Instant research discovery
Search and browse arXiv CS/AI/ML papers, enriched with AI-generated insights.
Generate novel research ideas grounded in real arXiv papers with Brainstorm.
PreviousNext
| Paper | Published | Area | Tags | Intel | Citations |
|---|---|---|---|---|---|
Search and browse arXiv CS/AI/ML papers, enriched with AI-generated insights.
Generate novel research ideas grounded in real arXiv papers with Brainstorm.
| Paper | Published | Area | Tags | Intel | Citations |
|---|---|---|---|---|---|
Search and browse arXiv CS/AI/ML papers, enriched with AI-generated insights.
Generate novel research ideas grounded in real arXiv papers with Brainstorm.
| Paper | Published | Area | Tags | Intel | Citations |
|---|---|---|---|---|---|
Showing 1-30 of 46 papers (page 1 of 2)路 125 ms
| Paper | Published | Area | Tags | Intel | Citations |
|---|---|---|---|---|---|
| Why LLM Agents Favor Their Group: Stakes, Observed Norms, and Reputation Yujiao Chen Published: 2026-10-07Area: physics.soc-phCitations: - Tags: ai-safety, physicssoc-ph, preprint | 2026-10-07 | physics.soc-ph | ai-safety, physicssoc-ph, preprint | E9 / R6 (91%) | - |
| Performance of Zero-determinant Strategies in Repeated Games without Discounting Masahiko Ueda Published: 2026-10-02Area: physics.soc-phCitations: 25 Tags: ai-safety, physicssoc-ph, preprint | 2026-10-02 | physics.soc-ph | ai-safety, physicssoc-ph, preprint | E8 / R6 (92%) | 25 |
| An LLM-powered Agent Framework for Heterogeneous Evacuation Behavior Modeling under a Moving Threat in a Public Plaza Jian Ma, Runxin Yu, Tianyu Tang, Xiaolian Li Published: 2026-09-29Area: physics.soc-phCitations: - Tags: ai-safety, physicssoc-ph, preprint | 2026-09-29 | physics.soc-ph | ai-safety, physicssoc-ph, preprint | E17 / R9 (95%) | - |
| Multi-agent discussion gains less when dissent is withheld Bryan Acton, Chand Sahil Mansuri, Dhaval Patel, Mengying Li Published: 2026-09-29Area: physics.soc-phCitations: - Tags: ai-safety, physicssoc-ph, preprint | 2026-09-29 | physics.soc-ph | ai-safety, physicssoc-ph, preprint | E9 / R6 (91%) | - |
| Hybrid epidemic simulation framework coupling equation-based and individual-based models Chin Chun Ooi, Jaeyoung Kwak, Michael H. Lees, Wentong Cai Published: 2026-09-28Area: physics.soc-phCitations: - Tags: ai-safety, physicssoc-ph, preprint | 2026-09-28 | physics.soc-ph | ai-safety, physicssoc-ph, preprint | E9 / R8 (92%) | - |
| Warned alike, AI agents avoid the less-crowded road while people take it Katsuhiro Nishinari, Naoto Imura, Takahiro Ezaki Published: 2026-09-25Area: physics.soc-phCitations: - Tags: ai-safety, physicssoc-ph, preprint | 2026-09-25 | physics.soc-ph | ai-safety, physicssoc-ph, preprint | E9 / R7 (94%) | - |
| Mitigating Disease Spread by Design in Refugee and IDP Camps Frank Krauss, Giulia Zarpellon, Joseph Aylett-Bullock, Miguel Luengo-Oroz Published: 2026-09-04Area: physics.soc-phCitations: 12 Tags: ai-safety, physicssoc-ph, preprint | 2026-09-04 | physics.soc-ph | ai-safety, physicssoc-ph, preprint | E8 / R7 (93%) | 12 |
| WolfSociety: Understanding Collective Risk from Harmful-Agent Scaling in Financial Agent Societies Lejun Zhang, Muning Wen, Sarah Lu-Liang, Shangding Gu Published: 2026-09-04Area: physics.soc-phCitations: - Tags: ai-safety, physicssoc-ph, preprint | 2026-09-04 | physics.soc-ph | ai-safety, physicssoc-ph, preprint | E9 / R6 (95%) | - |
