VAGEN: 軌跡に基づく段階的対話検証によるGUIエージェントの報酬モデリング
Agentic Reward Modeling: Verifying GUI Agent via Progressive Trajectory-Grounded Interaction
GUIエージェントの検証を、軌跡の直接証拠と環境への能動的プロービングを段階的に組み合わせて行うツール拡張型検証エージェントVAGENを提案し、OSWorldやAndroidWorldで評価精度と効率の両立を示した。
詳しい要約
1. どんなもの?
2. 先行研究と比べてどこがすごい?
3. 技術・手法の肝は?
4. どうやって有効だと検証した?
5. 議論はある?
6. 次に読むべき論文は?
※ AIが要旨から生成した要約です。正確性は原文をご確認ください。
著者: Chaoqun Cui, Jing Huang, Shijing Wang, Liming Zheng, Qingchao Kong, Zhixiong Zeng
分類: cs.RO
原文アブストラクト
Reinforcement learning with verifiable rewards (RLVR) provides a promising pathway for continuously advancing GUI agents, yet existing reward modeling paradigms face complementary limitations. Rule-based methods suffer from poor scalability and cannot handle open-ended tasks. LLM-as-a-Judge methods enable scalable trajectory verification but remain passive and are constrained by partial state observability, since key evidence often resides in latent environment states beyond the trajectory. Recent active environment interaction methods mitigate observability issues but tend to over-rely on probing while under-utilizing direct trajectory evidence, leading to verification inefficiency. To address these challenges, we advocate a trajectory-grounded interactive verification paradigm. We introduce VAGEN, a framework that employs a tool-augmented verifier agent governed by a Progressive Verification Mechanism, which follows a surface-to-latent and cheap-to-expensive design philosophy to extract trajectory evidence and probe environment states in a proactive end-to-end manner. Experiments on OSWorld-Verified and AndroidWorld benchmarks demonstrate that VAGEN significantly improves evaluation accuracy with a favorable performance-efficiency trade-off.
