SIA (Self-Improving AI)

Official implementation of SIA: Self Improving AI with Harness & Weight Updates (Hebbar et al., 2026) — a self-improving loop where a language-model agent updates both the harness and the weights of a task-specific agent. The paper reports a 56.6% gain on LawBench, 91.9% runtime reduction on GPU kernels, and 502% improvement on single-cell RNA denoising over baseline.

SIA is a Self Improving AI framework to autonomously improve the performance of any AI system (Model / Agent) on a benchmark task.

Just want to try it? Skip to Run SIA locally.

Introduction Videos

• SIA setup
• SIA Runs Visualizer

Architecture

Control flow between Meta, Target, and Feedback agents over successive generations.

SIA operates by coordinating three main types of AI agents that work together to continuously improve task performance:

Glossary

1. Meta-Agent: Reads the task description and generates an initial Target Agent tailored to the task.
2. Target / Task Specific Agent: Attempts to complete the task and records its actions and results.
3. Feedback/Improvement Agent: Reviews the Target Agent's performance logs, identifies improvements, and updates the Target Agent accordingly.

This iterative process allows the system to autonomously refine and enhance its ability to solve scientific tasks.

Benchmark Results

OpenAI MLE-Bench Hard: a gauntlet of real Kaggle ML competitions where agents must write, run, and iterate full ML pipelines. SIA ranks #1 across all generations tested.

LawBench: predict the criminal charge from Chinese court case descriptions across 191 charge categories. SIA-W+H reaches 70.1% Top-1 accuracy, beating the prior SOTA of 45%.

AlphaFold-3 TriMul Triton Kernel: implement and optimize the Triangle Multiplicative Update as a Triton kernel, preserving correctness while hitting H100 latency targets. SIA-W+H achieves 14x speedup over baseline.

scRNA-seq Denoising: impute missing gene expression values in single-cell RNA sequencing data. SIA-W+H scores 0.289 MSE_norm, surpassing the prior SOTA of 0.240.

Run SIA locally with built-in tasks

SIA ships with four built-in tasks: gpqa, lawbench, longcot-chess, spaceship-titanic.

Install

Pick the agent impl that matches the LLMs you want to run.

Claude agent impl (Claude Agent SDK, Claude models only):

python3 -m venv .venv && source .venv/bin/activate
pip install 'sia-agent[claude]'
export ANTHROPIC_API_KEY="..."

OpenHands agent impl (multi-provider — Gemini, OpenAI, Anthropic, etc.):

python3 -m venv .venv && s