让AI在执行任务时主动收集证据，提升验证效率与可靠性。
SmartSnap: Proactive Evidence Seeking for Self-Verifying Agents
- AI主动截取关键操作快照，替代事后冗长回溯验证。
- 8B和30B模型性能分别提升26.08%和16.66%。
- 适合追求高效、可验证的自动化智能体研发人员。
基于智能体的强化学习在复杂图形界面任务中展现巨大潜力，但其可扩展性受限于任务完成状态的验证难题。现有验证方式为被动、事后的分析：通过规则脚本、奖励模型或大模型作为裁判，对完整交互轨迹进行评估，导致处理大量无关噪声数据，造成成本高、可靠性低的问题。为此，本文提出SmartSnap，将验证范式从被动后置转为主动实时自验证。我们设计了具备双重使命的自验证智能体：不仅完成任务，还需通过精心挑选的快照证据证明成果。依据完整性、简洁性与创造性（3C）原则，智能体利用在线环境访问能力，仅对最小且决定性的快照集进行自验证。这些快照作为唯一材料供通用大模型裁判判断其有效性和相关性。在跨模型系列与规模的移动端任务实验中，SmartSnap实现了可扩展的训练，使8B与30B模型性能分别提升26.08%和16.66%。解法探索与证据收集的协同，推动高效自验证智能体的发展，其表现媲美DeepSeek V3.1与Qwen3-235B-A22B。代码已开源。
原文摘要 · Abstract (English)
Agentic reinforcement learning (RL) holds great promise for the development of autonomous agents under complex GUI tasks, but its scalability remains severely hampered by the verification of task completion. Existing task verification is treated as a passive, post-hoc process: a verifier (i.e., rule-based scoring script, reward or critic model, and LLM-as-a-Judge) analyzes the agent's entire interaction trajectory to determine if the agent succeeds. Such processing of verbose context that contains irrelevant, noisy history poses challenges to the verification protocols and therefore leads to prohibitive cost and low reliability. To overcome this bottleneck, we propose SmartSnap, a paradigm shift from this passive, post-hoc verification to proactive, in-situ self-verification by the agent itself. We introduce the Self-Verifying Agent, a new type of agent designed with dual missions: to not only complete a task but also to prove its accomplishment with curated snapshot evidences. Guided by our proposed 3C Principles (Completeness, Conciseness, and Creativity), the agent leverages its accessibility to the online environment to perform self-verification on a minimal, decisive set of snapshots. Such evidences are provided as the sole materials for a general LLM-as-a-Judge verifier to determine their validity and relevance. Experiments on mobile tasks across model families and scales demonstrate that our SmartSnap paradigm allows training LLM-driven agents in a scalable manner, bringing performance gains up to 26.08% and 16.66% respectively to 8B and 30B models. The synergizing between solution finding and evidence seeking facilitates the cultivation of efficient, self-verifying agents with competitive performance against DeepSeek V3.1 and Qwen3-235B-A22B. Code is available at: https://github.com/TencentYoutuResearch/SmartSnap
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。