三种大模型智能体框架虽理念不同，最终走向相似架构。
The Empire, Long Divided, Must Unite: Architectural Convergence in Three LLM Agent Harnesses
- 对比三种不同哲学的智能体框架设计思路。
- 发现三者均收敛到包含五个核心组件的统一架构。
- 揭示架构演进中存在复用与共享，但缺乏外部可验证性。
智能体框架是将语言模型转化为自主代理的关键：它构建模型上下文、管理工具、运行循环并持久化长周期状态。这一层正成为限制智能体行为的核心因素。本文对三个开源编码代理框架（LangChain deepagents、Earendil pi、DeepSeek dsh）进行源码级多案例研究，它们分别代表‘全功能集成’、‘极致极简’和‘插件化一切’的不同理念。分析其固定版本及提交历史后发现，两个成熟框架虽路径相反（deepagents削减代码，pi积累基础设施），却共同趋向一种包含五个共现元素的中间架构：标准化的执行循环、不可篡改的会话记录、将模型特性作为数据处理、渐进式上下文披露、显式的扩展接口。第三个框架在事后检查中也具备全部五项，甚至直接复用另一框架的实现。因此并非独立发明，而是由并行发现、知识传播和实际复用驱动的收敛。最后，一个关键维度——外部可验证性（无需信任运行时即可审计的防篡改记录）——在所有框架中均未出现，我们将其视为当前设计的预测性缺口，未来在需溯源敏感领域的框架中将成为分水岭。
原文摘要 · Abstract (English)
An agent harness is what turns a language model into an autonomous agent: the surrounding code that builds the model's context, mediates its tools, runs the loop, and persists state across a long-horizon run. This layer, not the model it wraps, is increasingly the binding constraint on agent behaviour. We present a source-level, multi-case study of three open coding-agent harnesses built from deliberately opposing philosophies: LangChain's deepagents (batteries-included), Earendil's pi (radical minimalism), and DeepSeek's dsh (everything-is-a-plugin). Reading each at a pinned commit and following its commit history, we find that the two mature harnesses have travelled in opposite directions (deepagents subtracting authored scaffolding, pi accreting durable infrastructure), yet converged toward one architectural middle form of five recurring elements: a commoditised loop, an append-only replayable session record, model quirks kept as data, progressive disclosure of context, and explicit extension seams. A third harness, read afterward as a held-out check, exhibits all five, and in one seam reuses another's implementation outright. We therefore do not claim independent invention, and decompose the convergence into parallel discovery, diffusion, and literal reuse. Finally, one load-bearing dimension shows no convergence, and indeed no presence: external verifiability, a tamper-evident record an outside party can check without trusting the runtime. We read this absence not as an oversight but as a predictive gap, the next axis on which harnesses for provenance-sensitive domains will differ.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。