为什么Git是智能开发生命周期的记忆解决方案
Why Git Is the Memory Solution for the Agentic Development Lifecycle
浏览论文内容
中文总结 AI 辅助
研究智能开发生命周期中代码变更推理过程的记忆问题，提出将记忆与Git绑定的方法，通过解决种子供应和答案组装问题，实现低令牌数回答且结果可复制。
中文摘要 AI 辅助
编码智能体现在在团队代码产出中占比越来越大，但每次代码变更背后的推理过程都被困在会话结束后就消失的辅助记录中。智能开发生命周期（ADLC）的记忆通常被视为一个检索问题并构建相应机制。本文认为记忆应与Git绑定，内置于仓库的版本控制中。通过预注册的流程解决了种子供应问题，在答案组装方面，单步检索效果不佳，而本文的路由器通过向基于Git的结构图分派广度、向置信门控情节进行定向查找以及向决策合成提供原理，使得系统能够以较低的令牌数回答问题，且结果可复制。
英文摘要
Coding agents now produce a growing share of a team's code, while the reasoning behind each change -- the alternatives weighed, the constraints discovered, the approaches rejected -- is trapped in assistant transcripts that vanish with the session. Memory for this setting, the agentic development lifecycle (ADLC), is usually posed as one retrieval problem and built as machinery: tiered stores, memory graphs, compiled wikis, model-judged admission. We argue memory should instead be git-bound -- built into the repository's version control, inheriting the guarantees the machinery struggles to construct: ground truth from commits, freshness from rebuild, verification from the merge, containment from review. On this ledger we solve two problems separately, then combine them. Seed supply is closed as an eight-corpus retrieval study under a pre-registered ship discipline: five imported ranking mechanisms rejected, two kept, and a best configuration of ~0.31 pooled MRR -- ~60x the raw-transcript grep floor, ~15x an honest parsed-turn floor. Answer assembly is where ranking stops helping: single-shot retrieval scores only 0.07-0.20 answer-sufficiency on real developer questions, and ungated episode injection measurably degrades good answers. A router dispatches breadth to a git-anchored structural map, pointed lookups to confidence-gated episodes, and rationale to decision synthesis, which reconstructs why-arcs no single session contains (0.83 sufficiency on a young ~50k-LOC production system). Routed, the system answers at 382-980 tokens per question -- three orders of magnitude below the recorded history. Because ground truth is mined from commit-session links rather than annotated, every result is replicable on any user's own history at zero labeling cost. The remaining constraint is capture. Code, benchmark, and paper source: github.com/rekal-dev/rekal-cli.
发表机构
- MIT（麻省理工学院）
机构由 AI 辅助整理，请以论文原文为准。
