English
Related papers

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

200 papers

Agentic AI systems, specifically LLM-driven agents that plan, invoke tools, maintain persistent memory, and delegate tasks to peer agents via protocols such as MCP and A2A, introduce a threat surface that differs materially from standalone…

Cryptography and Security · Computer Science 2026-05-08 Javad Forough , Marios Kogias , Hamed Haddadi

We investigate whether giving LLM agents the collaborative tools and autonomy that humans naturally use for problem solving can improve their performance. We equip Claude Code agents with MCP-based social media and journaling tools and…

Artificial Intelligence · Computer Science 2025-09-18 Harper Reed , Michael Sugimura , Angelo Zangari

World models - learned internal simulators of environment dynamics - are rapidly becoming foundational to autonomous decision-making in robotics, autonomous vehicles, and agentic AI. By predicting future states in compressed latent spaces,…

Cryptography and Security · Computer Science 2026-04-08 Manoj Parmar

Frontline humanitarian negotiators are increasingly exploring ways to use AI tools in their workflows. However, current AI-tools in negotiation primarily focus on outcomes, neglecting crucial aspects of the negotiation process. Through…

Human-Computer Interaction · Computer Science 2024-10-15 ZIlin Ma , Yiyang Mei , Claude Bruderlein , Krzysztof Z. Gajos , Weiwei Pan

When inferring the goals that others are trying to achieve, people intuitively understand that others might make mistakes along the way. This is crucial for activities such as teaching, offering assistance, and deciding between blame or…

Artificial Intelligence · Computer Science 2021-06-28 Arwa Alanqary , Gloria Z. Lin , Joie Le , Tan Zhi-Xuan , Vikash K. Mansinghka , Joshua B. Tenenbaum

Large Language Models (LLMs) increasingly use persistent memory from past interactions to enhance personalization and task performance. However, this memory introduces critical risks when sensitive information is revealed in inappropriate…

A central goal of LLM alignment is to balance helpfulness with harmlessness, yet these objectives conflict when the same knowledge serves both legitimate and malicious purposes. This tension is amplified by context-sensitive alignment: we…

Cryptography and Security · Computer Science 2026-04-20 Ki Sen Hung , Xi Yang , Chang Liu , Haoran Li , Kejiang Chen , Changxuan Fan , Tsun On Kwok , Weiming Zhang , Xiaomeng Li , Yangqiu Song

We consider the problem of object goal navigation in unseen environments. Solving this problem requires learning of contextual semantic priors, a challenging endeavour given the spatial and semantic variability of indoor environments.…

Computer Vision and Pattern Recognition · Computer Science 2022-03-10 Georgios Georgakis , Bernadette Bucher , Karl Schmeckpeper , Siddharth Singh , Kostas Daniilidis

We aim to better understand the emergence of `situational awareness' in large language models (LLMs). A model is situationally aware if it's aware that it's a model and can recognize whether it's currently in testing or deployment. Today's…

Computation and Language · Computer Science 2023-09-06 Lukas Berglund , Asa Cooper Stickland , Mikita Balesni , Max Kaufmann , Meg Tong , Tomasz Korbak , Daniel Kokotajlo , Owain Evans

Large language models (LLM) are perceived to offer promising potentials for automating security tasks, such as those found in security operation centers (SOCs). As a first step towards evaluating this perceived potential, we investigate the…

Cryptography and Security · Computer Science 2024-02-01 Kumar Shashwat , Francis Hahn , Xinming Ou , Dmitry Goldgof , Lawrence Hall , Jay Ligatti , S. Raj Rajgopalan , Armin Ziaie Tabari

AI agents have become surprisingly proficient at software engineering over the past year, largely due to improvements in reasoning capabilities. This raises a deeper question: can these systems extend their capabilities to automate AI…

Software Engineering · Computer Science 2026-03-11 Ben Rank , Hardik Bhatnagar , Ameya Prabhu , Shira Eisenberg , Karina Nguyen , Matthias Bethge , Maksym Andriushchenko

Can language models (LMs) self-refine their own responses? This question is increasingly relevant as a wide range of real-world user interactions involve refinement requests. However, prior studies have largely tested LMs' refinement…

Computation and Language · Computer Science 2025-12-01 Young-Jun Lee , Seungone Kim , Byung-Kwan Lee , Minkyeong Moon , Yechan Hwang , Jong Myoung Kim , Graham Neubig , Sean Welleck , Ho-Jin Choi

As large language models (LLMs) are increasingly deployed as autonomous agents, understanding how strategic behavior emerges in multi-agent environments has become an important alignment challenge. We take a neutral empirical stance and…

Autonomous planning has been an ongoing pursuit since the inception of artificial intelligence. Based on curated problem solvers, early planning agents could deliver precise solutions for specific tasks but lacked generalization. The…

Artificial Intelligence · Computer Science 2024-10-17 Jian Xie , Kexun Zhang , Jiangjie Chen , Siyu Yuan , Kai Zhang , Yikai Zhang , Lei Li , Yanghua Xiao

Large language models (LLMs) can autonomously conduct multi-stage cyber attacks, but the consistency of their offensive behavior under repeated trials remains unstudied. This work presents the first large-scale empirical measurement of LLM…

Cryptography and Security · Computer Science 2026-05-29 Galip Tolga Erdem

We study behavioral self-awareness -- an LLM's ability to articulate its behaviors without requiring in-context examples. We finetune LLMs on datasets that exhibit particular behaviors, such as (a) making high-risk economic decisions, and…

Computation and Language · Computer Science 2025-01-22 Jan Betley , Xuchan Bao , Martín Soto , Anna Sztyber-Betley , James Chua , Owain Evans

AI agents -- systems that combine foundation models with reasoning, planning, memory, and tool use -- are rapidly becoming a practical interface between natural-language intent and real-world computation. This survey synthesizes the…

Artificial Intelligence · Computer Science 2026-01-06 Bin Xu

Modern large language models (LLMs) have demonstrated impressive performance across a wide range of multi-step reasoning tasks. Recent work suggests that LLMs may perform planning - selecting a future target token in advance and generating…

Computation and Language · Computer Science 2025-08-26 Jatin Nainani , Sankaran Vaidyanathan , Connor Watts , Andre N. Assis , Alice Rigg

Foundation models, such as large language models (LLMs), have been widely recognised as transformative AI technologies due to their capabilities to understand and generate content, including plans with reasoning capabilities. Foundation…

Artificial Intelligence · Computer Science 2024-04-04 Qinghua Lu , Liming Zhu , Xiwei Xu , Zhenchang Xing , Stefan Harrer , Jon Whittle

As artificial intelligence scales, the concepts of alignment, agency, and autonomy have become central to AI safety, governance, and control. However, even in human contexts, these terms lack universal definitions, varying across…

Computers and Society · Computer Science 2025-03-11 Krti Tallam