Software Engineer @ Scale AI
Joined March 2023
- Tweets436
- Following181
- Followers472
- Likes1.7K
We are making CUA Evals extremely easy to build in AgentEnv Framework. We are doing an early showcase of this with Cua Driver Bench.
With our framework you can build an RL environment that has an arbitrary number of computers, swappable drivers, many agents on a single computer, host websites and proxy through your computers, and a whole lot more.
Data labs ranked by number of papers accepted into Neurips 2026
I asked people which data companies influence research direction at the frontier:
16 votes: Surge (@echen)
13 votes: Proximal (@calvinchen, @MatternJustus)
8 votes: Preference Model (@jennifgcrl, @Ning_Catsnail)
7 votes: Datacurve (@serenaa_ge, @charleyslee)
6 votes each:
- Mechanize (pre-acquisition) (@tamaybes, @EgeErdil2, @MatthewJBar)
- Mercor (@BrendanFoody, @adarsh_exe, @suryamidha)
5 votes: Fleet (@nicoup, @andrewthezhou)
4 votes each:
- AfterQuery (@CarlosGeorgescu, @spencermateega)
- Prime Intellect (@vincentweisser, @johannes_hage)
3 votes: Latch (@AlfredoAndere, @kenbwork, @kylegiff)
2 votes each:
- Abundant (@huyouare, @kehuangsf, @meji_abidoye)
- Artificial Analysis (@_micah_h, @grmcameron)
- Bespoke Labs (@madiator, @AlexGDimakis)
- micro1 (@aliansarinik)
- Terminal-Bench (@Mike_A_Merrill, @alexgshaw)
50 people voted. People couldn't pick a company they work at or founded. Disclosure: on this list, I'm a small investor in Abundant, AfterQuery, Arcanum, DLR, Fleet, Latch, Paper Instruments, Snorkel, and Vmax. I didn't vote.
Continued:
Frontier models of today are trained largely from publicly available data on the internet. Most data in the real world is not available on the internet; this is especially true in economically valuable verticals like law, finance, etc. The RL Environments we build at @scale_AI provide an opportunity to the frontier labs to get access to this extremely valuable data.
Today we're publishing a major RL environments update: 3,300+ tasks across tool use and computer use, already running with customers. Some tasks in our newest RL environments take a human team 3 weeks and 500+ tool calls.
scale.com/rlenvironments
Train on GridSimEnv using @PrimeIntellect 's prime-rl training framework agentenvframework.com/docs/t… in AgentEnv today!
At @ScaleAILabs we created a high fidelity RL Environment of a trading desk in a real Texas battery grid.
GPT-6.1 Sol made $85,771 trading a real Texas battery. The battery's real operator made $20,647.
Edgar Arakelyan retweeted
Check out our recent blog post detailing this RL environment!
agentenvframework.com/blog/c…
We support SkyRL in AgentEnv agentenvframework.com/docs/t… -- train your model on GridSimEnv using SkyRL today!
At @ScaleAILabs we created a high fidelity RL Environment of a trading desk in a real Texas battery grid.
GPT-6.1 Sol made $85,771 trading a real Texas battery. The battery's real operator made $20,647.
Edgar Arakelyan retweeted
OpenHands is now supported in @scale_AI's open-source AgentEnv framework.
Run and evaluate agents against the same tasks and environments, without locking into one agent or infrastructure provider.
More interoperability, more choice. That’s the future we’re building toward.
Details 👇
agentenvframework.com/docs/a…
At @ScaleAILabs we created a high fidelity RL Environment of a trading desk in a real Texas battery grid.
GPT-6.1 Sol made $85,771 trading a real Texas battery. The battery's real operator made $20,647.
Hugging Face: huggingface.co/spaces/earake…
Built using AgentEnvFramework.com
Edgar Arakelyan retweeted
Daytona sandboxes are now built into AgentEnv, @scale_AI's open-source framework for RL environments.
Every environment and agent gets its own sandbox with Docker inside, so compose stacks, agent containers and image builds run unchanged.
Setup below 👇
Boat sandboxes x TRL training agentenvframework.com/docs/t…
Edgar Arakelyan retweeted
How far can a better harness take a lightweight model?
Using Agent Env Framework from @ScaleAILabs, we let Haiku's harness recursively improve across 3 games and put it head to head against Opus.
See more at: agentenvframework.com/blog/t…
Edgar Arakelyan retweeted
RL works. The problem is leaky environments.
If a rollout can see the last one's files or look the answer up online, the model learns to cheat. AgentEnv from @ScaleAILabs now gives each environment and agent its own boxd VM. It boots in 2 seconds and is deleted afterwards.
Edgar Arakelyan retweeted
@smolmachines x AgentEnv from scale.
You can leverage smol to power AgentEnv workloads now to run it on any platform, locally or remote.
open source loves open source! Thanks @earakely for partnering up on this!
agentenvframework.com/docs/s…
github.com/smol-machines/smo…
Edgar Arakelyan retweeted
You can now run AgentEnv evals from @ScaleAILabs on Vercel Sandbox.
Give your agent a task, run it in a sandbox, and check how it performed.
vercel.com/changelog/run-sca…
We are doing this in collaboration with @hark_labs & @trycua.
Check out AgentEnv here agentenvframework.com/