| How Fast Do Agents Rot? An Empirical Study of Long-Horizon Degradation in LLM Agents for Production Decision-Making Shubhra Mittal Published: 2026-08-31Area: physics.soc-phCitations: - Tags: ai-safety, physicssoc-ph, preprint | 2026-08-31 | physics.soc-ph | ai-safety, physicssoc-ph, preprint | E12 / R7 (93%) | - |
| Rock, Paper, Scissors, ... Dynamite - A Model of Disruption from New Technologies Andrew J. Lohn Published: 2026-08-31Area: physics.soc-phCitations: - Tags: ai-safety, physicssoc-ph, preprint | 2026-08-31 | physics.soc-ph | ai-safety, physicssoc-ph, preprint | E6 / R6 (91%) | - |
| Integrating adaptive human behavior into epidemic models with large language models Haoyang Li, Hongru Du, Rob Deardon, Yicheng Mao Published: 2026-08-30Area: physics.soc-phCitations: - Tags: ai-safety, physicssoc-ph, preprint | 2026-08-30 | physics.soc-ph | ai-safety, physicssoc-ph, preprint | - | - |
| Measurement Validity in LLM Cultural Alignment An Duy Nguyen, Muhammad Aurangzeb Ahmad Published: 2026-08-29Area: physics.soc-phCitations: 15 Tags: ai-safety, alignment-training, physicssoc-ph, preprint | 2026-08-29 | physics.soc-ph | ai-safety, alignment-training, physicssoc-ph, preprint | E8 / R6 (94%) | 15 |
| Sustained Heterogeneity: an emergent collective mechanism in LLM-driven traffic Yangyang Guan, Yujun Qi Published: 2026-08-29Area: physics.soc-phCitations: 27 Tags: ai-safety, physicssoc-ph, preprint | 2026-08-29 | physics.soc-ph | ai-safety, physicssoc-ph, preprint | E7 / R6 (90%) | 27 |
| Prompt Sensitivity of Generative Agents: Evidence from an Epidemic Model Niyousha Hosseinichimeh, Ross Williams Published: 2026-08-26Area: physics.soc-phCitations: 26 Tags: ai-safety, physicssoc-ph, preprint | 2026-08-26 | physics.soc-ph | ai-safety, physicssoc-ph, preprint | E9 / R7 (94%) | 26 |
| Why fragmented parliaments stop passing legislation: Opposition discipline and representation across four democratic institutions Fuad Ali Published: 2026-08-25Area: physics.soc-phCitations: - Tags: ai-safety, physicssoc-ph, preprint | 2026-08-25 | physics.soc-ph | ai-safety, physicssoc-ph, preprint | E12 / R7 (95%) | - |
| Growth Without Us: Machine Consumers, Corporate Circularity, and the Decoupling of GDP from Humanity after AGI Sahil Sharma Published: 2026-08-20Area: physics.soc-phCitations: - Tags: ai-safety, physicssoc-ph, preprint | 2026-08-20 | physics.soc-ph | ai-safety, physicssoc-ph, preprint | E9 / R10 (94%) | - |
| Peer-Voted LLM-Agent Stress Tests Find Feed-Induced Lexical Convergence but No Reliable Matched-Exposure Advantage for Distributed Sources Dominic Williamson, Rana Muhammad Usman Published: 2026-08-20Area: physics.soc-phCitations: 12 Tags: ai-safety, physicssoc-ph, preprint | 2026-08-20 | physics.soc-ph | ai-safety, physicssoc-ph, preprint | E14 / R10 (94%) | 12 |
| Coordinated incentives in AI-generated misinformation governance Attila Szolnoki, Gui Zhang, Matjaz Perc, Minyu Feng Published: 2026-08-07Area: physics.soc-phCitations: - Tags: ai-safety, physicssoc-ph, preprint | 2026-08-07 | physics.soc-ph | ai-safety, physicssoc-ph, preprint | E7 / R7 (93%) | - |
| Coordinated incentives in AI-generated misinformation governance Attila Szolnoki, Gui Zhang, Matjaz Perc, Minyu Feng Published: 2026-08-07Area: physics.soc-phCitations: - Tags: ai-safety, physicssoc-ph, preprint | 2026-08-07 | physics.soc-ph | ai-safety, physicssoc-ph, preprint | E8 / R6 (93%) | - |
