The paper introduces Signals and Queries (S&Q), a lightweight first-stage relevance filter for LLM agents that removes at least 30% of candidate policies before downstream evaluation while maintaining high recall. S&Q uses offline-generated activating examples and hard negatives to train a logistic classifier that predicts policy relevance via embeddings and vector dot products, eliminating per-turn LLM calls. Evaluated on 9,144 relevance labels across 254 conversation prefixes and 36 airline policies, S&Q outperforms top‑K and cosine‑threshold retrieval in precision at every recall level, consistently across two embedding providers.
User-facing LLM agents must identify which behavioral policies apply at each turn, but evaluating every policy with an LLM is costly. We introduce Signals and Queries (S&Q), a lightweight first-stage...
Merchant risk control at large payment platforms screens tens of millions of merchants daily, where false positives harm legitimate merchants and false negatives leave harmful activity undetected. The hardest cases require jointly understanding a merchant's textual profile and long behavioral sequence.
arXiv:2607. 23121v1 Announce Type: cross Abstract: Dynamic Product Ads (DPA) require retrieving relevant items from multi-million product catalogs, balancing two competing objectives: retargeting (re-surfacing known interests) and prospecting (discovering new categories).
arXiv:2607. 29606v1 Announce Type: cross Abstract: A fundamental challenge of vector search is achieving consistently high recall while minimizing computational costs.
arXiv:2607. 27172v1 Announce Type: cross Abstract: Traditional search systems are optimized to retrieve items that strictly match a query, often prioritizing precision over recall.
arXiv:2607. 22690v1 Announce Type: new Abstract: Long-term memory lets LLM agents reuse past interactions, but raw dialogue histories are verbose and information-sparse.
The paper introduces a memory-augmented retrieval method that leverages token-level evidence instead of relying solely on single-vector embeddings. By performing sparse token matching and aggregating scores with whole-memory similarity, the approach improves retrieval performance across eight benchmarks and various model families without extra training. An optional low-rank query adapter can further boost results when supervised.
arXiv:2607. 20528v1 Announce Type: new Abstract: Online recommendation platforms increasingly use Large Language Models (LLMs) to extract structured features from ad creatives.
arXiv:2610.14550v1 Announce Type: cross Abstract: Dynamic Product Advertising (DPA) retrieval systems are a core component of modern e-commerce advertising; however, their evaluation remains challeng...
arXiv:2603.18272v2 Announce Type: replace Abstract: While large language models (LLMs) have advanced the development of general-purpose agents, robust generalization to unseen tasks remains challengi...
arXiv:2605. 25475v2 Announce Type: replace-cross Abstract: Large Language Models (LLMs) are increasingly expected to operate over long contexts, yet standard softmax attention incurs a KV cache that grows linearly with sequence length, quickly becoming the bottleneck for long context inference.
arXiv:2609.23646v1 Announce Type: cross Abstract: E-commerce search requires distinguishing products that are merely related to a query from those that directly satisfy the user's shopping intent. We...