Related papers: Why Agent Caching Fails and How to Fix It: Structu…
Rapid advances in Large Language Models (LLMs) create new opportunities by enabling efficient exploration of broad, complex design spaces. This is particularly valuable in computer architecture, where performance depends on…
Large Language Models (LLMs) and other large foundation models have achieved noteworthy success, but their size exacerbates existing resource consumption and latency challenges. In particular, the large-scale deployment of these models is…
Modern code intelligence agents operate in contexts exceeding 1 million tokens--far beyond the scale where humans manually locate relevant files. Yet agents consistently fail to discover architecturally critical files when solving…
Recent advances in Large Language Models (LLMs) have revolutionized web applications, enabling intelligent search, recommendation, and assistant services with natural language interfaces. Tool-calling extends LLMs with the ability to…
Performance and scalability requirements have a fundamental role in most large-scale software applications. To satisfy such requirements, caching is often used at various levels and infrastructure layers. Application-level caching -- or…
When multiple LLM-based code agents independently implement parts of the same class, they must agree on shared internal representations, even when the specification leaves those choices implicit. We study this coordination problem across 51…
This report investigates enhancing semantic caching effectiveness by employing specialized, fine-tuned embedding models. Semantic caching relies on embedding similarity rather than exact key matching, presenting unique challenges in…
Large Language Models (LLMs) based autonomous agents demonstrate multifaceted capabilities to contribute substantially to economic production. However, existing benchmarks remain focused on single agentic capability, failing to capture…
Software bugs cost technology providers (e.g., AT&T) billions annually and cause developers to spend roughly 50% of their time on bug resolution. Traditional methods for bug localization often analyze the suspiciousness of code components…
In this paper we determine how multi-layer ensembling improves performance on multilingual intent classification. We develop a novel multi-layer ensembling approach that ensembles both different model initializations and different model…
Large language model based multi-agent systems have demonstrated significant potential in social simulation and complex task resolution domains. However, current frameworks face critical challenges in system architecture design,…
Agent Skills, structured packages of procedural knowledge loaded into an LLM agent at inference time, are widely reported to improve task pass rates by an average of 16.2~percentage points across diverse domains. Yet the same benchmarks…
Large Language Model-based Multi-Agent Systems (MAS) have demonstrated remarkable capabilities in complex tasks. However, manually designing optimal communication topologies is labor-intensive, while automated expansion methods often result…
We demonstrate how collective memory emerges in decentralized multi-agent systems through the interplay between individual agent memory and environmental trace communication. Our agents maintain internal memory states while depositing…
Large Language Model agents increasingly operate external systems through programmatic interfaces, yet practitioners lack empirical guidance on how to structure the context these agents consume. Using SQL generation as a proxy for…
As AI deployments become more complex and high-stakes, it becomes increasingly important to be able to estimate their risk. AI control is one framework for doing so. However, good control evaluations require eliciting strong attack…
AI governance programmes increasingly rely on natural language prompts to constrain and direct AI agent behaviour. These prompts function as executable specifications: they define the agent's mandate, scope, and quality criteria. Despite…
WebGIS development requires rigor, yet agentic AI frequently fails due to five large language model (LLM) limitations: context constraints, cross-session forgetting, stochasticity, instruction failure, and adaptation rigidity. We propose a…
Evaluating Large Language Models (LLMs) on repository-level feature implementation is a critical frontier in software engineering. However, establishing a benchmark that faithfully mirrors realistic development scenarios remains a…
Automated essay scoring (AES) systems increasingly rely on large language models, yet little is known about how architectural choices shape their performance across different essay quality levels. This paper evaluates single-agent and…