SIA (Self-Improving AI) is a framework that orchestrates a three-agent loop (meta-agent, target agent, feedback/improvement agent) to iteratively improve an AI system's performance on a benchmark task. In production, it runs as a CLI tool (`sia run`) that sets up a virtual environment, loads task files, and executes generations: the meta-agent reads `task.md` and generates `target_agent.py`, the target agent executes the task and logs results, and the feedback agent reviews the execution and rewrites the target agent for the next generation. A FastAPI web dashboard auto-launches to visualize per-generation accuracy, agent code, trajectories, and improvement plans. The architecture is a CLI-driven monolith with a plugin system for agent backends (Claude, OpenHands, PydanticAI), JSON-based provider/profile configuration, and Docker sandboxing for secure target-agent execution. It relies on external LLM APIs (Anthropic, OpenAI, Gemini, Nebius, OpenRouter, Together) and optionally on Modal/SandboxFusion for the RL-based weights mode. The repository also bundles four benchmark tasks (GPQA, lawbench, longcot-chess, spaceship-titanic) with public/private data splits and evaluators, giving it a hybrid character that includes data/research components. However, its primary function is as an application for running and visualizing self-improvement experiments.
This repository is a curated list (awesome list) of AutoResearch use cases, implementations, benchmarks, and forks. It does not contain any source code, data, or executable components. The sole content is a README.md file that organizes links to external projects, each with descriptions and links to optimization traces. The repository serves as a directory for the AutoResearch community, not as a software application or data research pipeline. It is a static documentation resource with no runtime behavior, architecture, or data flows.