Related papers: Semantic Caching for OLAP via LLM-Based Query Cano…

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…

We introduce an interleaving operational semantics for describing the client-observable behaviour of atomic transactions on distributed key-value stores. Our semantics builds on abstract states comprising centralised, global key-value…

Serialization formats designed for document interchange impose structural overhead that becomes prohibitive when large language models consume operational data at scale. A modest dataset of 1,000 IoT sensor readings serialized as JSON…

Web applications rely heavily on hyperlinks to connect disparate information resources. However, the dynamic nature of the web leads to link rot, where targets become unavailable, and more insidiously, semantic drift, where a valid HTTP 200…

Personal AI agents incur substantial cost via repeated LLM calls. We show existing caching methods fail: GPTCache achieves 37.9% accuracy on real benchmarks; APC achieves 0-12%. The root cause is optimizing for the wrong property -- cache…

As Large Language Models (LLMs) become increasingly popular, caching responses so that they can be reused by users with semantically similar queries has become a vital strategy for reducing inference costs and latency. Existing caching…

Evaluating large language models (LLMs) for clinical documentation tasks such as SOAP note generation remains challenging. Unlike standard summarization, these tasks require clinical abstraction, normalization of colloquial language, and…

We introduce a neuro-symbolic framework for multi-intent understanding in mobile AI agents by integrating a structured intent ontology with compact language models. Our method leverages retrieval-augmented prompting, logit biasing and…

Large Language Models (LLMs) exhibit strong capabilities in text processing, and recent research has augmented SQL and DataFrame with LLM-powered semantic operators for data analysis. However, LLM-based data processing is hindered by slower…

Agentic security systems increasingly audit live targets with tool-using LLMs, but prior systems fix a single coordination topology, leaving unclear when additional agents help and when they only add cost. We treat topology choice as an…

If LLM training data is polluted with benchmark test data, then benchmark performance gives biased estimates of out-of-distribution (OOD) generalization. Typical decontamination filters use n-gram matching which fail to detect semantic…

Large Language Models (LLMs) can enhance analytics systems with powerful data summarization, cleaning, and semantic transformation capabilities. However, deploying LLMs at scale -- processing millions to billions of rows -- remains…

Code commits in a version control system (e.g., Git) should be atomic, i.e., focused on a single goal, such as adding a feature or fixing a bug. In practice, however, developers often bundle multiple concerns into tangled commits, obscuring…

Why do language agents fail on tasks they are capable of solving? We argue that many such failures are reliability failures caused by stochastic drift from a task's latent solution structure, not capability failures. Every well-defined…

Many computer systems are now being redesigned to incorporate LLM-powered agents, enabling natural language input and more flexible operations. This paper focuses on handling database transactions created by large language models (LLMs).…

Third-Party Risk Assessment (TPRA) relies on large repositories of cybersecurity compliance questions used to assess external suppliers against standards such as ISO/IEC 27001 and NIST. In practice, not all questions are relevant for a…

Large Language Models (LLMs) show promise for automated code optimization but struggle without performance context. This work introduces Opal, a modular framework that connects performance analytics insights with the vast body of published…

Multi-LLM systems harness the complementary strengths of diverse Large Language Models, achieving performance and efficiency gains that are not attainable by a single model. In existing designs, LLMs communicate through text, forcing…

Long-context LLMs increasingly rely on extended, reusable prefill prompts for agents and domain Q&A, pushing attention and KV-cache to become the dominant decode-time bottlenecks. While sparse attention reduces computation and transfer…

We present SLATE, a sequence labeling approach for extracting tasks from free-form content such as digitally handwritten (or "inked") notes on a virtual whiteboard. Our approach allows us to create a single, low-latency model to…