用结构化记忆替代自由对话，让大模型更准地处理长文本推理。
COSMIR: Chain Orchestrated Structured Memory for Iterative Reasoning over Long Context
- 用结构化内存替代自由消息传递，提升信息保留与一致性。
- 在HEL MET数据集上，比CoA基线准确率更高，信息丢失减少。
- 适合需要高可信度、可审计的长文本问答任务。
长文本推理对大语言模型仍是挑战。现有方法或通过检索压缩输入（可能遗漏证据），或扩大上下文窗口（降低选择性），或分阶段由多个智能体处理。在分阶段流程（如链式代理，CoA）中，代理间传递的自由形式摘要易丢失关键细节并放大早期错误。我们提出COSMIR（链式结构化记忆迭代推理框架），以结构化记忆替代随意通信。规划者将用户查询转化为具体可验证的子问题；工作者按固定微循环（提取、推理、精炼）处理文本块，并将更新写入共享内存；管理者直接从内存合成最终答案。该设计既保留分步读取-推理优势，又通过结构化内存和固定工作流程提升忠实性、长程聚合能力与可审计性。在HEL MET长文本问答套件上，COSMIR显著减少传播阶段的信息损失，优于CoA基线。
原文摘要 · Abstract (English)
Reasoning over very long inputs remains difficult for large language models (LLMs). Common workarounds either shrink the input via retrieval (risking missed evidence), enlarge the context window (straining selectivity), or stage multiple agents to read in pieces. In staged pipelines (e.g., Chain of Agents, CoA), free-form summaries passed between agents can discard crucial details and amplify early mistakes. We introduce COSMIR (Chain Orchestrated Structured Memory for Iterative Reasoning), a chain-style framework that replaces ad hoc messages with a structured memory. A Planner agent first turns a user query into concrete, checkable sub-questions. worker agents process chunks via a fixed micro-cycle: Extract, Infer, Refine, writing all updates to the shared memory. A Manager agent then Synthesizes the final answer directly from the memory. This preserves step-wise read-then-reason benefits while changing both the communication medium (structured memory) and the worker procedure (fixed micro-cycle), yielding higher faithfulness, better long-range aggregation, and auditability. On long-context QA from the HELMET suite, COSMIR reduces propagation-stage information loss and improves accuracy over a CoA baseline.
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。