LCM让大模型在长文本任务中无损记忆，表现超越顶级代码助手。
LCM: Lossless Context Management
- 用两级确定性机制实现无损上下文压缩与任务拆分
- 在32K至100万token范围内均优于Claude Code
- 适合需要精准回溯历史的长流程推理场景
我们提出无损上下文管理（LCM），一种用于大模型记忆的确定性架构，在长上下文任务中表现优于Claude Code。使用Opus 4.6基准测试时，增强LCM的编码代理Volt在OOLONG长上下文评估中取得更高分数，涵盖32K至100万token的所有上下文长度。LCM可视为对递归语言模型（RLMs）开创性范式的验证与拓展。结果表明，递归上下文操作不仅优于传统大模型，还可超越具备原生文件系统访问权限的前沿代码代理。与RLM不同，LCM将符号递归分解为两种确定性、由引擎管理的机制：递归上下文压缩，通过层次化摘要有向无环图（DAG）自动压缩旧消息，同时保留所有原始内容的无损指针；递归任务拆分，使用引擎管理的并行原语（如LLM-Map）替代模型自写循环。这一设计类似编程语言从GOTO转向结构化控制流的演进，以牺牲最大灵活性为代价，换取终止保证、短任务零成本连续性及全部先前状态的无损可检索性。
原文摘要 · Abstract (English)
We introduce Lossless Context Management (LCM), a deterministic architecture for LLM memory that outperforms Claude Code on long-context tasks. When benchmarked using Opus 4.6, our LCM-augmented coding agent, Volt, achieves higher scores than Claude Code on the OOLONG long-context eval, including at every context length between 32K and 1M tokens. LCM may be considered both a vindication and extension of the recursive paradigm pioneered by Recursive Language Models (RLMs). Our results demonstrate that recursive context manipulation can outperform not just conventional LLMs, but frontier coding agents with native file-system access. LCM departs from RLM by decomposing symbolic recursion into two deterministic, engine-managed mechanisms: recursive context compression, in which a hierarchical summary DAG automatically compacts older messages while retaining lossless pointers to every original; and recursive task partitioning, in which engine-managed parallel primitives like LLM-Map replace model-written loops. This trade-off, analogous to the move from GOTO to structured control flow in program-ming language design, sacrifices maximal flexibility for termination guarantees, zero-cost continuity on short tasks, and lossless retrievability of all prior state.
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。