CORVUS：通过底层同步实现大语言模型编码代理的上下文优化与缩减
CORVUS: Context Optimization and Reduction Via Underlying Synchronization for LLM Coding Agents
浏览论文内容
中文总结 AI 辅助
研究针对大语言模型编码代理传统轨迹架构问题，提出CORVUS架构解耦文件读取与观察，通过维护同步注册表注入当前内容，经实验评估，该架构能减少输入令牌、缩短提示并减少推理周期，保持通过率。
中文摘要 AI 辅助
大语言模型编码代理通过构建积累推理、工具调用和结果的轨迹来进行多步决策。传统的仅追加轨迹架构将文件读取操作与其观察紧密耦合，随着文件变化，快照会过时，导致推理错误和冗余重读文件。为此，我们提出CORVUS，一种新颖的轨迹架构，通过维护相关文件的同步注册表并在每个推理周期仅注入当前内容，将文件读取操作与观察解耦。这使得轨迹更轻量，与实际代码库状态同步，消除冗余文件副本和过时快照。我们在四个大语言模型上对CORVUS进行评估，在保持可比通过率的同时，每个任务的平均输入令牌减少9 - 50%，最终提示缩短15 - 32%，推理周期减少多达37%。
英文摘要
LLM coding agents operate by constructing trajectories that accumulate reasoning, tool calls, and results to enable multi-step decision-making. However, the conventional append-only trajectory architecture found in practice tightly couples file-read actions with their observations, capturing snapshots that become permanently fixed in the chronological history. As files change through agent edits or concurrent human modifications, these snapshots become stale, causing reasoning errors and causing agents to redundantly re-read files, with each re-read appending yet another copy to the trajectory. To mitigate this, we propose CORVUS, a novel trajectory architecture that decouples file-read actions from their observations by maintaining a synchronized registry of relevant files and injecting only their current contents at each reasoning cycle. This structural change produces significantly lighter-weight trajectories that remain synchronized with the actual codebase state by construction, eliminating redundant file copies and stale snapshots that bloat conventional trajectories. We evaluated CORVUS on SWE- POLYBENCH_VERIFIED and SWE-BENCH PRO across four LLMs, achieving 9-50% reduction in average input tokens per task, 15-32% shorter final prompts, and up to 37% fewer reasoning cycles while maintaining comparable pass rates.
