Daniel Fried

User simulators bridge RL with real-world interaction // jessylin.com/2025/07/10/use… How do we get the RL paradigm to work on tasks beyond math & code? Instead of designing datasets, RL requires designing environments. Given that most non-trivial real-world tasks involve…

I will be at #ICML2025 🇨🇦 from Wednesday through Saturday. My students have a lot of exciting papers - check them out and come talk to us! Especially thrilled to have received the Outstanding Paper Award🏆 for our work on creativity.

Excited to be hanging out today at @WiMLworkshop 👩🏻‍💻 Come say hi during the poster session 🕝 2:45–3:30pm 📍 West Meeting Room 211–214 Let’s chat about how coding agents are changing developer workflows! 🤖💻🔧✨

Are code agents good at software design, ie building general and reusable code? We present Librarian, a new refactoring method, and MiniCode, a verifiable refactoring benchmark that requires agents to design libraries that jointly minimizes code from multiple repos 🧵

I've recently started my job as an asst professor at NTU, Singapore. If you are ever in town come say hi :)

Humans can perform complex reasoning without relying on specific domain knowledge, but can multimodal models truly do that as well? Short answer: No. Even the best models perform below the 5th-percentile human on our VisualPuzzles tasks. 🚀 Introducing VisualPuzzles🧩: a new…

Just look at these multi-modal refinement instructions! How would we ground them into reasonable executions?? joint work with @wp_mccarthy @saujasv @judyefan @dan_fried @KarlDD @JustinMatejka

What would it take to build agents that can similarly follow refinement instructions? We hope that mrCAD can help, by giving rollouts of successful human-human communications. [8/n]

Analyzing the instructions from successful rollouts reveals that: - people used more drawings in generation (round 1) and more texts in refinement (round 2+) - the texts become more "verb like" in refinements - the drawings become more partial in refinements [6/n]

In this multi-turn instruction following work, we found pretty interesting changes in the modalities people use to communicate from turn to turn -- and gaps in grounded LLM performance. I'm excited about this domain and dataset, and extensions to others (like code)!

I'm excited about Andre's work, which analyzes GRPO and identifies that it's biased towards reinforcing solutions that are already highly-probable. We found two easy-to-implement solutions. These improve pass@N, and produced a strong theorem proving model!

Happy to announce the first workshop on Pragmatic Reasoning in Language Models — PragLM @ COLM 2025! 🧠🎉 How do LLMs engage in pragmatic reasoning, and what core pragmatic capacities remain beyond their reach? 🌐 sites.google.com/berkeley.edu/p… 📅 Submit by June 23rd

Sharing some personal updates 🥳: - I've completed my PhD at @unccs! 🎓 - Starting Fall 2026, I'll be joining the Computer Science dept. at Johns Hopkins University (@JHUCompSci) as an Assistant Professor 💙 - Currently exploring options + finalizing the plan for my gap year (Aug…

🆕paper: LLMs Get Lost in Multi-Turn Conversation In real life, people don’t speak in perfect prompts. So we simulate multi-turn conversations — less lab-like, more like real use. We find that LLMs get lost in conversation. 👀What does that mean? 🧵1/N 📄arxiv.org/abs/2505.06120

Some personal news: I'll join @UMassAmherst CS as an assistant professor in fall 2026. Until then, I'll postdoc at @Meta nyc. Reasoning will continue to be my main interest, with a focus on data-centric approaches🤩 If you're also interested, apply to me (phds & a postdoc)!