Decoupling Search from Reasoning: A Vendor-Agnostic Grounding Architecture for LLM Agents

Production LLM agents increasingly depend on real-time search, yet native search grounding bundles retrieval policy, provider choice, evidence injection, cost, latency, and generation behavior behind a single model-provider boundary. This coupling makes grounding hard to inspect, tune, reuse, or port, and can trigger Search-Induced Verbosity that breaks strict output contracts. We present Decoupled Search Grounding (DSG), a vendor-agnostic boundary that moves grounding outside the reasoning model through an MCP-compatible gateway, exposing provider routing, source-aware context rendering, configured fallback, retrieval-depth control, and exact plus semantic caching as first-class controls. Across five frontier models on SimpleQA, FreshQA, and HotpotQA, native search leads on recency-sensitive FreshQA, but DSG exposes a stronger frontier when control matters: on SimpleQA it nearly matches native accuracy (86.1% vs. 87.7%) at 91% lower search cost, preserves concise answer contracts, and reaches a 99.4% warm-cache hit rate with 68% lower latency. Deployed as a shared production grounding layer for large-scale agentic workloads with interchangeable models, DSG matches or slightly exceeds native-search accuracy on an e-commerce query-understanding (QIU) workload while cutting search cost by over 98%. Real-time grounding is best treated as an optimizable interface boundary, not a fixed model feature.

Mind the Gap: Bridging Behavioral Silos with LLMs in Multi-Vertical Recommendations

In multi-vertical e-commerce platforms like DoorDash, relatively newer product verticals such as grocery and retail present a significant opportunity for personalization innovation. A key challenge lies in solving the "cold start" problem for users. This paper introduces a novel framework for enhancing recommendation quality by transferring knowledge from data-rich verticals (e.g., restaurants at DoorDash) to data-sparse ones. We leverage Large Language Models (LLMs) to perform generative inference, synthesizing sparse, high-dimensional features that encapsulate latent user affinities. Specifically, we employ a hierarchical Retrieval-Augmented Generation (RAG) pipeline to derive multi-level taxonomic features from user restaurant order histories and search queries. These generated features, encoding both long-term cross-vertical preferences and short-term intent, are integrated into a production Multi-Task Learning (MTL) ranking model. We demonstrate through extensive offline and online evaluation that this approach significantly improves personalization and engagement in emerging business verticals, effectively bridging the behavioral data gap.

Joint Optimization of Relevance and Engagement in Multi-Task Ranking for E-Commerce with Efficient LLM Supervision

Optimizing industrial search ranking models solely for user engagement signals often introduces systematic biases, prioritizing popular or price-anchored items that may not satisfy semantic intent. We present a production-scale multi-task ranking system that integrates semantic relevance as a primary optimization objective, enabling explicit and controllable relevance-engagement trade-offs. Our architecture employs an ordinal relevance head that predicts cumulative probabilities over relevance thresholds, preserving the inherent ordering of labels. These outputs are integrated with engagement heads through a unified value model scoring function, enabling systematic balancing of semantic quality and short-term behavioral signals. To provide high-quality supervision for this multi-task framework, we utilize fine-tuned lightweight Large Language Models (LLMs) to generate three-level ordinal relevance labels: irrelevant, moderately relevant, and highly relevant. We address challenges regarding label distribution sensitivity and ensure high alignment with human annotations to enable efficient labeling for over 100 million query-item pairs. Evaluation across offline metrics, including NDCG@10, and online A/B experiments demonstrates that our approach significantly improves semantic alignment while preserving core engagement objectives.

Build, Judge, Optimize: A Blueprint for Continuous Improvement of Multi-Agent Consumer Assistants

Conversational shopping assistants (CSAs) represent a compelling application of agentic AI, but moving from prototype to production reveals two underexplored challenges: how to evaluate multi-turn interactions and how to optimize tightly coupled multi-agent systems. Grocery shopping further amplifies these difficulties, as user requests are often underspecified, highly preference-sensitive, and constrained by factors such as budget and inventory. In this paper, we present a practical blueprint for evaluating and optimizing conversational shopping assistants, illustrated through a production-scale AI grocery assistant. We introduce a multi-faceted evaluation rubric that decomposes end-to-end shopping quality into structured dimensions and develop a calibrated LLM-as-judge pipeline aligned with human annotations. Building on this evaluation foundation, we investigate two complementary prompt-optimization strategies based on a SOTA prompt-optimizer called GEPA (Shao et al., 2025): (1) Sub-agent GEPA, which optimizes individual agent nodes against localized rubrics, and (2) MAMuT (Multi-Agent Multi-Turn) GEPA (Herrera et al., 2026), a novel system-level approach that jointly optimizes prompts across agents using multi-turn simulation and trajectory-level scoring. We release rubric templates and evaluation design guidance to support practitioners building production CSAs.

Agentic Multi-Source Grounding for Enhanced Query Intent Understanding: A DoorDash Case Study

Accurately mapping user queries to business categories is a fundamental Information Retrieval challenge for multi-category marketplaces, where context-sparse queries such as "Wildflower" exhibit intent ambiguity, simultaneously denoting a restaurant chain, a retail product, and a floral item. Traditional classifiers force a winner-takes-all assignment, while general-purpose LLMs hallucinate unavailable inventory. We introduce an Agentic Multi-Source Grounded system that addresses both failure modes by grounding LLM inference in (i) a staged catalog entity retrieval pipeline and (ii) an agentic web-search tool invoked autonomously for cold-start queries. Rather than predicting a single label, the model emits an ordered multi-intent set, resolved by a configurable disambiguation layer that applies deterministic business policies and is designed for extensibility to personalization signals. This decoupled design generalizes across domains, allowing any marketplace to supply its own grounding sources and resolution rules without modifying the core architecture. Evaluated on DoorDash's multi-vertical search platform, the system achieves +10.9pp over the ungrounded LLM baseline and +4.6pp over the legacy production system. On long-tail queries, incremental ablations attribute +8.3pp to catalog grounding, +3.2pp to agentic web search grounding, and +1.5pp to dual intent disambiguation, yielding 90.7% accuracy (+13.0pp over baseline). The system is deployed in production, serving over 95% of daily search impressions, and establishes a generalizable paradigm for applications requiring foundation models grounded in proprietary context and real-time web knowledge to resolve ambiguous, context-sparse decision problems at scale.

Mine and Refine: Optimizing Graded Relevance in E-commerce Search Retrieval

We propose a two-stage "Mine and Refine" contrastive training framework for semantic text embeddings to enhance multi-category e-commerce search retrieval. Large scale e-commerce search demands embeddings that generalize to long tail, noisy queries while adhering to scalable supervision compatible with product and policy constraints. A practical challenge is that relevance is often graded: users accept substitutes or complements beyond exact matches, and production systems benefit from clear separation of similarity scores across these relevance strata for stable hybrid blending and thresholding. To obtain scalable policy consistent supervision, we fine-tune a lightweight LLM on human annotations under a three-level relevance guideline and further reduce residual noise via engagement driven auditing. In Stage 1, we train a multilingual Siamese two-tower retriever with a label aware supervised contrastive objective that shapes a robust global semantic space. In Stage 2, we mine hard samples via ANN and re-annotate them with the policy aligned LLM, and introduce a multi-class extension of circle loss that explicitly sharpens similarity boundaries between relevance levels, to further refine and enrich the embedding space. Robustness is additionally improved through additive spelling augmentation and synthetic query generation. Extensive offline evaluations and production A/B tests show that our framework improves retrieval relevance and delivers statistically significant gains in engagement and business impact.