Saved in:
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2512.10371 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911659974459392 |
|---|---|
| author | Tian, Shizuo Wen, Hao Chen, Yuxuan Liu, Jiacheng Zhao, Shanhui Liu, Guohong Ren, Ju Liu, Yunxin Li, Yuanchun |
| author_facet | Tian, Shizuo Wen, Hao Chen, Yuxuan Liu, Jiacheng Zhao, Shanhui Liu, Guohong Ren, Ju Liu, Yunxin Li, Yuanchun |
| contents | The rapid development of mobile GUI agents has stimulated growing research interest in long-horizon task automation. However, building agents for these tasks faces a critical bottleneck: the reliance on ever-expanding interaction history incurs substantial context overhead. Existing context management and compression techniques often fail to preserve vital semantic information, leading to degraded task performance. We propose AgentProg, a program-guided approach for agent context management that reframes the interaction history as a program with variables and control flow. By organizing information according to the structure of program, this structure provides a principled mechanism to determine which information should be retained and which can be discarded. We further integrate a global belief state mechanism inspired by Belief MDP framework to handle partial observability and adapt to unexpected environmental changes. Experiments on AndroidWorld and our extended long-horizon task suite demonstrate that AgentProg has achieved the state-of-the-art success rates on these benchmarks. More importantly, it maintains robust performance on long-horizon tasks while baseline methods experience catastrophic degradation. Our system is open-sourced at https://github.com/MobileLLM/AgentProg. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2512_10371 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | AgentProg: Empowering Long-Horizon GUI Agents with Program-Guided Context Management Tian, Shizuo Wen, Hao Chen, Yuxuan Liu, Jiacheng Zhao, Shanhui Liu, Guohong Ren, Ju Liu, Yunxin Li, Yuanchun Artificial Intelligence The rapid development of mobile GUI agents has stimulated growing research interest in long-horizon task automation. However, building agents for these tasks faces a critical bottleneck: the reliance on ever-expanding interaction history incurs substantial context overhead. Existing context management and compression techniques often fail to preserve vital semantic information, leading to degraded task performance. We propose AgentProg, a program-guided approach for agent context management that reframes the interaction history as a program with variables and control flow. By organizing information according to the structure of program, this structure provides a principled mechanism to determine which information should be retained and which can be discarded. We further integrate a global belief state mechanism inspired by Belief MDP framework to handle partial observability and adapt to unexpected environmental changes. Experiments on AndroidWorld and our extended long-horizon task suite demonstrate that AgentProg has achieved the state-of-the-art success rates on these benchmarks. More importantly, it maintains robust performance on long-horizon tasks while baseline methods experience catastrophic degradation. Our system is open-sourced at https://github.com/MobileLLM/AgentProg. |
| title | AgentProg: Empowering Long-Horizon GUI Agents with Program-Guided Context Management |
| topic | Artificial Intelligence |
| url | https://arxiv.org/abs/2512.10371 |