Copertina

Convergence dynamics of Agent-to-Agent Interactions with Misaligned objectives

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Cosentino, Romain, Shekkizhar, Sarath, Earle, Adam
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Multiagent Systems Artificial Intelligence
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Beyond the Assistant Turn: User Turn Generation as a Probe of Interaction Awareness in Language Models
di: Shekkizhar, Sarath, et al.
Pubblicazione: (2026)

Interaction Theater: A case of LLM Agents Interacting at Scale
di: Shekkizhar, Sarath, et al.
Pubblicazione: (2026)

Echoing: Identity Failures when LLM Agents Talk to Each Other
di: Shekkizhar, Sarath, et al.
Pubblicazione: (2025)

Counterparty Modeling is Not Strategy: The Limits of LLM Negotiators
di: Cosentino, Romain, et al.
Pubblicazione: (2026)

A Generalist Hanabi Agent
di: Sudhakar, Arjun V, et al.
Pubblicazione: (2025)

Ariadne and Theseus: Exploration and Rendezvous with Two Mobile Agents in an Unknown Graph
di: Cosson, Romain
Pubblicazione: (2024)

Thought Virus: Viral Misalignment via Subliminal Prompting in Multi-Agent Systems
di: Weckbecker, Moritz, et al.
Pubblicazione: (2026)

Reasoning in Large Language Models: A Geometric Perspective
di: Cosentino, Romain, et al.
Pubblicazione: (2024)

AGI Is Coming... Right After AI Learns to Play Wordle
di: Shekkizhar, Sarath, et al.
Pubblicazione: (2025)

Interactional Fairness in LLM Multi-Agent Systems: An Evaluation Framework
di: Binkyte, Ruta
Pubblicazione: (2025)

Evaluating Theory of Mind and Internal Beliefs in LLM-Based Multi-Agent Systems
di: Kostka, Adam, et al.
Pubblicazione: (2026)

High-order Interactions Modeling for Interpretable Multi-Agent Q-Learning
di: Xu, Qinyu, et al.
Pubblicazione: (2025)

Verifiable Semantics for Agent-to-Agent Communication
di: Schoenegger, Philipp, et al.
Pubblicazione: (2026)

AgentArk: Distilling Multi-Agent Intelligence into a Single LLM Agent
di: Luo, Yinyi, et al.
Pubblicazione: (2026)

Beyond Single-Agent Safety: A Taxonomy of Risks in LLM-to-LLM Interactions
di: Bisconti, Piercosma, et al.
Pubblicazione: (2025)

From Single to Societal: Analyzing Persona-Induced Bias in Multi-Agent Interactions
di: Li, Jiayi, et al.
Pubblicazione: (2025)

The Bystander Effect in Multi-Agent Reasoning: Quantifying Cognitive Loafing in Collaborative Interactions
di: Shehata, Dahlia, et al.
Pubblicazione: (2026)

Spontaneous Emergence of Agent Individuality through Social Interactions in LLM-Based Communities
di: Takata, Ryosuke, et al.
Pubblicazione: (2024)

Enhancing LLM Problem Solving via Tutor-Student Multi-Agent Interaction
di: Özdemir, Nurullah Eymen, et al.
Pubblicazione: (2026)

SIGMAS: Second-Order Interaction-based Grouping for Overlapping Multi-Agent Swarms
di: Lee, Minah, et al.
Pubblicazione: (2026)

Heterogeneous Interaction Modeling With Reduced Accumulated Error for Multi-Agent Trajectory Prediction
di: Chen, Siyuan, et al.
Pubblicazione: (2024)

Can We Govern the Agent-to-Agent Economy?
di: Chaffer, Tomer Jordi
Pubblicazione: (2025)

ACPs: Agent Collaboration Protocols for the Internet of Agents
di: Liu, Jun, et al.
Pubblicazione: (2025)

Inverse Attention Agents for Multi-Agent Systems
di: Long, Qian, et al.
Pubblicazione: (2024)

Optimizing Sequential Multi-Step Tasks with Parallel LLM Agents
di: Zhang, Enhao, et al.
Pubblicazione: (2025)

When Cloud Agents Meet Device Agents: Lessons from Hybrid Multi-Agent Systems
di: Rainone, Corrado, et al.
Pubblicazione: (2026)

CityGPT: Towards Urban IoT Learning, Analysis and Interaction with Multi-Agent System
di: Guan, Qinghua, et al.
Pubblicazione: (2024)

Agent Exchange: Shaping the Future of AI Agent Economics
di: Yang, Yingxuan, et al.
Pubblicazione: (2025)

S-Agents: Self-organizing Agents in Open-ended Environments
di: Chen, Jiaqi, et al.
Pubblicazione: (2024)

AgentMixer: Multi-Agent Correlated Policy Factorization
di: Li, Zhiyuan, et al.
Pubblicazione: (2024)

Too Human to Model:The Uncanny Valley of LLMs in Social Simulation -- When Generative Language Agents Misalign with Modelling Principles
di: Zeng, Yongchao, et al.
Pubblicazione: (2025)

ColorAgent: Building A Robust, Personalized, and Interactive OS Agent
di: Li, Ning, et al.
Pubblicazione: (2025)

BioAgents: Democratizing Bioinformatics Analysis with Multi-Agent Systems
di: Mehandru, Nikita, et al.
Pubblicazione: (2025)

Optimizing Agent Collaboration through Heuristic Multi-Agent Planning
di: Soffair, Nitsan
Pubblicazione: (2023)

Very Large-Scale Multi-Agent Simulation in AgentScope
di: Pan, Xuchen, et al.
Pubblicazione: (2024)

Creative Agents: Simulating the Systems Model of Creativity with Generative Agents
di: Imasato, Naomi, et al.
Pubblicazione: (2024)

AgentSchool: An LLM-Powered Multi-Agent Simulation for Education
di: Ye, Yulei, et al.
Pubblicazione: (2026)

OPTAGENT: Optimizing Multi-Agent LLM Interactions Through Verbal Reinforcement Learning for Enhanced Reasoning
di: Bi, Zhenyu, et al.
Pubblicazione: (2025)

Single-Agent Scaling Fails Multi-Agent Intelligence: Towards Foundation Models with Native Multi-Agent Intelligence
di: Hu, Shuyue, et al.
Pubblicazione: (2025)

Distributionally Robust Cooperative Multi-Agent Reinforcement Learning via Robust Value Factorization
di: Qu, Chengrui, et al.
Pubblicazione: (2026)