NobleBlocks

Research indexPreprint

A Self-Improving Coding Agent

Robeyns, Szummer, Aitchison

arXiv (Cornell University)21 Apr 2025Open access

NobleIDark:/48914/w1/20260525/D1339CD7DOI10.48550/arxiv.2504.15228

Free to read at the publisher

You can read the abstract here, or the full text at the publisher.

Read at the publisher

Abstract

Recent advancements in Large Language Models (LLMs) have spurred interest in deploying LLM agents to undertake tasks in the world. LLMs are often deployed in agent systems: code that orchestrates LLM calls and provides them with tools. We demonstrate that an agent system, equipped with basic coding tools, can autonomously edit itself, and thereby improve its performance on benchmark tasks. We find performance gains from 17% to 53% on a random subset of SWE Bench Verified, with additional performance gains on LiveCodeBench, as well as synthetically generated agent benchmarks. Our work represents an advancement in the automated and open-ended design of agentic systems, and demonstrates a data-efficient, non gradient-based learning mechanism driven by LLM reflection and code updates.

Discussion

Topics

More

Suggest a correction or report