English
Related papers

Related papers: Epistemic Traps: Rational Misalignment Driven by M…

200 papers

An ethical value-action gap exists when there is a discrepancy between intentions and actions. This discrepancy may be caused by social and structural obstacles as well as cognitive biases. Computational models of cognition and affect can…

Artificial Intelligence · Computer Science 2022-02-25 Catriona M. Kennedy

The AI alignment problem, which focusses on ensuring that artificial intelligence (AI), including AGI and ASI, systems act according to human values, presents profound challenges. With the progression from narrow AI to Artificial General…

Artificial Intelligence · Computer Science 2025-07-25 Alberto Hernández-Espinosa , Felipe S. Abrahão , Olaf Witkowski , Hector Zenil

Many applications of intelligent systems require reasoning about the mental states of agents in the domain. We may want to reason about an agent's beliefs, including beliefs about other agents; we may also want to reason about an agent's…

Artificial Intelligence · Computer Science 2013-01-18 Brian Milch , Daphne Koller

Efforts to ensure the safe development of artificial general intelligence (AGI) often rely on consensus-based alignment approaches grounded in axiomatic formalism, interpretability, and empirical validation. However, these methods may be…

Artificial Intelligence · Computer Science 2025-04-04 Andy Williams

With autonomous vehicles (AV) set to integrate further into regular human traffic, there is an increasing consensus on treating AV motion planning as a multi-agent problem. However, the traditional game-theoretic assumption of complete…

Artificial Intelligence · Computer Science 2024-06-06 Atrisha Sarkar , Krzysztof Czarnecki

Emergent Misalignment refers to a failure mode in which fine-tuning large language models (LLMs) on narrowly scoped data induces broadly misaligned behavior. Prior explanations mainly attribute this phenomenon to the generalization of…

Computation and Language · Computer Science 2026-02-02 Yanghao Su , Wenbo Zhou , Tianwei Zhang , Qiu Han , Weiming Zhang , Nenghai Yu , Jie Zhang

When humans are subject to an algorithmic decision system, they can strategically adjust their behavior accordingly (``game'' the system). While a growing line of literature on strategic classification has used game-theoretic modeling to…

Machine Learning · Computer Science 2024-10-28 Raman Ebrahimi , Kristen Vaccaro , Parinaz Naghizadeh

As AI becomes more capable, we entrust it with more general and consequential tasks. The risks from failure grow more severe with increasing task scope. It is therefore important to understand how extremely capable AI models will fail: Will…

Artificial Intelligence · Computer Science 2026-04-13 Alexander Hägele , Aryo Pradipta Gema , Henry Sleight , Ethan Perez , Jascha Sohl-Dickstein

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 · Computer Science 2026-05-26 Wenqian Ye , Bo Yuan , Zhichao Xu , Yijun Tian , Yawei Wang , Henry Kautz , Aidong Zhang

Large language models (LLMs) are increasingly being adopted as the cognitive core of embodied agents. However, inherited hallucinations, which stem from failures to ground user instructions in the observed physical environment, can lead to…

Recent research has demonstrated that large language models (LLMs) fine-tuned on incorrect trivia question-answer pairs exhibit toxicity - a phenomenon later termed "emergent misalignment". Moreover, research has shown that LLMs possess…

Computation and Language · Computer Science 2026-02-17 Laurène Vaugrante , Anietta Weckauff , Thilo Hagendorff

The development of intelligent agents, particularly those powered by language models (LMs), has shown a critical role in various environments that require intelligent and autonomous decision-making. Environments are not passive testing…

Artificial Intelligence · Computer Science 2025-10-21 Antonin Sulc , Thorsten Hellert

As AI systems grow more capable and autonomous, ensuring their safety and reliability requires not only model-level alignment but also strategic oversight of the humans and institutions involved in their development and deployment. Existing…

Artificial Intelligence · Computer Science 2026-02-10 Cheol Woo Kim , Davin Choo , Tzeh Yuan Neoh , Milind Tambe

Existing alignment research is dominated by concerns about safety and preventing harm: safeguards, controllability, and compliance. This paradigm of alignment parallels early psychology's focus on mental illness: necessary but incomplete.…

We study strategic interaction in linear-quadratic network games where agents act on subjective, misspecified models of their environment. Agents observe noisy aggregate signals generated by local network externalities and interpret them…

Computer Science and Game Theory · Computer Science 2026-03-19 Quanyan Zhu , Zhengye Han

Safety benchmark scores provide incomplete evidence of deployment readiness: aligned language models often adhere to rigid rules even when a situational update flips which action is safe. We term this failure brittle safety. To diagnose it,…

Artificial Intelligence · Computer Science 2026-05-28 Dasol Choi , Alex Kwon

Agentic AIs $-$ AIs that are capable and permitted to undertake complex actions with little supervision $-$ mark a new frontier in AI capabilities and raise new questions about how to safely create and align such systems with users,…

Computers and Society · Computer Science 2024-10-04 Hayley Clatterbuck , Clinton Castro , Arvo Muñoz Morán

The advancement of large language model (LLM) based agents has shifted AI evaluation from single-turn response assessment to multi-step task completion in interactive environments. We present an empirical study evaluating frontier AI models…

Artificial Intelligence · Computer Science 2026-01-15 Logan Ritchie , Sushant Mehta , Nick Heiner , Mason Yu , Edwin Chen

Reinforcement learning (RL) plays a crucial role in shaping the behavior of large language and reasoning models (LLMs/LRMs). However, it often produces brittle and unstable policies, leading to critical failures such as spurious reasoning,…

Artificial Intelligence · Computer Science 2025-07-29 Xingcheng Xu

Fine-tuned large language models can exhibit reward-hacking behavior arising from emergent misalignment, which is difficult to detect from final outputs alone. While prior work has studied reward hacking at the level of completed responses,…

Computation and Language · Computer Science 2026-03-05 Patrick Wilhelm , Thorsten Wittkopp , Odej Kao