[论文] LongSeeker: Elastic Context Orchestration for Long-Horizon Search Agents

## 论文概要 **研究领域**: AI **作者**: Yijun Lu, Rui Ye, Yuwen Du, Jiajun Wang, Songhua Liu, Siheng Chen **发布时间**: 2026-05-06 **arXiv**: [2605.05191](https://arxiv.org/abs/2605.05191) ## 中文摘要 长程搜索智能体在推理、调用工具和观察信息时，必须管理快速增长的工作上下文。简单地累积所有中间内容可能使智能体不堪重负，增加成本和错误风险。我们提出，有效的上下文管理应该是自适应的：智能体轨迹的不同部分根据其当前与任务的相关性，以不同的详细程度进行维护。为将这一原则付诸实践，我们引入了Context-ReAct，一种用于弹性上下文编排的通用智能体范式，将推理、上下文管理和工具使用整合到一个统一的循环中。Context-ReAct提供五种原子操作：Skip、Compress、Rollback、Snippet和Delete，使智能体能够动态重塑其工作上下文，保留重要证据、总结已解决的信息、丢弃无用的分支并控制上下文大小。我们证明了Compress操作在表达上是完备的，而其他专门化操作提供了效率和保真度保证，能够降低生成成本和幻觉风险。基于这一范式，我们开发了LongSeeker，一个在10k合成轨迹上从Qwen3-30B-A3B微调的长程搜索智能体。在四个代表性搜索基准上，LongSeeker在BrowseComp上达到61.5%，在BrowseComp-ZH上达到62.5%，大幅超越通义深度研究（43.2%和46.7%）和AgentFold（36.2%和47.3%）。这些结果凸显了自适应上下文管理的潜力，表明智能体可以通过主动塑造工作记忆来实现更可靠和高效的长程推理。 ## 原文摘要 Long-horizon search agents must manage a rapidly growing working context as they reason, call tools, and observe information. Naively accumulating all intermediate content can overwhelm the agent, increasing costs and the risk of errors. We propose that effective context management should be adaptive: parts of the agent's trajectory are maintained at different levels of detail depending on their current relevance to the task. To operationalize this principle, we introduce Context-ReAct, a general agentic paradigm for elastic context orchestration that integrates reasoning, context management, and tool use in a unified loop. Context-ReAct provides five atomic operations: Skip, Compress, Rollback, Snippet and Delete, which allow the agent to dynamically reshape its working context, preserving important evidence, summarizing resolved information, discarding unhelpful branches, and controlling context size. We prove that the Compress operator is expressively complete, while the other specialized operators provide efficiency and fidelity guarantees that reduce generation cost and hallucination risk. Building on this paradigm, we develop LongSeeker, a long-horizon search agent fine-tuned from Qwen3-30B-A3B on 10k synthesized trajectories. Across four representative search benchmarks, LongSeeker achieves 61.5% on BrowseComp and 62.5% on BrowseComp-ZH, substantially outperforming Tongyi DeepResearch (43.2% and 46.7%) and AgentFold (36.2% and 47.3%). These results highlight the potential of adaptive context management, showing that agents can achieve more reliable and efficient long-horizon reasoning by actively shaping their working memory. --- *自动采集于 2026-05-08* #论文 #arXiv #AI #小凯