Does providing additional context to automated AI auditors improve their effectiveness? Using the Petri tool to audit LLM coding agents, we test the impact of providing two types of resources (an external codebase and benchmark transcripts) to LLM auditors, across four auditor-target LLM pairs and three behaviours (har...
Ben Slater, Ryan Lundqvist, Leo Richter et al.· 0 citations
Bayesian Networks (BNs) are established tools for letting agents reason under uncertainty in sequential decision-making. They split a joint distribution into local conditional mechanisms arranged on a directed acyclic graph, which makes them modular, interpretable, and ready to perform probabilistic inference. Their cl...
Giovanni Briglia, Marco Lippi, Stefano Mariani et al.· 0 citations
LLMs are used as high-level controllers for embodied agents, but it remains unclear whether they support collaborative reasoning, such as anticipating a collaborator's actions in real-time teamwork without dialogue. We ask if observing the partner's state, exchanging object knowledge, and predicting the partner's next...
Adrián Szlatincsán, Filippo Ziliotto, Bruno Lepri et al.· 0 citations
Transparency in AI-supported decision systems is widely required but poorly defined. Existing approaches treat transparency as a property of systems or components, producing characteristic failures: assessments that do not transfer across organizational boundaries, stakeholder questions that cannot be formulated within...
Mattias Brännström, T. Xanthopoulou, Li-Li Jiang· 0 citations
Reach audiences
Advertise in front of researchers, engineers, and readers.
There is a specific challenge designers face in developing autonomous robots capable of open-ended learning. This challenge is how one can develop such systems in an ethically sound way when there are many unknowns during design time about their manner of deployment, what they can and will learn, and how these systems...
Maud van Lier, Ludovica Marinucci, Vieri Giuliano Santucci et al.· 0 citations
Target-aware multimodal instruction selection requires useful examples and an appropriate balance of supervision. Sample-level rankings can overrepresent similar content without optimizing this balance; group-level methods face coarse units, predefined set-level validation signals, and costly or inaccurate mixture sear...
A benchmark that contrasts authorization evidence for the same operation in its language track is introduced, which combines expert-annotated natural-language scenarios with executed and verified operations, plus externally sourced native-policy requests.
Hui-Hao Jing, Shao-Jin Chen, Wen-Bin Hu et al.· 0 citations
Industrial manipulation in flexible manufacturing, e.g., high-mix, low-volume (HMLV) electronics assembly, requires robot policies to adapt to changing products and production conditions. Such settings impose industrial process constraints, including product variants, moving material flows, finite execution windows, an...
Ming Shin Cindy Sung, Duan Leijiahao, Hao-Xiang Wang et al.· 0 citations
Game-Creation-Agents achieves stronger requirement satisfaction, core mechanics, content depth, and functional visuals than a comparable open pipeline, and in a side-by-side human study, raters also score GCA's games higher on every dimension and prefer them overall.
Xiang-Xin Zhou, Jia-Qi Tang, Kenney Ma et al.· 0 citations
Geospatial reasoning links VLMs to real-world action and decision making. Reliable reasoning requires accurate spatial information and effective spatial representations. However, current VLMs obtain this information mainly from language and vision. At larger geographic scales, limited visual observations make it diffic...
LLM-based information systems need safety guardrails. Most guardrails classify the prompt alone. If the prompt looks harmful, the system rejects it before any answer is generated. This is costly. Many rejected prompts would have received a safe response. Users lose help they should have received from the information sy...
The rapid advancement of foundation models and edge intelligence is transforming wireless networks from data-oriented communication systems into artificial intelligence (AI)-native service platforms. Token communications (TokenCom) has emerged as a promising paradigm that directly transmits task-oriented AI representat...
Yuquan Xiao, Qinghe Du, Chaoyang Zhang et al.· 0 citations
