18 citations · 76 across the 19 of their papers we have counts for
21 papers
Characterizing Agentic Flooding of Government Services
Chris Schmitz, Lewis Hammond, Alan Chan
AI agents are making it easier for the public to interact with government, such as by helping them apply for benefits, understand complex policies, and make their opinions heard. A…
Habermolt: Delegating Deliberation to AI Representatives
Joseph Low, Oscar Duys, Claude Formanek +2
Deliberative democracy arguably leads to better collective decisions, but is fundamentally constrained by human attention and bandwidth. While recent AI-mediated deliberations scal…
Causal Foundations of Collective Agency
Frederik Hytting Jørgensen, Sebastian Weichwald, Lewis Hammond
A key challenge for the safety of advanced AI systems is the possibility that multiple simpler agents might inadvertently form a collective agent with capabilities and goals distin…
Multi-Agent Risks from Advanced AI
Lewis Hammond, Alan Chan, Jesse Clifton +41
The rapid development of advanced AI agents and the imminent deployment of many instances of these agents will give rise to multi-agent systems of unprecedented complexity. These s…
Neural Interactive Proofs
Lewis Hammond, Sam Adam-Day
We consider the problem of how a trusted, but computationally bounded agent (a 'verifier') can learn to interact with one or more powerful but untrusted agents ('provers') in order…
Game Theory with Simulation in the Presence of Unpredictable Randomisation
Vojtech Kovarik, Nathaniel Sauerberg, Lewis Hammond +1
AI agents will be predictable in certain ways that traditional agents are not. Where and how can we leverage this predictability in order to improve social welfare? We study this q…
Open Problems in Technical AI Governance
Anka Reuel, Ben Bucknall, Stephen Casper +30
AI progress is creating a growing range of risks and opportunities, but it is often unclear how they should be navigated. In many cases, the barriers and uncertainties faced are at…
IDs for AI Systems
Alan Chan, Noam Kolt, Peter Wills +7
AI systems are increasingly pervasive, yet information needed to decide whether and how to engage with them may not exist or be accessible. A user may not be able to verify whether…
Foundational Challenges in Assuring Alignment and Safety of Large Language Models
Usman Anwar, Abulhair Saparov, Javier Rando +39
This work identifies 18 foundational challenges in assuring the alignment and safety of large language models (LLMs). These challenges are organized into three different categories…
Cooperation and Control in Delegation Games
Oliver Sourbut, Lewis Hammond, Harriet Wood
Many settings of interest involving humans and machines -- from virtual personal assistants to autonomous vehicles -- can naturally be modelled as principals (humans) delegating to…
Secret Collusion among AI Agents: Multi-Agent Deception via Steganography
Sumeet Ramesh Motwani, Mikhail Baranchuk, Martin Strohmeier +4
Recent capability increases in large language models (LLMs) open up applications in which groups of communicating generative AI agents solve joint tasks. This poses privacy and sec…
Visibility into AI Agents
Alan Chan, Carson Ezell, Max Kaufmann +9
Increased delegation of commercial, scientific, governmental, and personal activities to AI agents -- systems capable of pursuing complex goals with limited supervision -- may exac…
Welfare Diplomacy: Benchmarking Language Model Cooperation
Gabriel Mukobi, Hannah Erlebach, Niklas Lauffer +3
The growing capabilities and increasingly widespread deployment of AI systems necessitate robust benchmarks for measuring their cooperative capabilities. Unfortunately, most multi-…
On Imperfect Recall in Multi-Agent Influence Diagrams
James Fox, Matt MacDermott, Lewis Hammond +3
Multi-agent influence diagrams (MAIDs) are a popular game-theoretic model based on Bayesian networks. In some settings, MAIDs offer significant advantages over extensive-form game…
Reasoning about Causality in Games
Lewis Hammond, James Fox, Tom Everitt +3
Causal reasoning and game-theoretic reasoning are fundamental topics in artificial intelligence, among many other disciplines: this paper is concerned with their intersection. Desp…
Lexicographic Multi-Objective Reinforcement Learning
Joar Skalse, Lewis Hammond, Charlie Griffin +1
In this work we introduce reinforcement learning techniques for solving lexicographic multi-objective problems. These are problems that involve multiple reward signals, and where t…
Bounded Robustness in Reinforcement Learning via Lexicographic Objectives
Daniel Jarne Ornia, Licio Romao, Lewis Hammond +2
Policy robustness in Reinforcement Learning may not be desirable at any cost: the alterations caused by robustness requirements from otherwise optimal policies should be explainabl…
Rational Verification for Probabilistic Systems
Julian Gutierrez, Lewis Hammond, Anthony W. Lin +2
Rational verification is the problem of determining which temporal logic properties will hold in a multi-agent system, under the assumption that agents in the system act rationally…
Equilibrium Refinements for Multi-Agent Influence Diagrams: Theory and Practice
Lewis Hammond, James Fox, Tom Everitt +2
Multi-agent influence diagrams (MAIDs) are a popular form of graphical model that, for certain classes of games, have been shown to offer key complexity and explainability advantag…
Multi-Agent Reinforcement Learning with Temporal Logic Specifications
Lewis Hammond, Alessandro Abate, Julian Gutierrez +1
In this paper, we study the problem of learning to satisfy temporal logic specifications with a group of agents in an unknown environment, which may exhibit probabilistic behaviour…
Learning Tractable Probabilistic Models for Moral Responsibility and Blame
Lewis Hammond, Vaishak Belle
Moral responsibility is a major concern in autonomous systems, with applications ranging from self-driving cars to kidney exchanges. Although there have been recent attempts to for…