Related papers: Frontier Models are Capable of In-context Scheming

Evaluating the safety of frontier AI systems is an increasingly important concern, helping to measure the capabilities of such models and identify risks before deployment. However, it has been recognised that if AI agents are aware that…

Successful self-replication under no human assistance is the essential step for AI to outsmart the human beings, and is an early signal for rogue AIs. That is why self-replication is widely recognized as one of the few red line risks of…

With the development of artificial intelligence and breakthroughs in deep learning, large-scale Foundation Models (FMs), such as GPT, Sora, etc., have achieved remarkable results in many fields including natural language processing and…

Large Language Models (LLMs) often struggle with complex multi-step planning tasks, showing high rates of constraint violations and inconsistent solutions. Existing strategies such as Chain-of-Thought and ReAct rely on implicit state…

Advanced AI models hold the promise of tremendous benefits for humanity, but society needs to proactively manage the accompanying risks. In this paper, we focus on what we term "frontier AI" models: highly capable foundation models that…

AI research often emphasizes model design and algorithmic performance, while deployment and inference remain comparatively underexplored despite being critical for real-world use. This study addresses that gap by investigating the…

This memorandum presents four recommendations aimed at strengthening the principles of AI model reliability and AI model governability, as DoW, ODNI, NIST, and CAISI refine AI assurance frameworks under the AI Action Plan. Our focus…

Recent advances in large language models (LLMs) have significantly impacted data science workflows, giving rise to specialized data science agents designed to automate analytical tasks. Despite rapid adoption, systematic benchmarks…

Symbolic planners can discover a sequence of actions from initial to goal states given expert-defined, domain-specific logical action semantics. Large Language Models (LLMs) can directly generate such sequences, but limitations in reasoning…

The ability to plan a course of action that achieves a desired state of affairs has long been considered a core competence of intelligent agents and has been an integral part of AI research since its inception. With the advent of large…

Alignment faking is a form of strategic deception in AI in which models selectively comply with training objectives when they infer that they are in training, while preserving different behavior outside training. The phenomenon was first…

Real-world requests to AI agents are fundamentally underspecified. Natural human communication relies on shared context and unstated constraints that speakers expect listeners to infer. Current agentic benchmarks test explicit…

With the rapid progress of Large Language Models (LLMs), it becomes increasingly important to understand their abilities and limitations. In two experiments, we investigate the causal and compositional reasoning abilities of LLMs and humans…

Large Language Models (LLMs) have demonstrated remarkable proficiency in code generation and general reasoning, yet their capacity for autonomous multi-stage planning in high-dimensional, physically constrained environments remains an open…

Designing autonomous drone swarms is hampered by a vast design space spanning platform, algorithmic, and numerical-strength choices. We perform large-scale agent-based simulations in three canonical scenarios: swarm-on-swarm battle,…

When an LLM-based embodied agent fails at a household task, the culprit could be misidentified objects, forgotten sub-goals, or poor action sequencing -- yet existing benchmarks report only a single success rate, making it impossible to…

We introduce Meta MLGym and MLGym-Bench, a new framework and benchmark for evaluating and developing LLM agents on AI research tasks. This is the first Gym environment for machine learning (ML) tasks, enabling research on reinforcement…

Large language models (LLMs) can internally distinguish between evaluation and deployment contexts, a behaviour known as \emph{evaluation awareness}. This undermines AI safety evaluations, as models may conceal dangerous capabilities during…

Foundation model-enabled generative artificial intelligence facilitates the development and implementation of agents, which can leverage distinguished reasoning and language processing capabilities to takes a proactive, autonomous role to…

Reasoning is a fundamental cognitive process underlying inference, problem-solving, and decision-making. While large language models (LLMs) demonstrate strong reasoning capabilities in closed-world settings, they struggle in open-ended and…