Siyuan Yang
Publications
OpAgent: Operator Agent for Web Navigation
To fulfill user instructions, autonomous web agents must contend with the inherent complexity and volatile nature of real-world websites. Conventional paradigms predominantly rely on Supervised Fine-Tuning (SFT) or Offline Reinforcement Learning (RL) using static datasets. However, these methods suffer from severe distributional shifts, as offline trajectories fail to capture the stochastic state transitions and real-time feedback of unconstrained wide web environments. In this paper, we propose a robust Online Reinforcement Learning WebAgent, designed to optimize its policy through direct, iterative interactions with unconstrained wide websites. Our approach comprises three core innovations: 1) Hierarchical Multi-Task Fine-tuning: We curate a comprehensive mixture of datasets categorized by functional primitives -- Planning, Acting, and Grounding -- establishing a Vision-Language Model (VLM) with strong instruction-following capabilities for Web GUI tasks. 2) Online Agentic RL in the Wild: We develop an online interaction environment and fine-tune the VLM using a specialized RL pipeline. We introduce a Hybrid Reward Mechanism that combines a ground-truth-agnostic WebJudge for holistic outcome assessment with a Rule-based Decision Tree (RDT) for progress reward. This system effectively mitigates the credit assignment challenge in long-horizon navigation. Notably, our RL-enhanced model achieves a 38.1\% success rate (pass@5) on WebArena, outperforming all existing monolithic baselines. 3) Operator Agent: We introduce a modular agentic framework, namely \textbf{OpAgent}, orchestrating a Planner, Grounder, Reflector, and Summarizer. This synergy enables robust error recovery and self-correction, elevating the agent's performance to a new State-of-the-Art (SOTA) success rate of \textbf{71.6\%}.
RegGuard: AI-Powered Retrieval-Enhanced Assistant for Pharmaceutical Regulatory Compliance
The increasing frequency and complexity of regulatory updates present a significant burden for multinational pharmaceutical companies. Compliance teams must interpret evolving rules across jurisdictions, formats, and agencies, often manually, at high cost and risk of error. We introduce RegGuard, an industrial-scale AI assistant designed to automate the interpretation of heterogeneous regulatory texts and align them with internal corporate policies. The system ingests heterogeneous document sources through a secure pipeline and enhances retrieval and generation quality with two novel components: HiSACC (Hierarchical Semantic Aggregation for Contextual Chunking) semantically segments long documents into coherent units while maintaining consistency across non-contiguous sections. ReLACE (Regulatory Listwise Adaptive Cross-Encoder for Reranking), a domain-adapted cross-encoder built on an open-source model, jointly models user queries and retrieved candidates to improve ranking relevance. Evaluations in enterprise settings demonstrate that RegGuard improves answer quality specifically in terms of relevance, groundedness, and contextual focus, while significantly mitigating hallucination risk. The system architecture is built for auditability and traceability, featuring provenance tracking, access control, and incremental indexing, making it highly responsive to evolving document sources and relevant for any domain with stringent compliance demands.