Unity Insight：面向Unity项目中LLM编码代理的生产级代码-资产索引

中文摘要 AI 辅助

LLM编码代理日益在游戏引擎仓库内运行，其中应用程序逻辑与序列化资产密不可分：单个游戏玩法变更可能跨越由Unity GUID连接的C#脚本、预制件、场景和ScriptableObject。代理当前携带的检索工具——shell工具和纯代码索引——无法回答基本的跨文件问题，因为这些关系存在于.meta文件和YAML资产中而非代码中。我们提出Unity Insight，据我们所知，这是首个面向Unity项目的持久化、面向LLM、代理集成的跨文件代码-资产索引，自2026-07-28公开上线以来，已随Tuanjie Engine的代理CLI——Tuanjie Codely——在生产环境中发布。在一项配对实验中——针对两个Unity游戏的28个特定项目问题，使用相同模型和测试框架，每个问题每臂运行一次——索引支持的代理比通用探索代理少花费53%的令牌和52%的墙钟时间（精确配对符号检验，p<0.004），仅使用其类型化索引查询工具。

英文摘要

LLM coding agents increasingly operate inside game-engine repositories, where application logic is inseparable from serialized assets: a single gameplay change may span C\# scripts, prefabs, scenes, and ScriptableObjects wired together by Unity GUIDs. The retrieval tools agents carry today---shell utilities and code-only indexes---cannot answer basic cross-file questions, because these relationships live in \texttt{.meta} files and YAML assets rather than in code. We present Unity Insight, to our knowledge the first persistent, LLM-facing, agent-integrated cross-file code--asset index for Unity projects, shipping in production with Tuanjie Codely, the agent CLI of Tuanjie Engine, since its public launch on 2026-07-28. In a paired experiment---28 project-specific questions on two Unity games, same model and harness, one run per arm per question---the index-backed agent spent 53\% fewer tokens and 52\% less wall-clock time than a general-purpose exploration agent (exact paired sign tests, $p{<}0.004$), using only its typed index-query tools.

发表机构

• Tuanjie Engine, Unity China（团结引擎，Unity中国）

机构由 AI 辅助整理，请以论文原文为准。