声明平面：并行编码智能体选择性并发的可靠性提升与局限——确定性预写准入的30对、3种子验证性研究
Claim Plane: Reliability Gains and the Limits of Selective Concurrency for Parallel Coding Agents: A 30-Pair, Three-Seed Confirmatory Study of Deterministic Pre-Write Admission
浏览论文内容
中文总结 AI 辅助
该研究提出声明平面机制，通过30对、3种子的验证性实验，发现其可提升并行编码智能体的可靠性，但静态准入会过度串行化执行，动态准入则存在范围覆盖问题，未实现有效并行加速。
中文摘要 AI 辅助
并行编码智能体可生成局部有效的变更，但在组合时会失败。声明平面（Claim Plane）通过对版本化变更意图采用确定性预写准入来解决该失败模式。本文报告一项验证性研究，涉及30个CooperBench冻结功能对，其中15个为冲突标签、15个为无冲突标签，搭配3个编码种子、4个协调分支，共完成360次执行。DeepSeek V4 Pro生成60个功能级规划器声明后冻结，所有分支和编码种子均使用该冻结声明，由DeepSeek V4 Flash执行编码工作。静态声明平面将对的通过率从无约束并行执行下的23.3%提升至50.0%，配对任务集群差异为+26.7个百分点（95%自助抽样置信区间9.6至60.0），集成成功率从65.6%提升至96.7%；在冲突标签对中，对的通过率从6.7%升至60.0%。但静态准入将96.7%的执行序列化为串行，包括93.3%的无冲突案例，因此其可靠性提升主要通过向串行执行靠拢实现。动态准入更具选择性，将66.7%的冲突案例和13.3%的无冲突案例序列化为串行，但90次执行中有46次因未声明范围而闭环失败，导致对的通过率降至22.2%；这46次失败中的45次针对已存在于冻结声明中的文件，表明问题在于区域覆盖不足和修正处理不当，而非完全未知的文件。结果支持预写准入作为一种可靠性机制，但未实现有用的 wall-clock 并行加速：提供商调用为物理串行，保守策略在很大程度上将工作序列化为串行。完整的研究工件、哈希值和聚类自助分析已公开发布以支持复现。
英文摘要
Parallel coding agents can produce locally valid changes that fail when combined. Claim Plane addresses this failure mode as deterministic pre-write admission over versioned change intents. This paper reports a confirmatory study on 30 frozen CooperBench feature pairs, balanced between 15 conflict and 15 clean labels, with three coder seeds, four coordination arms, and 360 completed executions. DeepSeek V4 Pro generated 60 feature-level planner declarations once; the declarations were frozen across all arms and coder seeds, while DeepSeek V4 Flash performed the coding work. Static Claim Plane raised pair pass from 23.3% under unconstrained parallel execution to 50.0%, a paired task-cluster difference of +26.7 percentage points (95% bootstrap CI 9.6 to 60.0), and raised integration success from 65.6% to 96.7%. On conflict-labeled pairs, pair pass rose from 6.7% to 60.0%. However, static admission serialized 96.7% of executions, including 93.3% of clean cases, and therefore recovered reliability largely by collapsing toward serial execution. Dynamic admission was more selective, serializing 66.7% of conflict cases and 13.3% of clean cases, but 46 of 90 executions failed closed on undeclared scope, reducing pair pass to 22.2%. Forty-five of those 46 blocks targeted files already present in the frozen declarations, indicating region undercoverage and insufficient amendment handling rather than wholly unknown files. The results support pre-write admission as a reliability mechanism, but they do not establish useful wall-clock parallel speedup: provider calls were physically sequential, and the conservative policy largely serialized the workload. The complete study artifacts, hashes, and clustered bootstrap analysis are publicly released for reproduction.
