Image de couverture de livre

Inherent and emergent liability issues in LLM-based agentic systems: a principal-agent perspective

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Gabison, Garry A., Xian, R. Patrick
Format:	Preprint
Publié:	2025
Sujets:	Computers and Society Computation and Language Multiagent Systems
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Reliable agent engineering should integrate machine-compatible organizational principles
par: Xian, R. Patrick, et autres
Publié: (2025)

MultiAgentBench: Evaluating the Collaboration and Competition of LLM agents
par: Zhu, Kunlun, et autres
Publié: (2025)

An agent-based model of modal choice with perception biases and habits
par: Adam, Carole, et autres
Publié: (2024)

LLM-Based Social Simulations Require a Boundary
par: Wu, Zengqing, et autres
Publié: (2025)

Group size effects and collective misalignment in LLM multi-agent systems
par: Flint, Ariel, et autres
Publié: (2025)

Towards Simulating Social Influence Dynamics with LLM-based Multi-agents
par: Lin, Hsien-Tsung, et autres
Publié: (2025)

An agent-based epidemics simulation to compare and explain screening and vaccination prioritisation strategies
par: Adam, Carole, et autres
Publié: (2022)

The emergence of numerical representations in communicating artificial agents
par: Mihai, Daniela, et autres
Publié: (2026)

A survey about perceptions of mobility to inform an agent-based simulator of subjective modal choice
par: Adam, Carole, et autres
Publié: (2025)

Collaborating Action by Action: A Multi-agent LLM Framework for Embodied Reasoning
par: White, Isadora, et autres
Publié: (2025)

Cooperative Profiles Predict Multi-Agent LLM Team Performance in AI for Science Workflows
par: Kumar, Shivani, et autres
Publié: (2026)

Enhancing Value Alignment of LLMs with Multi-agent system and Combinatorial Fusion
par: Wu, Yuanhong, et autres
Publié: (2026)

LLM-Coordination: Evaluating and Analyzing Multi-agent Coordination Abilities in Large Language Models
par: Agashe, Saaket, et autres
Publié: (2023)

Food4All: A Multi-Agent Framework for Real-time Free Food Discovery with Integrated Nutritional Metadata
par: Yuan, Zhengqing, et autres
Publié: (2025)

Reimagining Urban Science: Scaling Causal Inference with Large Language Models
par: Xia, Yutong, et autres
Publié: (2025)

AI Urban Scientist: Multi-Agent Collaborative Automation for Urban Research
par: Xia, Tong, et autres
Publié: (2025)

Emergent Social Intelligence Risks in Generative Multi-Agent Systems
par: Huang, Yue, et autres
Publié: (2026)

Embodied LLM Agents Learn to Cooperate in Organized Teams
par: Guo, Xudong, et autres
Publié: (2024)

Law in Silico: Simulating Legal Society with LLM-Based Agents
par: Wang, Yiding, et autres
Publié: (2025)

Mechanism Plausibility in Generative Agent-Based Modeling
par: Zhao, Patrick, et autres
Publié: (2026)

DECAF: Learning to be Fair in Multi-agent Resource Allocation
par: Kumar, Ashwin, et autres
Publié: (2025)

ColorEcosystem: Powering Personalized, Standardized, and Trustworthy Agentic Service in massive-agent Ecosystem
par: Wu, Fangwen, et autres
Publié: (2025)

Can LLMs Write Faithfully? An Agent-Based Evaluation of LLM-generated Islamic Content
par: Mushtaq, Abdullah, et autres
Publié: (2025)

Social Catalysts, Not Moral Agents: The Illusion of Alignment in LLM Societies
par: Hu, Yueqing, et autres
Publié: (2026)

When Roles Fail: Epistemic Constraints on Advocate Role Fidelity in LLM-Based Political Statement Analysis
par: Dietrich, Juergen
Publié: (2026)

LLM Agents in Interaction: Measuring Personality Consistency and Linguistic Alignment in Interacting Populations of Large Language Models
par: Frisch, Ivar, et autres
Publié: (2024)

Assemble Your Crew: Automatic Multi-agent Communication Topology Design via Autoregressive Graph Generation
par: Li, Shiyuan, et autres
Publié: (2025)

Mapping Human Anti-collusion Mechanisms to Multi-agent AI Systems
par: Idowu, Jamiu, et autres
Publié: (2026)

Among Them: A game-based framework for assessing persuasion capabilities of LLMs
par: Idziejczak, Mateusz, et autres
Publié: (2025)

Leveraging LLM-based agents for social science research: insights from citation network simulations
par: Ji, Jiarui, et autres
Publié: (2025)

Anemoi: A Semi-Centralized Multi-agent System Based on Agent-to-Agent Communication MCP server from Coral Protocol
par: Ren, Xinxing, et autres
Publié: (2025)

The potential role of AI agents in transforming nuclear medicine research and cancer management in India
par: Vashistha, Rajat, et autres
Publié: (2025)

Addressing the alignment problem in transportation policy making: an LLM approach
par: Yan, Xiaoyu, et autres
Publié: (2025)

Collective Behavior of AI Agents: the Case of Moltbook
par: De Marzo, Giordano, et autres
Publié: (2026)

Conformity Generates Collective Misalignment in AI Agents Societies
par: De Marzo, Giordano, et autres
Publié: (2026)

Multi-agent Architecture Search via Agentic Supernet
par: Zhang, Guibin, et autres
Publié: (2025)

Mina: A Multilingual LLM-Powered Legal Assistant Agent for Bangladesh for Empowering Access to Justice
par: Wasi, Azmine Toushik, et autres
Publié: (2025)

Safe Multi-agent Reinforcement Learning with Natural Language Constraints
par: Wang, Ziyan, et autres
Publié: (2024)

MAS-KCL: Knowledge component graph structure learning with large language model-based agentic workflow
par: Jiang, Yuan-Hao, et autres
Publié: (2025)

Heterogeneous Debate Engine: Identity-Grounded Cognitive Architecture for Resilient LLM-Based Ethical Tutoring
par: Masłowski, Jakub, et autres
Publié: (2026)