English
Related papers

Related papers: Harness Engineering as Categorical Architecture

200 papers

Modern Large Language Model (LLM) systems are assembled from third-party artifacts such as pre-trained weights, fine-tuning adapters, datasets, dependency packages, and container images, fetched through automated pipelines. This speed comes…

Cryptography and Security · Computer Science 2026-04-01 Zhuoran Tan , Jeremy Singer , Christos Anagnostopoulos

Building and evaluating enterprise AI systems requires synthetic organizational corpora that are internally consistent, temporally structured, and cross-artifact traceable. Existing corpora either carry legal constraints or inherit…

Computation and Language · Computer Science 2026-04-10 Jeffrey Flynt

Precision process planning in Computer Numerical Control (CNC) machining demands rapid, context-aware decisions on tool selection, feed-speed pairs, and multi-axis routing, placing immense cognitive and procedural burdens on engineers from…

Artificial Intelligence · Computer Science 2025-06-17 Danny Hoang , David Gorsich , Matthew P. Castanier , Farhad Imani

We present a framework for verifying the deterministic structured computations surrounding a large language model rather than the model itself, extending a Lean 4 trust-boundary architecture to the generic interfaces of modern LLM…

Logic in Computer Science · Computer Science 2026-05-19 George Koomullil

We present a readiness harness for LLM and RAG applications that turns evaluation into a deployment decision workflow. The system combines automated benchmarks, OpenTelemetry observability, and CI quality gates under a minimal API contract,…

Artificial Intelligence · Computer Science 2026-05-22 Alexandre Cristovão Maiorano

This position paper argues that enforcing LLM agent safety within a single abstraction layer is not merely suboptimal but categorically insufficient for deployed LLM agents -- a structural consequence of how agent execution works, not a…

Artificial Intelligence · Computer Science 2026-05-19 S. Bensalem , Y. Dong , M. Franzle , X. Huang , J. Kroger , D. Nickovic , A. Nouri , R. Roy , C. Wu

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…

Artificial Intelligence · Computer Science 2026-03-05 Boyuan , Guan , Wencong Cui , Levente Juhasz

Large language models excel on objectively verifiable tasks such as math and programming, where evaluation reduces to unit tests or a single correct answer. In contrast, real-world enterprise work is often subjective and context-dependent:…

Artificial Intelligence · Computer Science 2026-03-25 Abhishek Chandwani , Ishan Gupta

LLM-based multi-agent systems (MAS) have emerged as a promising approach to tackle complex tasks that are difficult for individual LLMs. A natural strategy is to scale performance by increasing the number of agents; however, we find that…

Artificial Intelligence · Computer Science 2026-02-04 Yingxuan Yang , Chengrui Qu , Muning Wen , Laixi Shi , Ying Wen , Weinan Zhang , Adam Wierman , Shangding Gu

Recent advances in programming languages study and design have established a standard way of grounding computational systems representation in category theory. These formal results led to a better understanding of issues of control and…

Artificial Intelligence · Computer Science 2009-09-29 Jean-Marie Chauvet

The advancement of large language model (LLM) based agents has shifted AI evaluation from single-turn response assessment to multi-step task completion in interactive environments. We present an empirical study evaluating frontier AI models…

Artificial Intelligence · Computer Science 2026-01-15 Logan Ritchie , Sushant Mehta , Nick Heiner , Mason Yu , Edwin Chen

Identifying architecturally relevant entities in textual artifacts is crucial for Traceability Link Recovery (TLR) between Software Architecture Documentation (SAD) and source code. While Software Architecture Models (SAMs) can bridge the…

Software Engineering · Computer Science 2026-04-09 Dominik Fuchß , Haoyu Liu , Sophie Corallo , Tobias Hey , Jan Keim , Johannes von Geisau , Anne Koziolek

AlphaEvolve and FunSearch have demonstrated the potential of combining large language models (LLMs) with evolutionary search for automated algorithm discovery. However, discovery success is shaped not only by model capability but also…

Software Engineering · Computer Science 2026-05-18 Yoichi Ishibashi , Taro Yano , Masafumi Oyamada

Modern LLM-based agents and chat assistants rely on long-term memory frameworks to store reusable knowledge, recall user preferences, and augment reasoning. As researchers create more complex memory architectures, it becomes increasingly…

Machine Learning · Computer Science 2026-05-25 Alina Shutova , Alexandra Olenina , Ivan Vinogradov , Anton Sinitsin

Designing high-performance system heuristics is a creative, iterative process requiring experts to form hypotheses and execute multi-step conceptual shifts. While Large Language Models (LLMs) show promise in automating this loop, they…

Artificial Intelligence · Computer Science 2026-03-24 Pantea Karimi , Kimia Noorbakhsh , Mohammad Alizadeh , Hari Balakrishnan

While Large Language Models (LLMs) have demonstrated potential in healthcare, they often struggle with the complex, non-linear reasoning required for accurate clinical diagnosis. Existing methods typically rely on static, linear mappings…

Computation and Language · Computer Science 2026-05-28 Zhuohan Ge , Haoyang Li , Yubo Wang , Nicole Hu , Chen Jason Zhang , Qing Li

AI agents that interact with the real world through tool calls pose fundamental safety challenges: agents might leak private information, cause unintended side effects, or be manipulated through prompt injection. To address these…

Artificial Intelligence · Computer Science 2026-05-29 Martin Odersky , Yaoyu Zhao , Yichen Xu , Oliver Bračevac , Cao Nguyen Pham

Agent orchestration frameworks have proliferated, collectively exceeding 290,000 GitHub stars across LangGraph, CrewAI, Google ADK, OpenAI Agents SDK, Semantic Kernel, Strands, and LlamaIndex. All follow the same pattern: an external…

Artificial Intelligence · Computer Science 2026-05-22 Simon Dennis , Rivaan Patil , Kevin Shabahang , Hao Guo

Deep Research Agents (DRAs) aim to answer complex questions by searching the web, checking evidence, and synthesizing conclusions across heterogeneous sources. We introduce a category-theoretic framework for evaluating and improving such…

Machine Learning · Computer Science 2026-04-30 Shuoling Liu , Zhiquan Tan , Kun Yi , Hui Wu , Yihan Li , Jiangpeng Yan , Liyuan Chen , Kai Chen , Qiang Yang

Operating LLMs as coordinated multi-agent research systems over multi-hour runs surfaces failure modes that single-shot evaluation cannot: upstream providers throttle without warning, sub-agents drift the task to fit accessible tools,…

Artificial Intelligence · Computer Science 2026-05-26 Sasank Annapureddy
‹ Prev 1 4 5 6 7 8 10 Next ›