Copertina

Evaluating and Understanding Scheming Propensity in LLM Agents

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Hopman, Mia, Elstner, Jannes, Avramidou, Maria, Prasad, Amritanshu, Lindner, David
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Artificial Intelligence
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Consistency Training while Mitigating Obfuscation via Rate Matching
di: Imran, Sohaib, et al.
Pubblicazione: (2026)

The Geometry of Refusal in Large Language Models: Concept Cones and Representational Independence
di: Wollschläger, Tom, et al.
Pubblicazione: (2025)

Differential Harm Propensity in Personalized LLM Agents: The Curious Case of Mental Health Disclosure
di: Yildirim, Caglar
Pubblicazione: (2026)

Instrumental Choices: Measuring the Propensity of LLM Agents to Pursue Instrumental Behaviors
di: Wiedermann-Möller, Jonas, et al.
Pubblicazione: (2026)

Combining Cost-Constrained Runtime Monitors for AI Safety
di: Hua, Tim Tian, et al.
Pubblicazione: (2025)

Towards Understanding Specification Gaming in Reasoning Models
di: Nishimura-Gasparian, Kei, et al.
Pubblicazione: (2026)

Propensity Inference: Environmental Contributors to LLM Behaviour
di: Järviniemi, Olli, et al.
Pubblicazione: (2026)

Put Your Money Where Your Mouth Is: Evaluating Strategic Planning and Execution of LLM Agents in an Auction Arena
di: Chen, Jiangjie, et al.
Pubblicazione: (2023)

LifelongAgentBench: Evaluating LLM Agents as Lifelong Learners
di: Zheng, Junhao, et al.
Pubblicazione: (2025)

Do LLM Agents Know How to Ground, Recover, and Assess? A Benchmark for Epistemic Competence in Information-Seeking Agents
di: Shao, Jiaqi, et al.
Pubblicazione: (2025)

AgentAuditor: Human-Level Safety and Security Evaluation for LLM Agents
di: Luo, Hanjun, et al.
Pubblicazione: (2025)

PolicyBank: Evolving Policy Understanding for LLM Agents
di: Choi, Jihye, et al.
Pubblicazione: (2026)

Evaluating the Propensity of Generative AI for Producing Harmful Disinformation During the 2024 US Election Cycle
di: Schlicht, Erik J
Pubblicazione: (2024)

RewardHackingAgents: Benchmarking Evaluation Integrity for LLM ML-Engineering Agents
di: Atinafu, Yonas, et al.
Pubblicazione: (2026)

Understanding Agent Scaling in LLM-Based Multi-Agent Systems via Diversity
di: Yang, Yingxuan, et al.
Pubblicazione: (2026)

AgentEscapeBench: Evaluating Out-of-Domain Tool-Grounded Reasoning in LLM Agents
di: Guo, Zhengkang, et al.
Pubblicazione: (2026)

The Necessity of a Unified Framework for LLM-Based Agent Evaluation
di: Zhu, Pengyu, et al.
Pubblicazione: (2026)

Memory for Autonomous LLM Agents:Mechanisms, Evaluation, and Emerging Frontiers
di: Du, Pengfei
Pubblicazione: (2026)

SOP-Bench: Complex Industrial SOPs for Evaluating LLM Agents
di: Nandi, Subhrangshu, et al.
Pubblicazione: (2025)

PowerChain: A Verifiable Agentic AI System for Automating Distribution Grid Analyses
di: Badmus, Emmanuel O., et al.
Pubblicazione: (2025)

AgentMisalignment: Measuring the Propensity for Misaligned Behaviour in LLM-Based Agents
di: Naik, Akshat, et al.
Pubblicazione: (2025)

Beyond Scalars: Evaluating and Understanding LLM Reasoning via Geometric Progress and Stability
di: Jiang, Xinyan, et al.
Pubblicazione: (2026)

RADAR: Mechanistic Pathways for Detecting Data Contamination in LLM Evaluation
di: Kattamuri, Ashish, et al.
Pubblicazione: (2025)

Got a Secret? LLM Agents Can't Keep It: Evaluating Privacy in Multi-Agent Systems
di: Priyanshu, Aman, et al.
Pubblicazione: (2026)

Discovery of False Data Injection Schemes on Frequency Controllers with Reinforcement Learning
di: Prasad, Romesh, et al.
Pubblicazione: (2024)

Evaluation and Benchmarking of LLM Agents: A Survey
di: Mohammadi, Mahmoud, et al.
Pubblicazione: (2025)

MIRAI: Evaluating LLM Agents for Event Forecasting
di: Ye, Chenchen, et al.
Pubblicazione: (2024)

PhysicianBench: Evaluating LLM Agents in Real-World EHR Environments
di: Liu, Ruoqi, et al.
Pubblicazione: (2026)

Toward Personalized LLM-Powered Agents: Foundations, Evaluation, and Future Directions
di: Xu, Yue, et al.
Pubblicazione: (2026)

GVGAI-LLM: Evaluating Large Language Model Agents with Infinite Games
di: Li, Yuchen, et al.
Pubblicazione: (2025)

Evaluating Multi-Turn Bargain Skills in LLM-Based Seller Agent
di: Wang, Issue Yishu, et al.
Pubblicazione: (2025)

CORE: Full-Path Evaluation of LLM Agents Beyond Final State
di: Michelakis, Panagiotis, et al.
Pubblicazione: (2025)

InnovatorBench: Evaluating Agents' Ability to Conduct Innovative LLM Research
di: Wu, Yunze, et al.
Pubblicazione: (2025)

Agent-in-the-Loop: A Data Flywheel for Continuous Improvement in LLM-based Customer Support
di: Zhao, Cen Mia, et al.
Pubblicazione: (2025)

Scheming Ability in LLM-to-LLM Strategic Interactions
di: Pham, Thao
Pubblicazione: (2025)

Towards Understanding the Robustness of LLM-based Evaluations under Perturbations
di: Chaudhary, Manav, et al.
Pubblicazione: (2024)

LLM-BABYBENCH: Understanding and Evaluating Grounded Planning and Reasoning in LLMs
di: Choukrani, Omar, et al.
Pubblicazione: (2025)

Quantifying the Necessity of Chain of Thought through Opaque Serial Depth
di: Brown-Cohen, Jonah, et al.
Pubblicazione: (2026)

The Propensity for Density in Feed-forward Models
di: Schoots, Nandi, et al.
Pubblicazione: (2024)

ShopSimulator: Evaluating and Exploring RL-Driven LLM Agent for Shopping Assistants
di: Wang, Pei, et al.
Pubblicazione: (2026)