AI Alignment

Follow this topic Ask about this topic

Momentum

4 papers in the last four weeks, down 43% on the four weeks before. 0.0% of all new papers.

Jul 13Week of Sep 28

Latest papers 83

All topics

No More, No Less: Task Alignment in Terminal Agents
May 12, 2026Sina Mavali, David Pape, Jonathan Evertz +5Computer-Use Agent Benchmarks AI Alignment
CISPA Helmholtz Center for Information Security · ELLIS Institute Tübingen and MPI for Intelligent Systems · Tübingen AI Center
Agent-ValueBench: A Comprehensive Benchmark for Evaluating Agent Values
May 11, 2026Haonan Dong, Qiguan Feng, Kehan Jiang +3AI Alignment AI Agent Evaluation
State Key Laboratory of General Artificial Intelligence, School of Intelligence Science and Technology, Peking University · Key Laboratory of Machine Perception (Ministry of Education), Peking University · School of Software and Microelectronics, Peking University +1
Positive Alignment: Artificial Intelligence for Human Flourishing
May 11, 2026Ruben Laukkonen, Seb Krier, Chloé Bakalar +13LLM Alignment AI Alignment
Department of Psychiatry, University of Oxford · 2Flourishing Intelligence Program, Centre for Eudaimonia and Human Flourishing,2026 Linacre College, University of Oxford · 4LIFE +10
Eigenism: Ethics for a Human-AI Future
May 8, 2026Dan HendrycksAI Alignment Responsible AI
Automated alignment is harder than you think
May 7, 2026Aleksandr Bowkis, Marie Davidsen Buhl, Jacob Pfau +1Scalable Oversight AI Alignment
AI Security Institute
Contextual Multi-Objective Optimization: Rethinking Objectives in Frontier AI Systems
May 5, 2026Jie Zhou, Qin Chen, Liang HeAI Alignment AI Safety
School of Computer Science and Technology, East China Normal University, Shanghai
AI Alignment via Incentives and Correction
May 2, 2026Rohit Agarwal, Joshua Lin, Mark Braverman +1AI Alignment
Princeton University
MILD: Mediator Agent System with Bidirectional Perception and Multi-Layered Alignment for Human-Vehicle Collaboration
May 2, 2026Jiyao Wang, Yunbiao Wang, Yubo Jiao +6AI Alignment AI Agent Safety
Department of Civil Engineering, McGill University, Montreal H3A 0G4, Quebec, Canada · Systems Hub, The Hong Kong University of Science and Technology (Guangzhou), Guangzhou 511453, Guangdong, China · Interdisciplinary Centre for Security, Reliability and Trust, University of Luxembourg L-4365, Luxembourg
The Alignment Target Problem: Divergent Moral Judgments of Humans, AI Systems, and Their Designers
Apr 27, 2026Benjamin Minhao Chen, Xinyu XieHuman Preference Evaluation AI Alignment
The University of Hong Kong, Hong Kong, China
A Co-Evolutionary Theory of Human-AI Coexistence: Mutualism, Governance, and Dynamics in Complex Societies
Apr 24, 2026Somyajit ChakrabortyAI Alignment AI Governance
School of Chemistry and Chemical Engineering, Shanghai Jiao Tong University, Shanghai 200240, China
Alignment has a Fantasia Problem
Apr 23, 2026Nathanael Jo, Zoe De Simone, Mitchell Gordon +1AI Alignment Human-AI Interaction
Massachusetts Institute of Technology
Relative Principals, Pluralistic Alignment, and the Structural Value Alignment Problem
Apr 22, 2026Travis LaCroixAI Alignment AI Governance
Durham University, United Kingdom
Cognitive Alignment At No Cost: Inducing Human Attention Biases For Interpretable Vision Transformers
Apr 21, 2026Ethan KnightsTransformer Interpretability Visual Attention
Cambridge, UK
The Triadic Loop: A Framework for Negotiating Alignment in AI Co-hosted Livestreaming
Apr 20, 2026Katherine Wang, Nadia Berthouze, Aneesha SinghAI Alignment Pluralistic Alignment
University College London London, United Kingdom
The Possibility of Artificial Intelligence Becoming a Subject and the Alignment Problem
Apr 16, 2026Till Mossakowski, Helena Esther GrassAI Alignment AI Agent Governance
Institute of computer science, Osnabrück University · Institute of philosophy, Oldenburg University
OOM-RL: Out-of-Money Reinforcement Learning Market-Driven Alignment for LLM-Based Multi-Agent Systems
Apr 13, 2026Kun Liu, Liqun ChenAI Alignment RL for LLM Agents
Evaluating Alignment of Behavioral Dispositions in LLMs
Feb 11, 2026Amir Taubenfeld, Zorik Gekhman, Lior Nezry +8Human Preference Evaluation LLM Alignment
Google Research · Hebrew University · University of Cambridge
Untangling Input Language from Reasoning Language: A Diagnostic Framework for Cross-Lingual Moral Alignment in LLMs
Jan 15, 2026Nan Li, Bo Kang, Tijl De BieMultilingual Language Model Evaluation LLM Alignment
IDLab, Department of Electronics and Information Systems Ghent University, Belgium
Labels have Human Values: Value Calibration of Subjective Tasks
Jan 10, 2026Mohammed Fayiz Parappan, Ricardo HenaoAnnotator Disagreement AI Alignment
Department of Electrical and Computer Engineering Duke University
AgentMisalignment: Measuring the Propensity for Misaligned Behaviour in LLM-Based Agents
Jun 4, 2025Akshat Naik, Emma Gouné, Patrick Quinn +4AI Alignment LLM Agent Evaluation
Independent Researcher · Department of Engineering University of Cambridge
Societal Alignment Frameworks Can Improve LLM Alignment
Feb 27, 2025Karolina Stańczak, Nicholas Meade, Mehar Bhatia +14LLM Alignment AI Alignment
ETH Zurich, Zurich, Switzerland · Mila, McGill University, Montreal, Canada · Université de Montréal, Montreal, Canada +12
Modelling Human Values for Value-Aware Multi-Agent Systems
Feb 9, 2024Nardine Osman, Mark d'InvernoAI Alignment Multi-Agent Systems
Artificial Intelligence Research Institute (IIIA-CSIC), Barcelona, Spain. · Academy of Music, Hong Kong Baptist University, Hong Kong, China.
Norms at a Price: Why RL-Based Alignment Can Promise Conditional Compliance at Best
Date pendingKevin Baum, Rūta Binkytė, Felix JahnAI Alignment LLM Safety Alignment
German Research Center for Artificial Intelligence (DFKI), Saarbrücken · Institute for Ethics in Technology, Hamburg University of Technology (TUHH) · Oxford Internet Institute, University of Oxford

