相关论文: A Sober Look at Agentic Misalignment in Automated …

This paper aims to improve the explainability of Autoencoder's (AE) predictions by proposing two explanation methods based on the mean and epistemic uncertainty of log-likelihood estimate, which naturally arise from the probabilistic…

We propose a minimal agentic baseline that enables systematic comparison across different AI-based theorem prover architectures. This design implements the core features shared among state-of-the-art systems: iterative proof refinement,…

This article develops the concept of the agentic economy and diagnoses its measurable preconditions: a transition in which economic action is increasingly distributed among humans, AI agents, industrial robots, executable protocols, compute…

We develop a theory of intelligent agency grounded in probabilistic modeling for neural models. Agents are represented as outcome distributions with epistemic utility given by log score, and compositions are defined through weighted…

This paper introduces a methodology based on agentic workflows for economic research that leverages Large Language Models (LLMs) and multimodal AI to enhance research efficiency and reproducibility. Our approach features autonomous and…

The increasing prevalence of artificial agents creates a correspondingly increasing need to manage disagreements between humans and artificial agents, as well as between artificial agents themselves. Considering this larger space of…

When should we delegate decisions to AI systems? While the value alignment literature has developed techniques for shaping AI values, less attention has been paid to how to determine, under uncertainty, when imperfect alignment is good…

Given that AI systems are set to play a pivotal role in future decision-making processes, their trustworthiness and reliability are of critical concern. Due to their scale and complexity, modern AI systems resist direct interpretation, and…

Multi-Agent Systems (MAS) built on Large Language Models (LLMs) often exhibit high variance in their reasoning trajectories. Process verification, which evaluates intermediate steps in trajectories, has shown promise in general reasoning…

Agentic AI shifts LLM serving from isolated prompt-generation requests to stateful, multi-turn executions that repeatedly invoke the model, call tools, and grow context over time. This paper characterizes ReAct-style agents from both the…

The present approach highlights the synergies between application integration and interaction protocols. Since both fields have advanced in different directions, a number of important technical problems can be addressed by their proper…

LLM-powered Multi-Agent Systems (MAS) have demonstrated remarkable capabilities in complex domains but suffer from inherent fragility and opaque failure mechanisms. Existing failure attribution methods, whether relying on direct prompting,…

Agentic large language model systems have demonstrated strong capabilities. However, their reliance on language as the universal interface fundamentally limits their applicability to many real-world problems, especially in scientific…

Frontier AI systems are rapidly advancing in their capabilities to persuade, deceive, and influence human behaviour, with current models already demonstrating human-level persuasion and strategic deception in specific contexts. Humans are…

Large language model (LLM) applications such as agents and domain-specific reasoning increasingly rely on context adaptation: modifying inputs with instructions, strategies, or evidence, rather than weight updates. Prior approaches improve…

As large language models are increasingly deployed as interacting agents in high-stakes decisions, the AI safety community assumes that safety properties of individual models will compose into safe multi-agent behavior. This position paper…

AI systems often rely on two key components: a specified goal or reward function and an optimization algorithm to compute the optimal behavior for that goal. This approach is intended to provide value for a principal: the user on whose…

This paper presents a temporal expression language for monitoring AI agent behavior, enabling systematic error-detection of LLM-based agentic systems that exhibit variable outputs due to stochastic generation processes. Drawing from…

Agentic systems that chain reasoning, tool use, and synthesis into multi-step workflows are entering production, yet prevailing evaluation practices like end-to-end outcome checks and ad-hoc trace inspection systematically mask the…

We propose a multi-agent epistemic logic of asynchronous announcements, where truthful announcements are publicly sent but individually received by agents, and in the order in which they were sent. Additional to epistemic modalities the…