{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,18]],"date-time":"2026-03-18T03:24:56Z","timestamp":1773804296831,"version":"3.50.1"},"reference-count":0,"publisher":"Association for the Advancement of Artificial Intelligence (AAAI)","issue":"33","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["AAAI"],"abstract":"<jats:p>This paper presents FDC-Ground, a reinforcement learning framework that addresses the high-cost, low-signal challenge of GUI grounding training. The framework introduces two core contributions: (1) the Exponentially Decayed Distance Reward (EDDR), which provides resolution-robust and continuous feedback for position predictions, and (2) the Fact-Aligned Dynamic Completions Pruning (FDC-Pruning) strategy, which selectively retains completions whose advantage signs align with factual correctness, thereby reducing computational overhead while enhancing gradient quality and training stability. Using only 3.2K training samples and a single epoch, our 7B-parameter model achieves 88.3% and 91.0% accuracy on ScreenSpot and ScreenSpot-v2, outperforming several RL-based models such as UIShift and SE-GUI. Our 3B-parameter model based on Qwen2.5-VL-3B surpasses its original performance by +26.6%, demonstrating the effectiveness of our reward design and pruning strategy under low-resource conditions. Furthermore, the proposed FDC-Pruning strategy achieves a 1.18\u00d7 training speedup and a +5.9% accuracy improvement over standard GRPO, and expanding the exploration space to 4\u00d7 yields an additional +10.5% gain, confirming both the scalability and the training efficiency of our approach. These findings highlight that combining EDDR with FDC-Pruning offers a practical path toward scalable and efficient RL-based GUI grounding, even in low-resource settings.<\/jats:p>","DOI":"10.1609\/aaai.v40i33.40038","type":"journal-article","created":{"date-parts":[[2026,3,18]],"date-time":"2026-03-18T02:21:24Z","timestamp":1773800484000},"page":"28122-28130","source":"Crossref","is-referenced-by-count":0,"title":["FDC-Ground: Improving GRPO for GUI Grounding via Exponential Rewards and Fact-Aligned Pruning"],"prefix":"10.1609","volume":"40","author":[{"given":"Xiangjian","family":"Zeng","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wenjing","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qingqiang","family":"Wu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Liang","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"9382","published-online":{"date-parts":[[2026,3,14]]},"container-title":["Proceedings of the AAAI Conference on Artificial Intelligence"],"original-title":[],"link":[{"URL":"https:\/\/ojs.aaai.org\/index.php\/AAAI\/article\/download\/40038\/43999","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/ojs.aaai.org\/index.php\/AAAI\/article\/download\/40038\/43999","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,18]],"date-time":"2026-03-18T02:21:24Z","timestamp":1773800484000},"score":1,"resource":{"primary":{"URL":"https:\/\/ojs.aaai.org\/index.php\/AAAI\/article\/view\/40038"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,14]]},"references-count":0,"journal-issue":{"issue":"33","published-online":{"date-parts":[[2026,3,17]]}},"URL":"https:\/\/doi.org\/10.1609\/aaai.v40i33.40038","relation":{},"ISSN":["2374-3468","2159-5399"],"issn-type":[{"value":"2374-3468","type":"electronic"},{"value":"2159-5399","type":"print"}],"subject":[],"published":{"date-parts":[[2026,3,14]]}}}