NesyProAct: Proactive Neural-Symbolic Control for Web Agents

Keyi Xiang, Tianyi Tang, Jie-Jing Shao, Yueming Lyu, Ivor Tsang, Yew-Soon Ong, Haiyan Yin

Keywords: Structured Control, Proactive Grounding

Abstract: Web-based language agents operate under severe partial observability, where the semantic divergence between internal state assumptions and the ground-truth environment is often unobservable. Consequently, agents frequently maintain high-level reasoning coherence over misgrounded states, causing errors to compound as subsequent decisions are conditioned on silently invalidated premises. We present **NesyProAct**, a proactive neural-symbolic agentic decision framework that transforms conventional ReAct-style web agents from reactive prompting pipelines into execution-aware decision processes. NesyProAct exposes a typed symbolic decision interface over states, actions, transitions, and subgoals, enabling LLM-based agents to automatically compose and reason over execution semantics across decision hierarchies. From this interface, programmatic verification logic is synthesized online to evaluate step-level executability and progress, with verification outcomes directly regulating decision evolution through targeted grounding interventions. As a result, execution feedback is integrated into planning itself, allowing agents to maintain semantic alignment under partial observability rather than propagating unverified assumptions. On WebArena, NesyProAct achieves a **17.8%** overall improvement over strong skill-induction agentic web framework ASI across six domains. NesyProAct also achieves noticeable performance when reasoning with small models GPT-4o-mini, with **5.1%** gain over ASI with Claude-3.5.

Email Sharing: We authorize the sharing of all author emails with Program Chairs.

Data Release: We authorize the release of our submission and author names to the public in the event of acceptance.

Submission Number: 106