2 citations · 6 across the 19 of their papers we have counts for
21 papers
BazaarBench: Delegation Safety in Decentralized C2C Marketplaces Run by LLM Agents
Ziyan Wang, Shuqing Shi, James Oldfield +5
In decentralized consumer-to-consumer (C2C) marketplaces, people list goods, negotiate with strangers, and rate one another, so trust rests on reputation. Large language model (LLM…
AISPA: User-Centric System Prompt Auditing for Large Language Model Applications
Xiangning Lin, Shenzhe Zhu, Shu Yang +23
System prompts are instructions configured by developers to govern the behaviors of foundation models in AI applications. They are used throughout commercial AI products, but are r…
Mechanism Design Is Not Enough: Prosocial Agents for Cooperative AI
Xuanqiang Angelo Huang, Charlie Tharas, Samuele Marro +4
Ensuring that AI agents behave safely and beneficially when interacting with other parties has emerged as one of the central challenges of modern AI safety. While mechanism design,…
Plan2Map: A Multimodal Benchmark for Document-Grounded Geospatial Boundary Reconstruction from Planning Records
Fabian Degen, Oishi Deb, Jindong Gu +4
Planning records define restrictions over geographic areas, but their source documents often provide only indirect spatial evidence rather than machine-readable boundaries. We intr…
LLM Wardens: Mitigating Adversarial Persuasion with Third-Party Conversational Oversight
Lennart Wachowiak, Scott D. Blain, David Williams-King +1
LLMs are increasingly capable of persuasion, which raises the question of how to protect users against manipulation. In a preregistered user study (N=120) across four decision-maki…
Profit is the Red Team: Stress-Testing Agents in Strategic Economic Interactions
Shouqiao Wang, Marcello Politi, Samuele Marro +1
As agentic systems move into real-world deployments, their decisions increasingly depend on external inputs such as retrieved content, tool outputs, and information provided by oth…
Benchmarking at the Edge of Comprehension
Samuele Marro, Jialin Yu, Emanuele La Malfa +8
As frontier Large Language Models (LLMs) increasingly saturate new benchmarks shortly after they are published, benchmarking itself is at a juncture: if frontier models keep improv…
Permission Manifests for Web Agents
Samuele Marro, Alan Chan, Xinxing Ren +12
The rise of Large Language Model (LLM)-based web agents represents a significant shift in automated interactions with the web. Unlike traditional crawlers that follow simple conven…
Full-Stack Alignment: Co-Aligning AI and Institutions with Thick Models of Value
Joe Edelman, Tan Zhi-Xuan, Ryan Lowe +30
Beneficial societal outcomes cannot be guaranteed by aligning individual AI systems with the intentions of their operators or users. Even an AI system that is perfectly aligned to…
End-to-end PDDL Planning with Hardcoded and Dynamic Agents
Emanuele La Malfa, Ping Zhu, Samuele Marro +2
We present an end-to-end framework for planning supported by verifiers. An orchestrator receives a human specification written in natural language and converts it into a PDDL (Plan…
LLM Agents Are the Antidote to Walled Gardens
Samuele Marro, Philip Torr
While the Internet's core infrastructure was designed to be open and universal, today's application layer is dominated by closed, proprietary platforms. Open and interoperable APIs…
Large Language Models Miss the Multi-Agent Mark
Emanuele La Malfa, Gabriele La Malfa, Samuele Marro +5
Recent interest in Multi-Agent Systems of Large Language Models (MAS LLMs) has led to an increase in frameworks leveraging multiple LLMs to tackle complex tasks. However, much of t…
Language Models Are Implicitly Continuous
Samuele Marro, Davide Evangelista, X. Angelo Huang +3
Language is typically modelled with discrete sequences. However, the most successful approaches to language modelling, namely neural networks, are continuous and smooth function ap…
Code Simulation as a Proxy for High-order Tasks in Large Language Models
Emanuele La Malfa, Christoph Weinhuber, Orazio Torre +6
Many reasoning, planning, and problem-solving tasks share an intrinsic algorithmic nature: correctly simulating each step is a sufficient condition to solve them correctly. We coll…
Authenticated Delegation and Authorized AI Agents
Tobin South, Samuele Marro, Thomas Hardjono +5
The rapid deployment of autonomous AI agents creates urgent challenges around authorization, accountability, and access control in digital spaces. New standards are needed to know…
Jailbreaking Large Language Models in Infinitely Many Ways
Oliver Goldstein, Emanuele La Malfa, Felix Drinkall +2
We discuss the ``Infinitely Many Paraphrases'' attacks (IMP), a category of jailbreaks that leverages the increasing capabilities of a model to handle paraphrases and encoded commu…
A Scalable Communication Protocol for Networks of Large Language Models
Samuele Marro, Emanuele La Malfa, Jesse Wright +4
Communication is a prerequisite for collaboration. When scaling networks of AI-powered agents, communication must be versatile, efficient, and portable. These requisites, which we…
A Notion of Complexity for Theory of Mind via Discrete World Models
X. Angelo Huang, Emanuele La Malfa, Samuele Marro +3
Theory of Mind (ToM) can be used to assess the capabilities of Large Language Models (LLMs) in complex scenarios where social reasoning is required. While the research community ha…
Computational Asymmetries in Robust Classification
Samuele Marro, Michele Lombardi
In the context of adversarial robustness, we make three strongly related contributions. First, we prove that while attacking ReLU classifiers is -hard, ensuring their…
Image Embedding for Denoising Generative Models
Andrea Asperti, Davide Evangelista, Samuele Marro +1
Denoising Diffusion models are gaining increasing popularity in the field of generative modeling for several reasons, including the simple and stable training, the excellent genera…
Green NFTs: A Study on the Environmental Impact of Cryptoart Technologies
Samuele Marro, Luca Donno
We introduce a model of greenhouse gas emissions due to on-chain activity on Ethereum, focusing on cryptoart. We also estimate the impact of individual transactions on the environm…