Yinglun Zhu

@yinglun122

post-training @axiommathai, prof @UCRiverside. scaling rl and agents.

yinglunz.com

Joined December 2022

451 Following

618 Followers

Replies Reposts Media

Pinned
Yinglun Zhu
@yinglun122
Jun 18
Excited to share a new preprint on agentic RL. We train LLM agents not only to act, but also to reflect on environment feedback, e.g., execution results or error messages, and assess whether they have completed the task. RefGRPO improves both reflection calibration and task
6
Yinglun Zhu
@yinglun122
Nov 4
time to seriously consider importing stacks alongside mathlib
Axiom
@axiommathai
Nov 4
Most think vibecoding at scale is slop. Here’s a counterexample. Today we release a 16M-line formalization of the entire Stacks Project, critical infra underlying modern math, with optimized code quality and its highly interconnected structure preserved. A mathematical city 🌆
Yinglun Zhu
@yinglun122
Oct 27
cfsg
Axiom
@axiommathai
Oct 27
The largest math proof in human history is now computer-verified. Today, Axiom announces a complete Lean auto-formalization of the Classification of Finite Simple Groups, the "periodic table of symmetry." About 15,000 pages, built by over 100 mathematicians across generations.
2
Yinglun Zhu
@yinglun122
Sep 3
\leq 212
Axiom
@axiommathai
Sep 3
1/ ✨ World record today on bounded gaps between primes, one of number theory’s oldest open conjectures. We show that infinitely many pairs of prime numbers are separated by 212 or less.
Yinglun Zhu
@yinglun122
May 20
This is really cool! Extracting useful (and usually free) signal from the environment is definitely the way to go! I’ve been exploring this from a different angle too — more soon :)
Dimitris Papailiopoulos
@DimitrisPapail
May 18
Article
ECHO: Terminal Agents Learn World Models for Free
Co-written with @VaishShrivas We taught CLI agents to predict terminal responses during RL, alongside the usual GRPO loss on actions. The change is tiny: same rollout and forward pass, but stop
1

Yinglun Zhu

Yinglun Zhu’s posts