Gespeichert in:
| Hauptverfasser: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | https://arxiv.org/abs/2509.21823 |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866910130488999936 |
|---|---|
| author | Dai, Gaole Jiang, Shiqi Cao, Ting Yang, Yuqing Li, Yuanchun Tan, Rui Li, Mo Qiu, Lili |
| author_facet | Dai, Gaole Jiang, Shiqi Cao, Ting Yang, Yuqing Li, Yuanchun Tan, Rui Li, Mo Qiu, Lili |
| contents | Reward is critical to the evaluation and training of large language models (LLMs). However, existing rule-based or model-based reward methods struggle to generalize to GUI agents, where access to ground-truth trajectories or application databases is often unavailable, and static trajectory-based LLM-as-a-Judge approaches suffer from limited accuracy. To address these challenges, we propose ProRe, a proactive reward system that leverages a general-purpose reasoner and domain-specific evaluator agents (actors). The reasoner schedules targeted state probing tasks, which the evaluator agents then execute by actively interacting with the environment to collect additional observations. This enables the reasoner to assign more accurate and verifiable rewards to GUI agents. Empirical results on over 3K trajectories demonstrate that ProRe improves reward accuracy and F1 score by up to 5.3\% and 19.4\%, respectively. Furthermore, integrating ProRe with state-of-the-art policy agents yields a success rate improvement of up to 22.4\%. The source code is available at https://github.com/V-Droid-Agent/ProRe. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_21823 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | ProRe: A Proactive Reward System for GUI Agents via Reasoner-Actor Collaboration Dai, Gaole Jiang, Shiqi Cao, Ting Yang, Yuqing Li, Yuanchun Tan, Rui Li, Mo Qiu, Lili Artificial Intelligence Reward is critical to the evaluation and training of large language models (LLMs). However, existing rule-based or model-based reward methods struggle to generalize to GUI agents, where access to ground-truth trajectories or application databases is often unavailable, and static trajectory-based LLM-as-a-Judge approaches suffer from limited accuracy. To address these challenges, we propose ProRe, a proactive reward system that leverages a general-purpose reasoner and domain-specific evaluator agents (actors). The reasoner schedules targeted state probing tasks, which the evaluator agents then execute by actively interacting with the environment to collect additional observations. This enables the reasoner to assign more accurate and verifiable rewards to GUI agents. Empirical results on over 3K trajectories demonstrate that ProRe improves reward accuracy and F1 score by up to 5.3\% and 19.4\%, respectively. Furthermore, integrating ProRe with state-of-the-art policy agents yields a success rate improvement of up to 22.4\%. The source code is available at https://github.com/V-Droid-Agent/ProRe. |
| title | ProRe: A Proactive Reward System for GUI Agents via Reasoner-Actor Collaboration |
| topic | Artificial Intelligence |
| url | https://arxiv.org/abs/2509.21823 |