This repository demonstrates an experimental autonomous coding agent that can iteratively improve code, generate new tests (including edge cases), evaluate itself in a sandbox, and self-train via LoRA using its own interaction data. write → test → reflect → improve → generate data → fine-tune → repeat It is designed as a research prototype for studying recursive self-improvement, agentic programming, and self-generated supervision. A local sandbox directory containing: — Initial example code (example.py) — Initial tests (testexample.py`) — All patches and generated tests The agent maintains memory across iterations: — Success history — Reward signals — Files modified — Plateau counter (to detect stagnation) Each decision (patch or test generation) allows multiple retries if output is malformed or incomplete. This increases robustness without human intervention. Improvement is estimated by: — Increase in passing test count — Comparison against prior iterations If no improvement is detected for several iterations, training stops automatically. — This is a research prototype, not a production system. — Improvement signals are approximate, not formal verification. — Generated code and…
Модальности:
Генерация текста
Области применения:
Диалог / чат
Задача: Генерация текста
Автор: EpistemeAI
Теги: gpt_oss, text-generation-inference, unsloth, conversational, en, endpoints_compatible
Лайков: 3 | Загрузок: 20
Описание основано на материалах HuggingFace. Перевод выполнен автоматически.
