相关论文: LLM Readiness Harness: Evaluation, Observability, …

LASSi is a tool aimed at analyzing application usage and contention caused by use of shared resources (filesystem or network) in a HPC system. LASSi was initially developed to support the ARCHER system where there are large variations in…

Recent autonomous research systems -- AI-Scientist, PaperOrchestra, AutoSOTA, DeepResearch, InternAgent, ResearchAgent and others -- show LLM agents can ideate, run experiments and write papers, but each fixes a particular control-flow…

Deploying large language models (LLMs) in edge-cloud environments requires an efficient routing strategy to balance cost and response quality. Traditional approaches prioritize either human-preference data or accuracy metrics from benchmark…

Current hardware security verification processes predominantly rely on manual threat modeling and test plan generation, which are labor-intensive, error-prone, and struggle to scale with increasing design complexity and evolving attack…

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…

Large Language Models (LLMs) deployed in production environments face a fundamental safety-utility trade-off either a strict filtering mechanisms prevent harmful outputs but often block benign queries or a relaxed controls risk unsafe…

The development and deployment of machine learning (ML) systems can be executed easily with modern tools, but the process is typically rushed and means-to-an-end. The lack of diligence can lead to technical debt, scope creep and misaligned…

As LLMs increasingly impact safety-critical applications, ensuring their safety using guardrails remains a key challenge. This paper proposes GuardReasoner, a new safeguard for LLMs, by guiding the guard model to learn to reason.…

Stateful tool-using LLM agents treat the context window as working memory, yet today's agent harnesses manage residency and durability as best-effort, causing recurring failures: lost state after compaction, bypassed flushes on reset, and…

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,…

LLM-based web agents have recently made significant progress, but much of it has occurred in closed-source systems, widening the gap with open-source alternatives. Progress has been held back by two key challenges: first, a narrow focus on…

General aviation fault diagnosis and efficient maintenance are critical to flight safety; however, deploying deep learning models on resource-constrained edge devices poses dual challenges in computational capacity and interpretability.…

General-purpose agents perform tasks in unfamiliar environments without domain-specific manual customization. Yet no study has systematically measured how agent architecture shapes performance across heterogeneous protocols and diverse…

Credible safety plans for advanced AI development require methods to verify agent behavior and detect potential control deficiencies early. A fundamental aspect is ensuring agents adhere to safety-critical principles, especially when these…

As the number of connected IoT devices continues to grow, securing these systems against cyber threats remains a major challenge, especially in environments with limited computational and energy resources. This paper presents an…

Retrieval-Augmented Generation (RAG) has advanced significantly in recent years. The complexity of RAG systems, which involve multiple components-such as indexing, retrieval, and generation-along with numerous other parameters, poses…

This technical report accompanies the LLM robustness leaderboard published by PRISM Eval for the Paris AI Action Summit. We introduce PRISM Eval Behavior Elicitation Tool (BET), an AI system performing automated red-teaming through Dynamic…

HTML observations in LLM-based web agents are extremely long, and while many reduction methods have been proposed, it remains unclear which methods reduce overall agent latency while maintaining performance. The main obstacle is the high…

Recent large language models (LLMs) have demonstrated strong capabilities in understanding and generating code, from competitive programming to repository-level software engineering. In emerging agentic systems, code is no longer only a…

An ever shorter technology lifecycle engendered the need for assessing new technologies w.r.t. their market readiness. Knowing the Technology readiness level (TRL) of a given target technology proved to be useful to mitigate risks such as…