Exciting new research led by @lorenz_wlf to accelerate RL task generation using mech interp methods in collaboration with @GoodfireAI

Exciting work on unix environment generation led by @radbadgeoffbrad!

Our designer @wwwjim has made something really special for this blog post.

Vmax is building an open-ended learning system that generates and optimizes itself on tasks that it creates, avoiding human bias that may corrupt optimal learning curricula. In PopuLoRA, we instantiate this as co-evolving populations of LLMs performing asymmetric self-play.

We are so excited to have @tensorfi joining @VmaxAI! Maxwill joins us from @Meta, where he was working RL and LLMs for recommendation. Previously, he has also worked @Tesla on the autopilot team and also in Quant finance at Kronos research. He also holds an MS in CS from Georgia Tech. Maxwill simultaneously understands pre-LLM RL fundamentals but also how to scale pipelines for RL training for modern recommendation systems. Maxwill is already levelling up our pipeline for automated environment design, pushing multiple PRs as soon as he joined. Really excited about the velocity of his contributions and excited to share more soon.

Welcome Geoffrey!

PR review is one of the fast growing categories in AI for SWE, now you can benchmark agents on *real* PRs

So excited to have @lorenz_wlf join @VmaxAI as a research fellow this spring! At NeurIPS last year, we caught up with Lorenz, realised how aligned he is with our research vision and invited him to join us shortly after. Lorenz comes from the @FAICDT1 programme at UCL (where I did my PhD also) and is supervised by @mircomusolesi. Previously he worked on differential privacy and personalized recommender systems at Apple and did his undergrad in mathematics and statistics at Imperial College London. Lorenz’s research focuses on RL, RLHF and modular continually learning RL agents. He has contributed to papers in ICLR, TMLR and AI STATS. So excited for him to join us and accelerate our efforts on unsupervised environment design. You can read Lorenz's research in the replies. Much more to come.

22/ Reinforcement learning, but make it automated. @MavorParker & @matthewjsargent showed us how they’re generating long-horizon environments at @VmaxAI. vmax.ai/

welcome Roger!

As an initial step in this direction, we have built on top of methods like SWE-smith and BugPilot, adding to the list of repo profiles built by the swe-bench community

This is a preview of many more tasks to come for Ares!

RL progress is bottlenecked by infra for training and evaluation. @VmaxAI is excited to be partnering @withmartian, generating environments for the Agentic Research and Evaluation (ARES) framework

ARES uses the Harbor task format ( @alexgshaw ). It comes with SWE-Bench Verified, TerminalBench2, SWESmith, and everything else in the Harbor ecosystem. We're also releasing 1k new JavaScript tasks with @VmaxAI ( @MavorParker @matthewjsargent ) to help the ecosystem grow.

Really excited for this 👀 reach out to josh!

Which pre-LLM methods matter most in the LLM era? We hosted an off the record event with @danijarh (world models for robotics), @ashvinair (RL @cursor_ai) and @nikishin_evg (reasoning @OpenAI) to share their takes @southpkcommons.

The RL event @VmaxAI and @southpkcommons are organizing has a stacked panel of amazing researchers, whose work I have admired since my PhD, when RL was not as much of a hot topic as it is today. Here's a thread on our panelists 👇

At @VmaxAI, we take the bitter lesson seriously. Come get your Vmax chocolate at the scaling environments workshop @SEAWorkshop

Very excited to sponsor the scaling environments workshop

At Vmax, we are automating the construction of RL environments and the post-training of agents. We are hiring members of technical staff and research fellows. Come join us in SF! (link to apply in comments).