COSMIR：面向长上下文迭代推理的链式编排结构化记忆
COSMIR: Chain Orchestrated Structured Memory for Iterative Reasoning over Long Context
AI总结：
针对大语言模型长上下文推理的信息丢失与错误放大问题，提出采用结构化记忆和固定工作微周期的COSMIR链式框架，在HELMET长问答任务上相比CoA基线减少信息损失、提升准确率。
摘要：
大语言模型（LLM）在处理超长输入的推理任务时仍存在困难。常见的解决方案要么通过检索压缩输入（存在遗漏证据的风险），要么扩大上下文窗口（会加重信息筛选的负担），要么采用多智能体分块读取的流水线模式。在分阶段流水线（例如Chain of Agents，简称CoA）中，智能体之间传递的自由形式摘要可能丢失关键细节，还会放大早期错误。\n我们提出了COSMIR（Chain Orchestrated Structured Memory for Iterative Reasoning，面向迭代推理的链式编排结构化记忆），这是一种链式框架，用结构化记忆替代了临时传递的消息。Planner（规划器）智能体首先将用户查询转化为具体、可验证的子问题。worker（工作）智能体通过固定的微周期处理文本块：提取、推理、精炼，并将所有更新写入共享记忆。随后Manager（管理器）智能体直接从记忆中合成最终答案。该方法保留了“先读取后推理”的分步优势，同时改变了通信媒介（结构化记忆）和工作智能体的执行流程（固定微周期），从而实现更高的忠实度、更好的长距离信息聚合能力以及可审计性。在HELMET基准套件的长上下文问答任务上，COSMIR减少了传播阶段的信息损失，相比CoA基线提升了准确率。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
