Function-Aware Fill-in-the-Middle Mid-Training Improves Coding Agent Performance

Jul 15, 2026

A new self-supervised mid-training method called function-aware fill-in-the-middle (FIM) is proposed to enhance coding agents' ability to integrate external tool outputs. Applied to Qwen2.5-Coder-Instruct and Qwen3-8B models, this approach yields improvements of +2.8 to +5.4 points on SWE-Bench benchmarks and helps prevent the loss of general coding and tool-use abilities that can result from agentic post-training.

Why it matters: This work demonstrates a novel training objective that leverages the structural similarity between coding agent workflows and function call sites, leading to measurable gains in agent performance and robustness.

Full story at: arXiv AI/ML ↗