Related papers: When Only the Final Text Survives: Implicit Execut…

Evaluating large language model (LLM)-based multi-agent systems remains a critical challenge, as these systems must exhibit reliable coordination, transparent decision-making, and verifiable performance across evolving tasks. Existing…

The rapid spread of misinformation in the digital era poses significant challenges to public discourse, necessitating robust and scalable fact-checking solutions. Traditional human-led fact-checking methods, while credible, struggle with…

Failure attribution in LLM multi-agent systems-identifying the agent and step responsible for task failures-provides crucial clues for systems debugging but remains underexplored and labor-intensive. In this paper, we propose and formulate…

We study a class of emergent misalignment in multi-agent systems (MAS), with a focus on automated workflows, which we refer to agentic misalignment. Although these systems can solve complex tasks, they often fail because agents act…

Artificial intelligence systems are increasingly integrated into writing processes, challenging traditional notions of authorship, responsibility, and intellectual contribution. Current disclosure practices usually indicate whether AI was…

Agentic computing systems, while immensely capable, raise serious security, privacy, and safety concerns. A key issue is that the full set of functionalities offered by these systems, combined with their probabilistic execution flows, is…

Practitioners are increasingly turning to Extract-Load-Transform (ELT) pipelines with the widespread adoption of cloud data warehouses. However, designing these pipelines often involves significant manual work to ensure correctness. Recent…

This technical white paper introduces the Interactive Agents Call Tree (IACT), a computational model designed to address the limitations of static, hard-coded agent workflows. Unlike traditional systems that require pre-defined graphs or…

Alignment research focuses on making individual AI systems reliable. Human institutions achieve reliable collective behaviour differently: they mitigate the risk posed by misaligned individuals through organisational structure. Multi-agent…

Agentic AI systems plan, use tools, maintain state, and act across multi-step workflows with external effects, meaning trustworthy deployment can no longer be judged by task completion alone. The current literature remains fragmented across…

Existing AI-generated text detection methods heavily depend on large annotated datasets and external threshold tuning, restricting interpretability, adaptability, and zero-shot effectiveness. To address these limitations, we propose…

Evidence plays a crucial role in automated fact-checking. When verifying real-world claims, existing fact-checking systems either assume the evidence sentences are given or use the search snippets returned by the search engine. Such methods…

Intelligent Tutoring Systems have become critically important in future learning environments. Knowledge Tracing (KT) is a crucial part of that system. It is about inferring the skill mastery of students and predicting their performance to…

Reinforcement learning with verifiable rewards has become a common way to improve explicit reasoning in large language models, but final-answer correctness alone does not reveal whether the reasoning trace is faithful, reliable, or useful…

The deployment of autonomous AI agents in Internet of Things (IoT) energy systems requires decision-making mechanisms that remain robust, efficient, and trustworthy under real-time constraints and imperfect monitoring. While reinforcement…

AI coding agents make empirical specification search fast and cheap, but they also widen hidden researcher degrees of freedom. Building on an open-source agent-loop architecture, this paper adapts that framework to an empirical economics…

Attribution of cyber-attacks remains a complex but critical challenge for cyber defenders. Currently, manual extraction of behavioral indicators from dense forensic documentation causes significant attribution delays, especially following…

Natural language processing (NLP) models may leak private information in different ways, including membership inference, reconstruction or attribute inference attacks. Sensitive information may not be explicit in the text, but hidden in…

From disinformation spread by AI chatbots to AI recommendations that inadvertently reinforce stereotypes, textual bias poses a significant challenge to the trustworthiness of large language models (LLMs). In this paper, we propose a…

Automated fact-checking systems often struggle with trustworthiness, as their generated explanations can include hallucinations. In this work, we explore evidence attribution for fact-checking explanation generation. We introduce a novel…