Saved in:
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2512.01763 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866910044570779648 |
|---|---|
| author | Zhou, Xurui Chen, Gongwei Xie, Yuquan Li, Zaijing Zhou, Kaiwen Wang, Shuai Yang, Shuo Tian, Zhuotao Shao, Rui |
| author_facet | Zhou, Xurui Chen, Gongwei Xie, Yuquan Li, Zaijing Zhou, Kaiwen Wang, Shuai Yang, Shuo Tian, Zhuotao Shao, Rui |
| contents | Graphical User Interface (GUI) agents require effective use of historical context to perform sequential navigation tasks. While incorporating past actions and observations can improve decision making, naive use of full history leads to excessive computational overhead and distraction from irrelevant information. To address this, we introduce HiconAgent, a GUI agent trained with History Context-aware Policy Optimization (HCPO) for efficient and effective utilization of historical information. HCPO optimizes history usage in both sampling and policy updates through two complementary components: (1) Dynamic Context Sampling (DCS) presents the agent with variable length histories during sampling, enabling adaptive use of the most relevant context; (2) Anchor-guided History Compression (AHC) refines the policy update phase with a dual branch strategy where the compressed branch removes history observations while keeping history actions as information flow anchors. The compressed and uncompressed branches are coupled through a history-enhanced alignment loss to enforce consistent history usage while maintaining efficiency. Experiments on mainstream GUI navigation benchmarks demonstrate strong performance. Despite being smaller, HiconAgent-3B outperforms GUI-R1-7B by +8.46 percent grounding accuracy and +11.32 percent step success rate on GUI-Odyssey, while achieving comparable results on AndroidControl and AITW with up to 2.47x computational speedup and 60 percent FLOPs reduction. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2512_01763 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | HiconAgent: History Context-aware Policy Optimization for GUI Agents Zhou, Xurui Chen, Gongwei Xie, Yuquan Li, Zaijing Zhou, Kaiwen Wang, Shuai Yang, Shuo Tian, Zhuotao Shao, Rui Computer Vision and Pattern Recognition Graphical User Interface (GUI) agents require effective use of historical context to perform sequential navigation tasks. While incorporating past actions and observations can improve decision making, naive use of full history leads to excessive computational overhead and distraction from irrelevant information. To address this, we introduce HiconAgent, a GUI agent trained with History Context-aware Policy Optimization (HCPO) for efficient and effective utilization of historical information. HCPO optimizes history usage in both sampling and policy updates through two complementary components: (1) Dynamic Context Sampling (DCS) presents the agent with variable length histories during sampling, enabling adaptive use of the most relevant context; (2) Anchor-guided History Compression (AHC) refines the policy update phase with a dual branch strategy where the compressed branch removes history observations while keeping history actions as information flow anchors. The compressed and uncompressed branches are coupled through a history-enhanced alignment loss to enforce consistent history usage while maintaining efficiency. Experiments on mainstream GUI navigation benchmarks demonstrate strong performance. Despite being smaller, HiconAgent-3B outperforms GUI-R1-7B by +8.46 percent grounding accuracy and +11.32 percent step success rate on GUI-Odyssey, while achieving comparable results on AndroidControl and AITW with up to 2.47x computational speedup and 60 percent FLOPs reduction. |
| title | HiconAgent: History Context-aware Policy Optimization for GUI Agents |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2512.01763 |