用双代理架构把网络信息变结构化记忆，提升未来事件预测能力
ForeDreamer: A Self-Evolving Dual-Agent Memory Architecture for Future Event Prediction
- 双代理分工：主代理搜索，子代理将结果转为问题相关的结构化事实记忆
- 在Prophet Arena和FutureX上预测准确率显著优于基线方法
- 适合需要长期推理与动态知识更新的开放网络预测任务
开放网络未来事件预测需从嘈杂、冗余且不完整的证据中提取可靠信号。现有检索/记忆机制直接使用检索内容或仅简单存储复用历史信息，难以应对开放网络预测需求。本文提出将原始网络证据转化为结构化记忆再进行预测，使代理能基于提炼后的、针对性强的证据推理，而非原始噪声结果。提出ForeDreamer框架，通过双代理机制分离事实记忆（当前预测专用）与经验记忆（跨任务累积的代理经验）。主代理负责搜索与预测，子代理利用专用工具将搜索结果转化为事实记忆。同时通过两条路径进化经验记忆，持续优化预测决策与事实记忆构建能力。在Prophet Arena与FutureX上的实验验证了其有效性。
原文摘要 · Abstract (English)
Open-web future event prediction requires agents to distill reliable signals from noisy, redundant, and incomplete evidence. Existing retrieval/memory mechanisms directly feed retrieved information to agents or rely on simple memory functions such as storing and reusing prior information for prediction, leaving them insufficient for open-web forecasting. We propose to transform raw web evidence into structured memory before prediction, enabling agents to reason over distilled, question-specific evidence rather than noisy retrieval results. This paper presents ForeDreamer, a self-evolving dual-agent framework for managing memory over open-web evidence. ForeDreamer separates factual memory, a question-specific evidence state for the current forecast, from experiential memory, persistent agent experience accumulated across forecasting episodes. It uses a main agent for search and prediction, and a memory-processing subagent to convert search results into factual memory with dedicated tools. ForeDreamer further evolves experiential memory through two tracks, improving both forecasting decisions and factual-memory construction. Experiments on Prophet Arena and FutureX demonstrate the effectiveness of ForeDreamer. Project page: https://zhongzero.github.io/ForeDreamer
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。