Learning to Adapt: Self-Improving Web Agent via Cognitive-Aware Exploration
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2026
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866913173770076160 |
|---|---|
| author | Chen, Weile Miao, Bingchen Yu, Qifan Bu, Wendong Wang, Guoming Zhang, Wenqiao Zhang, Shengyu Li, Juncheng Tang, Siliang |
| author_facet | Chen, Weile Miao, Bingchen Yu, Qifan Bu, Wendong Wang, Guoming Zhang, Wenqiao Zhang, Shengyu Li, Juncheng Tang, Siliang |
| contents | Recent advances in Multimodal Large Language Models (MLLMs) have led to promising progress in web agents. However, existing web agents often rely on handcrafted execution pipelines or expensive expert trajectories, limiting their adaptability to complex, dynamic environments. To address these challenges, we propose SCALE (Self-Cognitive-Aware Learning and Exploration), which leverages three adversarial roles, Selector, Predictor, and Judger to autonomously discover the agent's limitations and expand its cognitive boundaries through environmental exploration. Moreover, we propose SCALE-Hop, a graph exploration strategy that facilitates global planning and helps agents avoid local exploration traps. To further support learning, we construct SCALE-20k, a large-scale dataset collected from 19 real-world websites, containing diverse task types and structured demonstrations generated from SCALE's exploration traces. Experimental results show that our approach significantly improves the performance and generalization of multiple MLLMs in various web environments. Our framework offers a scalable and generalizable solution for building truly autonomous and adaptive web agents. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_31365 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Learning to Adapt: Self-Improving Web Agent via Cognitive-Aware Exploration Chen, Weile Miao, Bingchen Yu, Qifan Bu, Wendong Wang, Guoming Zhang, Wenqiao Zhang, Shengyu Li, Juncheng Tang, Siliang Artificial Intelligence Recent advances in Multimodal Large Language Models (MLLMs) have led to promising progress in web agents. However, existing web agents often rely on handcrafted execution pipelines or expensive expert trajectories, limiting their adaptability to complex, dynamic environments. To address these challenges, we propose SCALE (Self-Cognitive-Aware Learning and Exploration), which leverages three adversarial roles, Selector, Predictor, and Judger to autonomously discover the agent's limitations and expand its cognitive boundaries through environmental exploration. Moreover, we propose SCALE-Hop, a graph exploration strategy that facilitates global planning and helps agents avoid local exploration traps. To further support learning, we construct SCALE-20k, a large-scale dataset collected from 19 real-world websites, containing diverse task types and structured demonstrations generated from SCALE's exploration traces. Experimental results show that our approach significantly improves the performance and generalization of multiple MLLMs in various web environments. Our framework offers a scalable and generalizable solution for building truly autonomous and adaptive web agents. |
| title | Learning to Adapt: Self-Improving Web Agent via Cognitive-Aware Exploration |
| topic | Artificial Intelligence |
| url | https://arxiv.org/abs/2605.31365 |