Imagen de Portada

AgentMisalignment: Measuring the Propensity for Misaligned Behaviour in LLM-Based Agents

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Naik, Akshat, Quinn, Patrick, Bosch, Guillermo, Gouné, Emma, Zabala, Francisco Javier Campos, Brown, Jason Ross, Young, Edward James
Formato:	Preprint
Publicado:	2025
Materias:	Artificial Intelligence Computation and Language Computers and Society Machine Learning I.2.7; I.2.11; K.4.1; I.2.6
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

From Helpfulness to Toxic Proactivity: Diagnosing Behavioral Misalignment in LLM Agents
por: Wang, Xinyue, et al.
Publicado: (2026)

Rewarding Beliefs, Not Actions: Consistency-Guided Credit Assignment for Long-Horizon Agents
por: Tang, Wenjie, et al.
Publicado: (2026)

Changing the Rules of the Game: Reasoning about Dynamic Phenomena in Multi-Agent Systems
por: Galimullin, Rustam, et al.
Publicado: (2025)

Agent Capsules: Quality-Gated Granularity Control for Multi-Agent LLM Pipelines
por: Ray, Aninda
Publicado: (2026)

On The Role of Intentionality in Knowledge Representation: Analyzing Scene Context for Cognitive Agents with a Tiny Language Model
por: Burgess, Mark
Publicado: (2025)

AgentLeak: A Full-Stack Benchmark for Privacy Leakage in Multi-Agent LLM Systems
por: Yagoubi, Faouzi El, et al.
Publicado: (2026)

Umwelt Engineering: Designing the Cognitive Worlds of Linguistic Agents
por: Jehu-Appiah, Rodney
Publicado: (2026)

From Safety Risk to Design Principle: Peer-Preservation in Multi-Agent LLM Systems and Its Implications for Orchestrated Democratic Discourse Analysis
por: Dietrich, Juergen
Publicado: (2026)

$γ(3,4)$ `Attention' in Cognitive Agents: Ontology-Free Knowledge Representations With Promise Theoretic Semantics
por: Burgess, Mark
Publicado: (2025)

Privacy as Commodity: MFG-RegretNet for Large-Scale Privacy Trading in Federated Learning
por: Sun, Kangkang, et al.
Publicado: (2026)

Policy Cards: Machine-Readable Runtime Governance for Autonomous AI Agents
por: Mavračić, Juraj
Publicado: (2025)

Council Mode: A Heterogeneous Multi-Agent Consensus Framework for Reducing LLM Hallucination and Bias
por: Wu, Shuai, et al.
Publicado: (2026)

Exploring Design of Multi-Agent LLM Dialogues for Research Ideation
por: Ueda, Keisuke, et al.
Publicado: (2025)

Comparing State-Representations for DEL Model Checking
por: Behnke, Gregor, et al.
Publicado: (2025)

FSFM: A Biologically-Inspired Framework for Selective Forgetting of Agent Memory
por: Gu, Yingjie, et al.
Publicado: (2026)

AgentSpawn: Adaptive Multi-Agent Collaboration Through Dynamic Spawning for Long-Horizon Code Generation
por: Costa, Igor
Publicado: (2026)

A Super-Learner with Large Language Models for Medical Emergency Advising
por: Aityan, Sergey K., et al.
Publicado: (2025)

Ontology-Constrained Neural Reasoning in Enterprise Agentic Systems: A Neurosymbolic Architecture for Domain-Grounded AI Agents
por: Tuan, Thanh Luong, et al.
Publicado: (2026)

N-Agent Ad Hoc Teamwork
por: Wang, Caroline, et al.
Publicado: (2024)

Beyond Rating: A Comprehensive Evaluation and Benchmark for AI Reviews
por: Li, Bowen, et al.
Publicado: (2026)

SoccerRef-Agents: Multi-Agent System for Automated Soccer Refereeing
por: Meng, Zi, et al.
Publicado: (2026)

MARS: Multi-Agent Robotic System with Multimodal Large Language Models for Assistive Intelligence
por: Gao, Renjun
Publicado: (2025)

Generating Causal Explanations of Vehicular Agent Behavioural Interactions with Learnt Reward Profiles
por: Howard, Rhys, et al.
Publicado: (2025)

SDOF: Taming the Alignment Tax in Multi-Agent Orchestration with State-Constrained Dispatch
por: Wang, Zhantao
Publicado: (2026)

Advancing Multimodal Agent Reasoning with Long-Term Neuro-Symbolic Memory
por: Jiang, Rongjie, et al.
Publicado: (2026)

AgentAtlas: Beyond Outcome Leaderboards for LLM Agents
por: Mazaheri, Parsa, et al.
Publicado: (2026)

Instruction-Level Weight Shaping: A Framework for Self-Improving AI Agents
por: Costa, Rimom
Publicado: (2025)

Sovereign-OS: A Charter-Governed Operating System for Autonomous AI Agents with Verifiable Fiscal Discipline
por: Yuan, Aojie, et al.
Publicado: (2026)

Privacy Preserving Multi Agent Path Finding
por: Lehman, Rotem Lev, et al.
Publicado: (2026)

One Policy, Infinite NPCs: Persona-Traceable Shared RL Policies for Scalable Game Agents
por: Hong, Yoosung
Publicado: (2026)

Exploring Robust Multi-Agent Workflows for Environmental Data Management
por: Guan, Boyuan, et al.
Publicado: (2026)

Multi-Agent Design Assistant for the Simulation of Inertial Fusion Energy
por: Shachar, Meir H., et al.
Publicado: (2025)

Applying Cognitive Design Patterns to General LLM Agents
por: Wray, Robert E., et al.
Publicado: (2025)

Agent Semantics, Semantic Spacetime, and Graphical Reasoning
por: Burgess, Mark
Publicado: (2025)

Robust and Diverse Multi-Agent Learning via Rational Policy Gradient
por: Lauffer, Niklas, et al.
Publicado: (2025)

Multi-Paradigm Agent Interaction in Practice:A Systematic Analysis of Generator-Evaluator, ReAct Loop,and Adversarial Evaluation in the buddyMe Framework
por: Wang, Xiaohua, et al.
Publicado: (2026)

Analysing Factorizations of Action-Value Networks for Cooperative Multi-Agent Reinforcement Learning
por: Castellini, Jacopo, et al.
Publicado: (2019)

PRIMA: Operational Patterns for Resilient Multi-Agent Research with Verifiable Identity and Convergent Feedback
por: Annapureddy, Sasank
Publicado: (2026)

ME-IGM: Individual-Global-Max in Maximum Entropy Multi-Agent Reinforcement Learning
por: Chen, Wen-Tse, et al.
Publicado: (2024)

Evolved Developmental Artificial Neural Networks for Multitasking with Advanced Activity Dependence
por: Zhang, Yintong, et al.
Publicado: (2024)