Vmax C Verified
RL environment company · ML
- Domains
- ML Coding Long-Horizon
- On X
- @VmaxAI ↗
- Tier
- C why
- Snapshot
What Vmax does
Vmax is an RL research lab building Campaign, self-play task generation infrastructure that turns a customer's proprietary data and evals into new RL environments for training agents.
- Sells
- RL environments
- Leads with
- Several domains (a generalist)
- Based in
- San Francisco, USA
- Team
- 1-10
- Website
- vmax.ai ↗
What Vmax sells
Read from Vmax's own website, checked October 13, 2026: the line that puts it in each category.
RL environments
“Campaign is our self-play task generation infrastructure. It transforms your proprietary data and evals into new sets of environments”
vmax.ai/ ↗
Domains Vmax covers
“doubling frontier-task generation across math, code, and SWE.”
vmax.ai/ ↗“doubling frontier-task generation across math, code, and SWE.”
vmax.ai/ ↗“a procedural generator of capture-the-flag environments for training and evaluating Unix competence in language-model shell agents.”
vmax.ai/ ↗
Benchmarks Vmax built or runs
unix-ctf built it
“We introduce unix-ctf, a procedural generator of capture-the-flag environments for training and evaluating Unix competence in language-model shell agents.”
vmax.ai/research ↗
Vmax competitors and alternatives
The companies that sell the most of the same things in the same domains, and what they share with Vmax.
- ReasonCore Also sells RL environments · also in math, coding and security
- Collinear Also sells RL environments · also in coding and security
- Preference Model Also sells RL environments · also in coding and math
- Prime Intellect Also sells RL environments · also in coding and math
- Surge AI Also sells RL environments · also in coding and math
Tier C
Early: a small team.
How much stands behind a tier: usage, who backs it, a confirmed line from its own site or paper, and a clear read on X. High with three of the four, medium with two, low otherwise.
- team 1-10
- investors: Race Capital, South Park Commons
- in curated RL directories (5 pts)
On X · unclear, low buzz, from 9 posts about Vmax in the last month
The posts are mostly unrelated replies to @wwwjim and say nothing substantive about Vmax's Campaign product, its customers or its results.
How we got to tier C
- Adoption: team 1-10; investors: Race Capital, South Park Commons. Tier C.
- On X: unclear, low buzz. “The posts are mostly unrelated replies to @wwwjim and say nothing substantive about Vmax's Campaign product, its customers or its results.” No move.
- In curated RL directories: 5 points, a floor of C.
- Confirmed: a line from its own site or paper places it.
A clear view on X moves a tier one step up or down; most entries don't move. How tiers work.
Training methods
Methods Vmax uses, offers or builds for, with public evidence: its own website says so, or two independent sites do.
- RLVR Reinforcement Learning with Verifiable Rewards On its own website
“DescriptionWe introduce PopuLoRA, a population-based asymmetric self-play framework for reinforcement learning with verifiable rewards (RLVR) post-training of LLMs.”
vmax.ai“The task format is also narrower than the full measurable distribution of Unix work. Capture-the-flag recovery is a clean way to procedurally generate Unix tasks with verifiable reward, but real Unix work includes administration, debugging, monitoring, repair, performance investigation, deployment, and multi-step maintenance tasks that do not reduce naturally to "find the hidden token."”
vmax.ai - GRPO Group Relative Policy Optimization On its own website
“The full unix-ctf loop: harvest a validated library, instantiate multi-flag containers, train with GRPO, then evaluate on held-out and external benchmarks.”
vmax.ai - SFT Supervised Fine-Tuning On its own website
“On the multi-family holdout, the base Qwen3-8B model solves 11.6% of tasks. GRPO from the base initialization reaches 27.6%. GRPO from the SFT-formatted initialization reaches 43.6%.”
vmax.ai
Where Vmax sits
Its domain on the map, live. Hover a logo for its name; click to open it. Open it on the full map
Latest from Vmax on X
@VmaxAI ↗Next: browse all environments. Entry from the RL Research daily scrape of public sources, 2026-11-05 snapshot.