Hosted by New York Machine Learning Research Guild (NYMLR)
AI/ML Lecture & Networking @ CUNY, Amazon JFK27
A monthly ML research colloquium by the New York Machine Learning Research Guild — this session in collaboration with our partner, CUNY Tech Prep.
Reasoning in Language Models
Zayne Sprague · PhD Researcher, Courant Institute of Mathematical Sciences, NYU & Google
Topic: From Chain of Thought to Agent Swarms: A Brief Story on Reasoning in LLMs
Giving language models more time to think has produced substantial gains, but in targeted domains, and the benefits appear to remain uneven across tasks. This talk explores how models can use additional computation at inference time effectively, reviewing the progression from prompt based methods to multi-agent systems. We will begin with chain-of-thought prompting, asking a model to think before giving a final answer, presenting our work showing that chain-of-thought prompting has its strongest benefits concentrated in mathematics and symbolic reasoning. These domains also share a practical advantage: answers can often be checked automatically, providing feedback that can be used to train models through reinforcement learning. This leads us to SkillFactory, where we use a model's own successful and unsuccessful attempts to construct training examples that demonstrate checking answers and retrying. Combining supervised finetuning on these examples with reinforcement learning helps models develop these behaviors and generalize to harder problems. Finally, we will discuss recent work on agent swarms, exploring how reasoning can scale in parallel and what role verification can play in making that additional computation useful.
This session is a close-quarters look at that work, with plenty of room to push back and dig in.
About Zayne
Zayne Sprague is an NLP PhD student at NYU's Courant Institute, advised by Greg Durrett in the TAUR Lab. His research asks how to evaluate reasoning in language models and how to instill it.
MuSR (ICLR 2024, spotlight) — a benchmark of multistep soft-reasoning problems
"To CoT or not to CoT?" (ICLR 2025) — showed chain-of-thought helps mainly on math and symbolic tasks
SkillFactory (ICLR 2026) — self-distillation to teach models reusable cognitive behaviors
OpenThoughts (ICLR 2026, oral) — open data recipes for reasoning models
Before the PhD, Zayne earned a BA and MSc in computer science at UT Austin and spent seven years in industry, most recently as a senior software engineer at CoPilot. He is now at Google.
Who this is for
NY-MLR colloquia are small by design. The room is capped, and we keep it that way so the discussion stays substantive and everyone in it can contribute.
We'd love to see you if you're:
A practitioner working seriously on ML, in industry or in a lab
A researcher or graduate student in ML, NLP, or an adjacent field
A highly motivated student or self-directed learner of any age or background, with real depth of interest
Sincere interest is enough to belong — that's one of our core principles. What we ask is that you come ready to engage. More on the Guild and our ethos at nymlr.com.
Schedule
5:00 – 5:30 PM — Doors open, arrivals, mingling
5:30 – 6:30 PM — Speaker Lecture
6:30 – 7:00 PM — Moderated Q&A
7:00 – 8:00 PM — After hours, mingling, wind-down
8:00 PM — Lights out
Venue: Amazon JFK27 ("Hank") · 12 W 39th St, New York, NY 10018
A note on no-shows
Seats are strictly limited by room capacity, and every in-person RSVP takes one from someone else who wanted it.
If you register to attend in person and your plans change, please amend your registration or cancel on Luma. It takes ten seconds and frees the seat.
Registering in person and not showing up without updating your RSVP will forfeit your access to future NY-MLR events. Please mark your attendance mode accurately.
Hosted by New York Machine Learning Research Guild (NYMLR)