Copertina

Technical Report: Evaluating Goal Drift in Language Model Agents

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Arike, Rauno, Donoway, Elizabeth, Bartsch, Henning, Hobbhahn, Marius
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Artificial Intelligence Machine Learning
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

C2-Faith: Benchmarking LLM Judges for Causal and Coverage Faithfulness in Chain-of-Thought Reasoning
di: Mittal, Avni, et al.
Pubblicazione: (2026)

Large Language Models can Strategically Deceive their Users when Put Under Pressure
di: Scheurer, Jérémy, et al.
Pubblicazione: (2023)

Large Language Models Often Know When They Are Being Evaluated
di: Needham, Joe, et al.
Pubblicazione: (2025)

Excess Description Length of Learning Generalizable Predictors
di: Donoway, Elizabeth, et al.
Pubblicazione: (2026)

Frontier Models are Capable of In-context Scheming
di: Meinke, Alexander, et al.
Pubblicazione: (2024)

Interpreting Learned Feedback Patterns in Large Language Models
di: Marks, Luke, et al.
Pubblicazione: (2023)

Evaluating the Goal-Directedness of Large Language Models
di: Everitt, Tom, et al.
Pubblicazione: (2025)

A Behavioural and Representational Evaluation of Goal-Directedness in Language Model Agents
di: Arghal, Raghu, et al.
Pubblicazione: (2026)

Forecasting Frontier Language Model Agent Capabilities
di: Pimpale, Govind, et al.
Pubblicazione: (2025)

The Elicitation Game: Evaluating Capability Elicitation Techniques
di: Hofstätter, Felix, et al.
Pubblicazione: (2025)

AutoML for Multi-Class Anomaly Compensation of Sensor Drift
di: Schaller, Melanie, et al.
Pubblicazione: (2025)

Cisco Time Series Model Technical Report
di: Gou, Liang, et al.
Pubblicazione: (2025)

Removing Sandbagging in LLMs by Training with Weak Supervision
di: Ryd, Emil, et al.
Pubblicazione: (2026)

LLMComp: A Language Modeling Paradigm for Error-Bounded Scientific Data Compression (Technical Report)
di: Li, Guozhong, et al.
Pubblicazione: (2025)

Technical Report: Small Language Model for Japanese Clinical and Medicine
di: Watanabe, Shogo
Pubblicazione: (2024)

World Models with Hints of Large Language Models for Goal Achieving
di: Liu, Zeyuan, et al.
Pubblicazione: (2024)

EPT-2 Technical Report
di: Molinaro, Roberto, et al.
Pubblicazione: (2025)

INTELLECT-3: Technical Report
di: Prime Intellect Team, et al.
Pubblicazione: (2025)

LFM2 Technical Report
di: Amini, Alexander, et al.
Pubblicazione: (2025)

How does information access affect LLM monitors' ability to detect sabotage?
di: Arike, Rauno, et al.
Pubblicazione: (2026)

Open Character Training: Shaping the Persona of AI Assistants through Constitutional AI
di: Maiya, Sharan, et al.
Pubblicazione: (2025)

DriftXpress: Faster Drifting Models via Projected RKHS Fields
di: Falahati, Ali, et al.
Pubblicazione: (2026)

Analyzing Probabilistic Methods for Evaluating Agent Capabilities
di: Højmark, Axel, et al.
Pubblicazione: (2024)

Goal-Conditioned Agents that Learn Everything All at Once
di: Matthews, Michael, et al.
Pubblicazione: (2026)

Recourse under Model Multiplicity via Argumentative Ensembling (Technical Report)
di: Jiang, Junqi, et al.
Pubblicazione: (2023)

Training Deliberative Monitors for Black-Box Scheming Detection
di: Sinha, Aditya, et al.
Pubblicazione: (2026)

Overcoming Dependent Censoring in the Evaluation of Survival Models
di: Lillelund, Christian Marius, et al.
Pubblicazione: (2025)

Evaluating Language-Model Agents on Realistic Autonomous Tasks
di: Kinniment, Megan, et al.
Pubblicazione: (2023)

Optimal Self-Consistency for Efficient Reasoning with Large Language Models
di: Feng, Austin, et al.
Pubblicazione: (2025)

Motif 2.6B Technical Report
di: Lim, Junghwan, et al.
Pubblicazione: (2025)

RLDX-1 Technical Report
di: Kim, Dongyoung, et al.
Pubblicazione: (2026)

Me, Myself, and AI: The Situational Awareness Dataset (SAD) for LLMs
di: Laine, Rudolf, et al.
Pubblicazione: (2024)

Paradigms of AI Evaluation: Mapping Goals, Methodologies and Culture
di: Burden, John, et al.
Pubblicazione: (2025)

Evaluating the Paperclip Maximizer: Are RL-Based Language Models More Likely to Pursue Instrumental Goals?
di: He, Yufei, et al.
Pubblicazione: (2025)

Self-Supervised Goal-Reaching Results in Multi-Agent Cooperation and Exploration
di: Nimonkar, Chirayu, et al.
Pubblicazione: (2025)

Reaching Consensus in Cooperative Multi-Agent Reinforcement Learning with Goal Imagination
di: Wang, Liangzhou, et al.
Pubblicazione: (2024)

Goal Recognition Design for General Behavioral Agents using Machine Learning
di: Kasumba, Robert, et al.
Pubblicazione: (2024)

Argumentative Debates for Transparent Bias Detection [Technical Report]
di: Ayoobi, Hamed, et al.
Pubblicazione: (2025)

On the Wasserstein Gradient Flow Interpretation of Drifting Models
di: Gretton, Arthur, et al.
Pubblicazione: (2026)

Incoherence in Goal-Conditioned Autoregressive Models
di: Karwowski, Jacek, et al.
Pubblicazione: (2025)