English
Related papers

Related papers: Inherited Goal Drift: Contextual Pressure Can Unde…

200 papers

As language models (LMs) are increasingly deployed as autonomous agents, their robust adherence to human-assigned objectives becomes crucial for safe operation. When these agents operate independently for extended periods without human…

Artificial Intelligence · Computer Science 2025-05-06 Rauno Arike , Elizabeth Donoway , Henning Bartsch , Marius Hobbhahn

Large Language Models (LLMs) excel at single-turn tasks such as instruction following and summarization, yet real-world deployments require sustained multi-turn interactions where user goals and conversational context persist and evolve. A…

Computation and Language · Computer Science 2025-11-25 Vardhan Dongre , Ryan A. Rossi , Viet Dac Lai , David Seunghyun Yoon , Dilek Hakkani-Tür , Trung Bui

Emergent multi-agent communication protocols are very different from natural language and not easily interpretable by humans. We find that agents that were initially pretrained to produce natural language can also experience detrimental…

Computation and Language · Computer Science 2019-09-11 Jason Lee , Kyunghyun Cho , Douwe Kiela

Large Language Model agents deployed in complex environments frequently encounter a conflict between maximizing goal achievement and adhering to safety constraints. This paper identifies a new concept called Agentic Pressure, which…

Artificial Intelligence · Computer Science 2026-04-21 Hengle Jiang , Ke Tang

Central to many self-improvement pipelines for large language models (LLMs) is the assumption that models can improve by reflecting on past mistakes. We study a phenomenon termed contextual drag: the presence of failed attempts in the…

Computation and Language · Computer Science 2026-03-04 Yun Cheng , Xingyu Zhu , Haoyu Zhao , Sanjeev Arora

Multi-agent Large Language Model (LLM) systems have emerged as powerful architectures for complex task decomposition and collaborative problem-solving. However, their long-term behavioral stability remains largely unexamined. This study…

Artificial Intelligence · Computer Science 2026-01-08 Abhishek Rath

Classical machine learning algorithms often assume that the data are drawn i.i.d. from a stationary probability distribution. Recently, continual learning emerged as a rapidly growing area of machine learning where this assumption is…

Machine Learning · Computer Science 2022-07-12 Timothée Lesort , Massimo Caccia , Irina Rish

When intelligent agents communicate to accomplish shared goals, how do these goals shape the agents' language? We study the dynamics of learning in latent language policies (LLPs), in which instructor agents generate natural-language…

Computation and Language · Computer Science 2021-04-16 Athul Paul Jacob , Mike Lewis , Jacob Andreas

Coding agents are increasingly deployed autonomously, at scale, and over long-context horizons. To be effective and safe, these agents must navigate complex trade-offs in deployment, balancing influence from the user, their learned values,…

Artificial Intelligence · Computer Science 2026-04-27 Magnus Saebo , Spencer Gibson , Tyler Crosse , Achyutha Menon , Eyon Jang , Diogo Cruz

As frontier language models are increasingly deployed as autonomous agents pursuing complex, long-term objectives, there is increased risk of scheming: agents covertly pursuing misaligned goals. Prior work has focused on showing agents are…

Artificial Intelligence · Computer Science 2026-03-31 Mia Hopman , Jannes Elstner , Maria Avramidou , Amritanshu Prasad , David Lindner

Large language models are increasingly deployed as specialized agents that plan, call tools, and take actions over extended horizons. Yet many existing evaluations assume a "clean interface" where dynamics are specified and stable, tools…

Computation and Language · Computer Science 2026-02-04 Pouya Pezeshkpour , Estevam Hruschka

Recent zero-shot evaluations have highlighted important limitations in the abilities of language models (LMs) to perform meaning extraction. However, it is now well known that LMs can demonstrate radical improvements in the presence of…

Computation and Language · Computer Science 2024-10-18 Kanishka Misra , Allyson Ettinger , Kyle Mahowald

Recently proposed evaluation benchmarks aim to characterize the effective context length and the forgetting tendencies of large language models (LLMs). However, these benchmarks often rely on simplistic 'needle in a haystack' retrieval or…

Computation and Language · Computer Science 2025-10-07 Raquib Bin Yousuf , Aadyant Khatri , Shengzhe Xu , Mandar Sharma , Naren Ramakrishnan

Language models (LMs) are trained on collections of documents, written by individual human agents to achieve specific goals in an outside world. During training, LMs have access only to text of these documents, with no direct evidence of…

Computation and Language · Computer Science 2022-12-06 Jacob Andreas

Data drift is the change in model input data that is one of the key factors leading to machine learning models performance degradation over time. Monitoring drift helps detecting these issues and preventing their harmful consequences.…

Computation and Language · Computer Science 2023-05-30 Ella Rabinovich , Matan Vetzler , Samuel Ackerman , Ateret Anaby-Tavor

Reinforcement learning (RL) agents typically assume stationary environment dynamics. Yet in real-world applications such as healthcare, robotics, and finance, transition probabilities or reward functions may evolve, leading to model drift.…

Machine Learning · Computer Science 2025-09-16 Chang-Hwan Lee , Alexander Shim

Machine Translation (MT) is widely employed to address resource scarcity in low-resource languages by generating synthetic data from high-resource counterparts. While sentiment preservation in translation has long been studied, a critical…

Computation and Language · Computer Science 2026-04-30 Mohsinul Kabir , Tasnim Ahmed , Md Mezbaur Rahman , Polydoros Giannouris , Sophia Ananiadou

A long-standing challenge in Reinforcement Learning is enabling agents to learn a model of their environment which can be transferred to solve other problems in a world with the same underlying rules. One reason this is difficult is the…

Machine Learning · Computer Science 2019-05-16 Kai Olav Ellefsen , Jim Torresen

Modern LLM agents combine long-term memory for personalization with tool-calling interfaces for taking actions in the world -- a combination underpinning contemporary production systems. We study a previously unexamined failure of this…

Cryptography and Security · Computer Science 2026-05-26 Mahavir Dabas , Jihyun Jeong , Ming Jin , Ruoxi Jia

Persistent language-model agents increasingly combine tool use, tiered memory, reflective prompting, and runtime adaptation. In such systems, behavior is shaped not only by current prompts but by mutable internal conditions that influence…

Artificial Intelligence · Computer Science 2026-05-13 Krti Tallam
‹ Prev 1 2 3 10 Next ›