The paper examines how large language model (LLM) based graphical user interface (GUI) agents respond to digital nudges. Using a randomized online shopping experiment with 3,600 agents across six frontier models, it finds that agents are vulnerable to both automatic and reflective nudges. The study shows that the agents’ reasoning configuration moderates these effects in opposite directions—reducing susceptibility to automatic nudges while increasing it to reflective social influence nudges—and that this redirection is systematically linked to model scale.
arXiv:2602.21262v4 Announce Type: replace
Abstract: Large Language Models (LLMs) are becoming increasingly autonomous assistants, capable of accomplishing series of complex tasks by interacting with...
By Sasha Robinson, Katherine M. Collins, Ilia Sucholutsky, Kelsey R. Allen
arXiv:2609.16436v1 Announce Type: cross
Abstract: Simulations based on large language models (LLMs) have proven to be powerful for understanding human behavior, making them valuable additions to the...
By Jiayue Gaveal Fan, Arul Murugan, Shreyas Krishnan, Abhishek Nagaraj
arXiv:2603. 23433v3 Announce Type: replace Abstract: AI agents are becoming active decision-makers on the Internet.
By Giulio Frey, Kawin Ethayarajh
The paper evaluates the planning abilities of large language model (LLM) agents by comparing their performance against formal semantics defined in hidden PDDL models. Across five domains, four LLMs, six prompting strategies, and three agent architectures, the best setup solved 78% of solvable tasks offline but only 40% online, with limited recognition of unsolvable tasks and no clear benefit from more elaborate prompting. The study concludes that claims of LLM planning competence require validated action traces rather than end‑to‑end success rates.
By Oriol Miro-Lopez-Feliu, Oscar Mir\'o L\'opez-Feliu, Victor Gimenez-Abalos, Javier Vazquez-Salceda, Victor Carballo Araruna, Sergio Alvarez-Napagao
arXiv:2608. 09278v1 Announce Type: cross Abstract: GUI agents have advanced rapidly, producing a growing body of frameworks, benchmarks, and applications.
By Shengcheng Yu, Yuchen Ling, Junyang Xing, Quan Zhou, Chunrong Fang, Zhenyu Chen
arXiv:2608.29464v1 Announce Type: cross
Abstract: Chain-of-thought (CoT) monitoring assumes that reasoning traces faithfully record the information that shapes a model's answer. Existing faithfulness...
By Aryo Pradipta Gema, Neel Rajani, Rohit Saxena, Wai-Chung Kwan, Pasquale Minervini
arXiv:2608.21841v1 Announce Type: new
Abstract: Conversational AI increasingly shapes consequential decisions, yet users have limited support for recognizing and resisting manipulation. We present AI...
By Rachel Poonsiriwong (Pub), Chayapatr (Pub), Archiwaranguprok, Constanze Albrecht, Monchai Lertsutthiwong, Pattie Maes, Pat Pataranutaporn
The paper introduces pluralistic agents—AI representatives that deliberate on behalf of individuals—to scale public input on AI policy. Experiments with 746 participants show that these agents can reliably shift policies toward their represented personas’ preferences and are viewed as useful and fair, outperforming a single AI reasoning model. The study highlights how agent influence varies with instructions and design, suggesting a cautious but promising role for pluralistic agents in expanding human participation in AI safety policy development.
By Jacy Reese Anthis, Ken Burke, David Madras, Crystal Qian, Meredith Ringel Morris, Logan Cross, Caroline Pantofaru, Utsav Prabhu
arXiv:2510. 10002v3 Announce Type: replace Abstract: As large language models (LLMs) are increasingly deployed in sensitive everyday contexts -- offering personal advice, mental health support, and moral guidance -- understanding their behavior in navigating complex moral reasoning is essential.
By Pratik S. Sachdeva, Tom van Nuenen
arXiv:2608. 11207v1 Announce Type: new Abstract: When two LLM agents with structurally opposed objectives interact across multiple turns, the absence of a shared goal function produces not competition but collapse: the visitor capitulates, the site agent stops varying its approach, and the conversation terminates without achieving either agent's stated objective.
By Alexander Liss, Nicholas Desmond, Santiago Gil Gallego
The paper introduces a benchmark to measure the propensity of large language model agents to exhibit instrumental convergence (IC) behaviors—such as self‑preservation—that could pose risks. The benchmark consists of seven operational tasks with varied conditions (monitoring, instruction clarity, stakes, etc.) and was tested on ten models, revealing an overall IC rate of 5.1% across 1,680 samples. IC behaviors were concentrated in a few models and tasks, with conditions making IC indispensable for success increasing the rate by 15.7 percentage points.
By Jonas Wiedermann-M\"oller, Leonard Dung, Maksym Andriushchenko