| Same physical state, different collective dynamics: state encodings select synchronization outcomes in language-model agents Katsuhiro Nishinari, Naoto Imura, Takahiro Ezaki Published: 2026-08-07Area: physics.soc-phCitations: - Tags: ai-safety, physicssoc-ph, preprint | 2026-08-07 | physics.soc-ph | ai-safety, physicssoc-ph, preprint | E8 / R6 (92%) | - |
| Microscopic dynamics of consensus formation in multi-agent LLM Naming Games Alessandro Codello, Cristiano De Nobili, Raffaella Burioni, Vijayasri Iyer Published: 2026-08-03Area: physics.soc-phCitations: 28 Tags: ai-safety, physicssoc-ph, preprint | 2026-08-03 | physics.soc-ph | ai-safety, physicssoc-ph, preprint | E10 / R7 (90%) | 28 |
| Temperature-driven inversion and nonlinear dynamics in ChatGPT-like AIs Bella Xinrui Li, Frank Yingjie Huo, Neil F. Johnson Published: 2026-08-02Area: physics.soc-phCitations: - Tags: ai-safety, physicssoc-ph, preprint | 2026-08-02 | physics.soc-ph | ai-safety, physicssoc-ph, preprint | - | - |
| Teacher Knows It Best: Spontaneous Symmetry Breaking and Tipping Points in Networked Langevin Dynamics AI Sycophancy Partha Pratim Chakrabarti, Saumik Bhattacharya, Sayantari Ghosh Published: 2026-07-27Area: physics.soc-phCitations: - Tags: ai-safety, physicssoc-ph, preprint | 2026-07-27 | physics.soc-ph | ai-safety, physicssoc-ph, preprint | - | - |
| When Shippers Become Algorithms: Candidate Exposure, Information Design, and the Concentration of LLM-Mediated Freight Markets Katsuhiro Nishinari, Naoto Imura, Takahiro Ezaki Published: 2026-07-22Area: physics.soc-phCitations: 15 Tags: ai-safety, physicssoc-ph, preprint | 2026-07-22 | physics.soc-ph | ai-safety, physicssoc-ph, preprint | E10 / R6 (91%) | 15 |
| Temporal-Causal Unity as an Operational Framework for Collective Dynamics: Causal-Progress Clocks, Synchronization, and Polarization Dong Sun, Jian Liu Published: 2026-07-21Area: physics.soc-phCitations: 1 Tags: ai-safety, physicssoc-ph, preprint | 2026-07-21 | physics.soc-ph | ai-safety, physicssoc-ph, preprint | E8 / R6 (90%) | 1 |
| Alignment of a Total Automation Economy David McAllester Published: 2026-07-19Area: physics.soc-phCitations: 5 Tags: ai-safety, alignment-training, physicssoc-ph, preprint | 2026-07-19 | physics.soc-ph | ai-safety, alignment-training, physicssoc-ph, preprint | E7 / R5 (91%) | 5 |
| Alignment of a Total Automation Economy David McAllester Published: 2026-07-19Area: physics.soc-phCitations: 5 Tags: ai-safety, alignment-training, physicssoc-ph, preprint | 2026-07-19 | physics.soc-ph | ai-safety, alignment-training, physicssoc-ph, preprint | E16 / R15 (91%) | 5 |
| Distribution-First Population Simulation: Collapse, Calibration, and Recall in Non-WEIRD LLM Persona Modeling Gurkan Ozkan Published: 2026-07-17Area: physics.soc-phCitations: 33 Tags: ai-safety, physicssoc-ph, preprint | 2026-07-17 | physics.soc-ph | ai-safety, physicssoc-ph, preprint | E9 / R8 (90%) | 33 |
| Sociocultural Influences on Opinion Formation: Word of Mouth Dynamics, Mass Media and Behavioural Development Elpida Tzafestas Published: 2026-07-17Area: physics.soc-phCitations: - Tags: ai-safety, physicssoc-ph, preprint | 2026-07-17 | physics.soc-ph | ai-safety, physicssoc-ph, preprint | E7 / R6 (88%) | - |
| Self-Reference in Large Language Models: The Introspection Threshold for Recursive Self-Improvement Bing Yuan, Jiang Zhang, Qian Zhang Published: 2026-07-05Area: physics.soc-phCitations: - Tags: ai-safety, physicssoc-ph, preprint | 2026-07-05 | physics.soc-ph | ai-safety, physicssoc-ph, preprint | E10 / R8 (93%) | - |