, data challenges, learning paradigms, & AI for innovation. Looking forward to teaming up with new students & colleagues! 🤠🤘

🚨 New Paper co-led with @bkjeon1211 🚨 Q. Can we adapt Language Models, trained to predict next token, to reason in sentence-level? I think LMs operating in higher-level abstraction would be a promising path towards advancing its reasoning, and I am excited to share our…

Within the RAG pipeline, the retriever often acts as the bottleneck! Instead of training a better embedding model, we explore using a reasoning model both as the retriever&generator. To do this, we add MCTS to the generative retrieval pipeline. Check out @chaechaek1214's post!

❓What if your RAG didn’t need a separate retrieval model at all? We present 🧊FREESON, a new framework for retriever-FREE retrieval-augmented reasoning. With FREESON, a single LRM acts as both generator and retriever, shifting the focus from seq2seq matching to locating…

We introduce Web Shepherd, the first PRM specialized for web navigation🌎 Prior works have used LLM-as-a-Judge to assess trajectories (RL) or each step (test-time algo.). Yet, this is not suitable in real-world scenarios since it takes too much time! Web Shepherd not only…

🚀 Introducing Web-Shepherd: the first Process Reward Model (PRM) that guides web agents. 🌐 Current web browsing agents look cool, but they're not fully reliable! 😬They excel at simple tasks but struggle with complex ones. ❓ Can inference-time scaling help? Previous methods…

Web-Shepherd just dropped on Hugging Face Advancing PRMs for Reinforcing Web Agents

Turns out that reasoning models not only excel at solving problems but are also excellent confidence estimators - an unexpected side effect of long CoTs! This reminds me that smart ppl are good at determining what they know & don't know👀 Check out @dongkeun_yoon 's post!