让AI学会“填函数”：编程智能体能力提升新路径
AI编程助手在写代码时，经常需要调用外部工具并等待返回结果——这就像写一个函数，先传参，再等返回值，然后继续。研究者发现，普通代码里到处都是这种结构，于是设计了一个“函数感知填空”训练：让AI在大量代码中，专门练习把被挖掉的函数体补全，而且只挑那些有复杂逻辑、能推断出来的函数。这样训练后，7B和14B的模型在SWE-Bench编程测试上提升了3-5个百分点，而且不会像其他训练那样让AI忘记普通编程能力。虽然训练数据只有Python，但学到的“函数调用”直觉还能迁移到其他工具使用场景。这不是你明天就能用的功能，但它指向一个方向：让AI更自然地理解“调用-等待-继续”的循环，而不是硬学规则。
📄 原文摘要(英文)
Coding agents must integrate external tool returns into ongoing reasoning - a capability that standard left-to-right pretraining on code exposes only in its forward direction. We observe that the action-observation-continuation loop of a coding agent is structurally isomorphic to a function call site, where a caller binds arguments, a callee returns a value computed elsewhere, and downstream code consumes that value. This conditioning structure exists at internet scale in ordinary code. We exploit it through function-aware fill-in-the-middle (FIM) mid-training: a self-supervised objective that masks functions selected via program dependency graph analysis and a complexity-inferability double criterion. We mid-train Qwen2.5-Coder-Instruct (7B/14B) and Qwen3-8B on a 2.6B-token decontaminated corpus drawn from 968 GitHub repositories, then apply existing agentic post-training pipelines. Mid-training improves SWE-Bench-Verified by +2.8/+3.0 at 7B/14B and by +3.2 on Qwen3-8B; SWE-Bench-Lite gains are +3.7/+4.0/+5.4 on the same models. The improvement holds across two post-training pipelines (R2E-Gym, SWE-Smith) and on a non-Qwen2.5 base (Qwen3-8B with SWE-Lego). Beyond in-domain gains, mid-training also mitigates the capability erosion that agentic post-training otherwise inflicts on non-agent coding (e.g., LiveCodeBench) and non-coding tool-use benchmarks (tau-bench, BFCL): although the mid-training corpus contains Python code only, the function-call inductive bias survives post-training and yields consistent gains.