Research Papers 论文研究 4h ago Updated 1h ago 更新于 1小时前 48

PersonaTrail: Benchmarking Personalized Web Agents through Browsing Trails PersonaTrail:通过浏览轨迹个性化网页代理基准测试

PersonaTrail is a new benchmark designed to evaluate personalized web agents by using realistic browsing trajectories as user history, addressing the gap in handling underspecified instructions. The paper introduces Preference-Aware Contextual Memory (PACMem), a framework that decomposes raw browsing histories into factual memories (session summaries) and preference memories (recurring behavioral patterns). PACMem enables agents to retrieve relevant context from past sessions to infer user prefe 提出 PersonaTrail,首个基于真实浏览轨迹评估个性化网页代理能力的基准测试。 解决现有基准缺乏对用户隐含偏好和未明确指令上下文推理能力的评估问题。 引入 PACMem 框架,将原始浏览历史分解为事实记忆与偏好记忆以增强个性化导航。 实验表明 PACMem 在从历史中推断用户意图和回忆信息方面显著优于基线方法。

65
Hot 热度
72
Quality 质量
68
Impact 影响力

Analysis 深度分析

TL;DR

  • PersonaTrail is a new benchmark designed to evaluate personalized web agents by using realistic browsing trajectories as user history, addressing the gap in handling underspecified instructions.
  • The paper introduces Preference-Aware Contextual Memory (PACMem), a framework that decomposes raw browsing histories into factual memories (session summaries) and preference memories (recurring behavioral patterns).
  • PACMem enables agents to retrieve relevant context from past sessions to infer user preferences and guide personalized navigation, outperforming existing memory-based baselines.
  • Existing benchmarks are criticized for either restricting tasks to fully explicit prompts or abstracting interaction history too much, failing to capture real-world personalization needs.

Why It Matters

This research addresses a critical limitation in current AI web agents: their inability to handle ambiguous user requests by leveraging personal context. By providing a benchmark and a novel memory architecture that distinguishes between specific facts and general preferences, it offers a pathway to more autonomous and personalized AI assistants that can operate effectively in open web environments without requiring exhaustive initial instructions.

Technical Details

  • Benchmark Design: PersonaTrail operates in a managed open web environment, utilizing realistic browsing trajectories to simulate user history. It specifically tests an agent's capacity to infer missing context from these raw histories rather than relying on explicit prompts.
  • Memory Architecture (PACMem): The proposed framework splits memory into two distinct types: "factual memories" which summarize individual browsing sessions, and "preference memories" which distill recurring behavioral patterns across sessions.
  • Retrieval Mechanism: At inference time, the agent retrieves the most relevant entries from both factual and preference memories to inform its decision-making process, allowing for dynamic adaptation to user-specific contexts.
  • Evaluation: Extensive experiments demonstrate that PACMem consistently achieves higher performance compared to existing memory-based baselines on tasks requiring personalization and context recall.

Industry Insight

  • Shift Towards Personalized Agents: The industry must move beyond generic task execution models to incorporate long-term memory structures that differentiate between transient facts and enduring user preferences.
  • Data Privacy and Structure: Decomposing browsing history into structured factual and preference memories offers a potential model for balancing utility with privacy, as it allows for abstraction of sensitive raw data while retaining useful behavioral insights.
  • Benchmarking Standards: Current evaluation metrics for web agents are insufficient for real-world deployment; adopting benchmarks like PersonaTrail that test for ambiguity resolution and personalization will be crucial for developing robust consumer-facing AI tools.

TL;DR

  • 提出 PersonaTrail,首个基于真实浏览轨迹评估个性化网页代理能力的基准测试。
  • 解决现有基准缺乏对用户隐含偏好和未明确指令上下文推理能力的评估问题。
  • 引入 PACMem 框架,将原始浏览历史分解为事实记忆与偏好记忆以增强个性化导航。
  • 实验表明 PACMem 在从历史中推断用户意图和回忆信息方面显著优于基线方法。

为什么值得看

随着大语言模型推动网页代理自主执行复杂任务,如何有效利用用户历史数据实现真正的个性化服务成为关键挑战。该研究不仅填补了个性化网页代理评估的空白,还提出了结构化的记忆管理机制,对提升AI代理的用户体验和理解能力具有重要参考价值。

技术解析

  • PersonaTrail 基准:构建于受控开放网络环境中,使用真实的浏览轨迹作为用户历史,专门评估代理从非明确指令中推断用户偏好及回忆过往会话信息的能力。
  • PACMem 框架:一种偏好感知上下文记忆机制,将非结构化的原始浏览历史分解为两类结构化记忆:总结单个会话内容的“事实记忆”和提炼重复行为模式的“偏好记忆”。
  • 检索与推理机制:在推理阶段,代理根据当前任务从上述两种记忆中检索最相关的条目,以此引导个性化的网页导航和决策过程。
  • 性能验证:通过广泛实验证明,PACMem 在处理个性化网页任务时,其表现一致性地超越了现有的基于记忆的基线模型。

行业启示

  • 个性化AI代理的新标准:行业需从单纯的任务完成度转向对用户隐式需求和历史行为的深度理解,建立更贴近真实场景的个性化评估体系。
  • 记忆架构的重要性:将非结构化数据(如浏览日志)转化为结构化记忆(事实+偏好)是提升LLM代理长期记忆和个性化服务能力的关键技术路径。
  • 隐私与数据利用平衡:在利用用户历史数据进行个性化优化的同时,需关注如何在受控环境中处理敏感浏览数据,确保符合数据隐私规范。

Disclaimer: The above content is generated by AI and is for reference only. 免责声明:以上内容由 AI 生成,仅供参考。

Agent Agent Benchmark 基准测试 Evaluation 评测