Einsia
@EinsiaAI
Einsia is a NeoLab advancing the frontier of real-world aligned intelligence
6 Following 862 Followers
Predicting a stock's next move?
That's the warm-up act.
The real exam for LLM agents: building signals from raw data, learning from losses, and making money on data it has never seen before.
That's exactly what we built. Today we’re releasing Quant-Arena, a benchmark for end-to-end quantitative research on real A-share market data.
9 frontier models. 3,042 stocks. One sealed year, 2024. Only 4 of the 9 models made money.Quant research is still wide open.
Full breakdown 👇
Project:
Paper:
Arena:
Show more
Coding agents are entering the physical world.
Zero-shot is only the starting point.
What if we gave them practice—and let the next agent inherit what they learned?
EmbodiedEvo: one Playground → reusable Skills & Lessons → unseen layouts. No model-weight updates.
45.08 average score. 38.95% success.
#1# on the RoboDojo leaderboard.
Project:
Paper:
Github：
Show more
We gave 8 SoTA video world models a physics exam.
Top score: 57.76 / 100.
One revealing result: free-fall video passed the consistency screen. Their average composite score was just 26.61/100.
Physics is still undefeated.
Today we introduce World Models' Last Exam in Physics — 40 controlled tasks, 9 physical categories, measured against real physical laws.
Full breakdown ⬇️
Github:
Project:
Paper:
Show more
An AI agent spends hours on a task. Why should all that work disappear when someone else takes over?
Einsia AI’s answer is AgentGit—an open-source platform for collaborating on agent sessions, so work can be saved, handed off, and continued by the next person.
Explore how others solve problems, and share your agent experience with the world.
Try AgentGit 👇
#OpenSource# #AIAgents# #DeveloperTools# #DevTools#
Show more
The ultimate test for coding agents isn't local editing—
it's whole-repo evolution, and right now, the survival rate is 5.4%.
Today we’re releasing SWE Refactor Bench, a benchmark for long-horizon, whole-repository software stack migration.
Coding agents are getting very good at fixing bugs.
But can they refactor an entire system, C → Rust, Maven → Gradle, POSIX → WebAssembly?
We built 20 real migrations across projects, including SQLite, zlib, libsodium, and GraphHopper.
520 runs. Only 28 survived all 3 stages. 13/20 tasks were solved by nobody.
System-scale migration is still wide open.
Full breakdown 👇
GitHub: [
Paper Link: [
Einsia Website: [
Show more
1/
Recursive self-improvement (RSI) depends on agents improving how AI systems are trained
—not just tuning hyperparameters, but improving the training algorithm itself.
We tested this directly with AI4AI-Bench: 10 real research repositories spanning 10 distinct algorithm families.
Full breakdown 👇
GitHub: [
Paper Link: [
Einsia Website:[
📊 The results:
The average score is just 0.166.
Even the best-performing model, Opus 5, reaches only 0.288.
The median exploration cost per task rises from $1.69 to $34.60.
#AI4AI# #RecursiveSelfImprovement# #AIResearch# #AI4AI_Bench#
Show more