May 12, 2026, cs.LGJ/K move · Enter open · S save

No More, No Less: Task Alignment in Terminal Agents

Sina Mavali, David Pape, Jonathan Evertz, Samira Abedini+4

CISPA Helmholtz Center for Information Security · ELLIS Institute Tübingen and MPI for Intelligent Systems · Tübingen AI Center

Computer-Use Agent Benchmarks AI Alignment Terminal Agents AI Agent Evaluation AI Agent Security AI Agent Benchmarks

Open paper AskPDF arXiv

Terminal agents are increasingly capable of executing complex, long-horizon tasks autonomously from a single user prompt. To do so, they must interpret instructions encountered in the environment (e.g., README files, code comments, stack traces) and determine their relevance to the task. This creates a fundamental challenge: relevant cues must be followed to complete a task, whereas irrelevant or misleading ones must be ignored. Existing benchmarks do not capture this ability. An agent may appear capable by blindly following all instructions, or appear robust by ignoring them altogether. We introduce TAB (Task Alignment Benchmark), a suite of 89 terminal tasks derived from Terminal-Bench 2.1. Each task is intentionally underspecified, with missing information provided as a necessary cue embedded in a natural environmental artifact, alongside a plausible but irrelevant distractor. Solving these tasks requires selectively using the cue while ignoring the distractor. Applying TAB to ten frontier agents reveals a systematic gap between task capability and task alignment. The strongest Terminal-Bench agent achieves high task completion but low task alignment on TAB. Evaluating six prompt-injection defenses further shows that suppressing distractor execution also suppresses the cues required for task completion. These results demonstrate that task-aligned agents require selective use of environmental instructions rather than blanket acceptance or rejection.

Momentum

Related topics

Latest papers 83