Cognitive Duality for Adaptive Web Agents

• URL: http://arxiv.org/abs/2508.05081v1
• Date: Thu, 07 Aug 2025 07:05:22 GMT
• Title: Cognitive Duality for Adaptive Web Agents
• Authors: Jiarun Liu, Chunhong Zhang, Zheng Hu,
• Abstract summary: We propose a principled decomposition into fast System 1 and slow System 2 cognitive processes.<n>We implement this framework in CogniWeb, a modular agent architecture that adaptively toggles between fast intuitive processing and deliberate reasoning based on task complexity.
• Score: 3.0069922338220825
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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).

Related papers

• Web-CogReasoner: Towards Knowledge-Induced Cognitive Reasoning for Web Agents [49.88380945341337]
  We decompose a web agent's capabilities into two essential stages: knowledge content learning and cognitive processes.<n>To facilitate knowledge acquisition, we construct the Web-CogDataset, a structured resource curated from 14 real-world websites.<n>Building on this foundation, we operationalize these processes through a novel knowledge-driven Chain-of-Thought (CoT) reasoning framework.
  arXiv  Detail & Related papers  (2025-08-03T17:17:52Z)
• WebCoT: Enhancing Web Agent Reasoning by Reconstructing Chain-of-Thought in Reflection, Branching, and Rollback [74.82886755416949]
  We identify key reasoning skills essential for effective web agents.<n>We reconstruct the agent's reasoning algorithms into chain-of-thought rationales.<n>Our approach yields significant improvements across multiple benchmarks.
  arXiv  Detail & Related papers  (2025-05-26T14:03:37Z)
• Incentivizing Dual Process Thinking for Efficient Large Language Model Reasoning [75.04643265875072]
  Large reasoning models (LRMs) have demonstrated strong performance on complex reasoning tasks, but often suffer from overthinking.<n>Inspired by the dual process theory in cognitive science, we propose Adaptive Cognition Policy Optimization.<n>ACPO enables LRMs to achieve efficient reasoning through adaptive cognitive allocation and dynamic system switch.
  arXiv  Detail & Related papers  (2025-05-22T07:15:08Z)
• WebGames: Challenging General-Purpose Web-Browsing AI Agents [11.320069795732058]
  WebGames is a comprehensive benchmark suite designed to evaluate general-purpose web-browsing AI agents.<n>We evaluate leading vision-language models including GPT-4o, Claude Computer-Use, Gemini-1.5-Pro, and Qwen2-VL against human performance.<n>Results reveal a substantial capability gap, with the best AI system achieving only 43.1% success rate compared to human performance of 95.7%.
  arXiv  Detail & Related papers  (2025-02-25T16:45:08Z)
• R2D2: Remembering, Replaying and Dynamic Decision Making with a Reflective Agentic Memory [53.94879482534949]
  Current models often struggle with efficient navigation and action execution due to limited visibility and understanding of web structures.<n>Our proposed R2D2 framework addresses these challenges by integrating two paradigms: Remember and Reflect.<n>Our findings suggest that a combination of memory-enhanced navigation and reflective learning promisingly advances the capabilities of web agents.
  arXiv  Detail & Related papers  (2025-01-21T20:21:58Z)
• Visual Agents as Fast and Slow Thinkers [88.1404921693082]
  We introduce FaST, which incorporates the Fast and Slow Thinking mechanism into visual agents.<n>FaST employs a switch adapter to dynamically select between System 1/2 modes.<n>It tackles uncertain and unseen objects by adjusting model confidence and integrating new contextual data.
  arXiv  Detail & Related papers  (2024-08-16T17:44:02Z)
• Robust Interaction-Based Relevance Modeling for Online e-Commerce Search [8.499253194630665]
  Traditional text-matching techniques fail to capture the nuances of search intent accurately. We introduce a robust interaction-based modeling paradigm to address these shortcomings. To the best of our knowledge, this method is the first interaction-based approach for large e-commerce search relevance calculation.
  arXiv  Detail & Related papers  (2024-06-04T09:24:04Z)
• Synergising Human-like Responses and Machine Intelligence for Planning in Disaster Response [10.294618771570985]
  We propose an attention-based cognitive architecture inspired by Dual Process Theory (DPT) This framework integrates, in an online fashion, rapid yet (human-like) responses with the slow but optimized planning capabilities of machine intelligence.
  arXiv  Detail & Related papers  (2024-04-15T15:47:08Z)
• Interactive Autonomous Navigation with Internal State Inference and Interactivity Estimation [58.21683603243387]
  We propose three auxiliary tasks with relational-temporal reasoning and integrate them into the standard Deep Learning framework. These auxiliary tasks provide additional supervision signals to infer the behavior patterns other interactive agents. Our approach achieves robust and state-of-the-art performance in terms of standard evaluation metrics.
  arXiv  Detail & Related papers  (2023-11-27T18:57:42Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.