将人类认知双系统理论用于网页智能体，提升决策效率与适应性。
Cognitive Duality for Adaptive Web Agents
- 采用快速直觉与慢速推理双模式切换机制
- 在WebArena上达43.96%成功率，令牌消耗减少75%
- 适合需要高效自适应的复杂网页任务场景
网页导航是评估通用人工智能（AGI）的关键挑战领域，需在高熵、动态环境中进行复杂决策，且动作空间呈组合爆炸式增长。当前自主网页智能体方法多聚焦于离线模仿学习或在线探索，但很少有效融合两者。受人类认知双过程理论启发，我们提出一种基于快速系统1与慢速系统2的认知分解框架。该框架统一了现有网页智能体方法，弥合了离线学习直觉反应行为与在线获取深思熟虑规划能力之间的鸿沟。我们构建了CogniWeb这一模块化智能体架构，根据任务复杂度自适应切换快慢处理模式。在WebArena上的评估显示，CogniWeb实现了43.96%的成功率，同时令牌使用量降低75%。
原文摘要 · Abstract (English)
Web navigation represents a critical and challenging domain for evaluating artificial general intelligence (AGI), demanding complex decision-making within high-entropy, dynamic environments with combinatorially explosive action spaces. Current approaches to building autonomous web agents either focus on offline imitation learning or online exploration, but rarely integrate both paradigms effectively. Inspired by the dual-process theory of human cognition, we derive a principled decomposition into fast System 1 and slow System 2 cognitive processes. This decomposition provides a unifying perspective on existing web agent methodologies, bridging the gap between offline learning of intuitive reactive behaviors and online acquisition of deliberative planning capabilities. We implement this framework in CogniWeb, a modular agent architecture that adaptively toggles between fast intuitive processing and deliberate reasoning based on task complexity. Our evaluation on WebArena demonstrates that CogniWeb achieves competitive performance (43.96% success rate) while maintaining significantly higher efficiency (75% reduction in token usage).
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。