Image de couverture de livre

Prompt Optimization Enables Stable Algorithmic Collusion in LLM Agents

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteur principal:	Tian, Yingtao
Format:	Preprint
Publié:	2026
Sujets:	Artificial Intelligence
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Voluntary Collusion with Secret Tools in Competing LLM Agents
par: Zeng, Xijie, et autres
Publié: (2026)

Evaluating LLM Agent Collusion in Double Auctions
par: Agrawal, Kushal, et autres
Publié: (2025)

Evolution Transformer: In-Context Evolutionary Optimization
par: Lange, Robert Tjarko, et autres
Publié: (2024)

Discovering Novel LLM Experts via Task-Capability Coevolution
par: Dai, Andrew, et autres
Publié: (2026)

Algorithmic Collusion by Large Language Models
par: Fish, Sara, et autres
Publié: (2024)

Detecting Multi-Agent Collusion Through Multi-Agent Interpretability
par: Rose, Aaron, et autres
Publié: (2026)

Strategic Collusion of LLM Agents: Market Division in Multi-Commodity Competitions
par: Lin, Ryan Y., et autres
Publié: (2024)

Secret Collusion among AI Agents: Multi-Agent Deception via Steganography
par: Motwani, Sumeet Ramesh, et autres
Publié: (2024)

Audit the Whisper: Detecting Steganographic Collusion in Multi-Agent LLMs
par: Tailor, Om
Publié: (2025)

The Spoils of Algorithmic Collusion: Profit Allocation Among Asymmetric Firms
par: Martin, Simon, et autres
Publié: (2025)

Agent-Based Genetic Algorithm for Crypto Trading Strategy Optimization
par: Tian, Qiushi, et autres
Publié: (2025)

AutoPDL: Automatic Prompt Optimization for LLM Agents
par: Spiess, Claudio, et autres
Publié: (2025)

Colosseum: Auditing Collusion in Cooperative Multi-Agent Systems
par: Nakamura, Mason, et autres
Publié: (2026)

GroupGuard: A Framework for Modeling and Defending Collusive Attacks in Multi-Agent Systems
par: Tao, Yiling, et autres
Publié: (2026)

Multi-Agent Reinforcement Learning for Market Making: Competition without Collusion
par: Wang, Ziyi, et autres
Publié: (2025)

Institutional AI: Governing LLM Collusion in Multi-Agent Cournot Markets via Public Governance Graphs
par: Syrnikov, Marcantonio Bracale, et autres
Publié: (2026)

Evolution of Collective AI Beyond Individual Optimization
par: Takata, Ryosuke, et autres
Publié: (2024)

GuruAgents: Emulating Wise Investors with Prompt-Guided LLM Agents
par: Kim, Yejin, et autres
Publié: (2025)

Collusive Pricing Under LLM
par: Cao, Shengyu, et autres
Publié: (2026)

MAPGD: Multi-Agent Prompt Gradient Descent for Collaborative Prompt Optimization
par: Han, Yichen, et autres
Publié: (2025)

Adaptive Prompt Embedding Optimization for LLM Jailbreaking
par: Li, Miles Q., et autres
Publié: (2026)

LLM Based Bayesian Optimization for Prompt Search
par: Ballew, Adam, et autres
Publié: (2025)

Algorithmic Collusion or Competition: the Role of Platforms' Recommender Systems
par: Xu, Xingchen, et autres
Publié: (2023)

ATLAS: Adaptive Trading with LLM AgentS Through Dynamic Prompt Optimization and Multi-Agent Coordination
par: Papadakis, Charidimos, et autres
Publié: (2025)

Unifying Temporal and Structural Credit Assignment in LLM-Based Multi-Agent Prompt Optimization
par: Li, Wenwu, et autres
Publié: (2026)

When Autonomy Goes Rogue: Preparing for Risks of Multi-Agent Collusion in Social Systems
par: Ren, Qibing, et autres
Publié: (2025)

Distribution-Aware Algorithm Design with LLM Agents
par: Koganti, Saharsh, et autres
Publié: (2026)

Learned Collusion
par: Compte, Olivier
Publié: (2023)

To Protect the LLM Agent Against the Prompt Injection Attack with Polymorphic Prompt
par: Wang, Zhilong, et autres
Publié: (2025)

PRACT: Optimizing Principled Reasoning and Acting of LLM Agent
par: Liu, Zhiwei, et autres
Publié: (2024)

Artificial Intelligence and Algorithmic Price Collusion in Two-sided Markets
par: Chica, Cristian, et autres
Publié: (2024)

EcoGEO: Trajectory-Aware Evidence Ecosystems for Web-Enabled LLM Search Agents
par: Ye, Hengwei, et autres
Publié: (2026)

Prompt Infection: LLM-to-LLM Prompt Injection within Multi-Agent Systems
par: Lee, Donghyun, et autres
Publié: (2024)

Bi-Level Prompt Optimization for Multimodal LLM-as-a-Judge
par: Pan, Bo, et autres
Publié: (2026)

EvoPrompt: Connecting LLMs with Evolutionary Algorithms Yields Powerful Prompt Optimizers
par: Guo, Qingyan, et autres
Publié: (2023)

PromptSculptor: Multi-Agent Based Text-to-Image Prompt Optimization
par: Xiang, Dawei, et autres
Publié: (2025)

Reimagining Agent-based Modeling with Large Language Model Agents via Shachi
par: Kuroki, So, et autres
Publié: (2025)

MASPO: Joint Prompt Optimization for LLM-based Multi-Agent Systems
par: Wang, Zhexuan, et autres
Publié: (2026)

Conjunctive Prompt Attacks in Multi-Agent LLM Systems
par: Arif, Nokimul Hasan, et autres
Publié: (2026)

Large Language Models As Evolution Strategies
par: Lange, Robert Tjarko, et autres
Publié: (2024)