Probe-then-Plan: Environment-Aware Planning for Industrial E-commerce Search
This work addresses the problem of efficient and effective search planning for complex user intents in industrial e-commerce, representing an incremental improvement by integrating environmental awareness into existing LLM-based methods.
The paper tackles the dilemma in e-commerce search between LLM-based query rewriting, which is blind to retrieval capabilities and inventory, and deep search agents, which are too slow for industrial budgets, by proposing Environment-Aware Search Planning (EASP) with a Probe-then-Plan mechanism. It demonstrates significant improvements in relevant recall and lifts in UCVR and GMV through offline evaluations and online A/B testing on JD.com.
Modern e-commerce search is evolving to resolve complex user intents. While Large Language Models (LLMs) offer strong reasoning, existing LLM-based paradigms face a fundamental blindness-latency dilemma: query rewriting is agnostic to retrieval capabilities and real-time inventory, yielding invalid plans; conversely, deep search agents rely on iterative tool calls and reflection, incurring seconds of latency incompatible with industrial sub-second budgets. To resolve this conflict, we propose Environment-Aware Search Planning (EASP), reformulating search planning as a dynamic reasoning process grounded in environmental reality. EASP introduces a Probe-then-Plan mechanism: a lightweight Retrieval Probe exposes the retrieval snapshot, enabling the Planner to diagnose execution gaps and generate grounded search plans. The methodology comprises three stages: (1) Offline Data Synthesis: A Teacher Agent synthesizes diverse, execution-validated plans by diagnosing the probed environment. (2) Planner Training and Alignment: The Planner is initialized via Supervised Fine-Tuning (SFT) to internalize diagnostic capabilities, then aligned with business outcomes (conversion rate) via Reinforcement Learning (RL). (3) Adaptive Online Serving: A complexity-aware routing mechanism selectively activates planning for complex queries, ensuring optimal resource allocation. Extensive offline evaluations and online A/B testing on JD.com demonstrate that EASP significantly improves relevant recall and achieves substantial lifts in UCVR and GMV. EASP has been successfully deployed in JD.com's AI-Search system.