Related papers: When Only the Final Text Survives: Implicit Execut…
The Internet of Electric Vehicles (IoEV) envisions a tightly coupled ecosystem of electric vehicles (EVs), charging infrastructure, and grid services, yet it remains vulnerable to cyberattacks, unreliable battery-state predictions, and…
We introduce the study of sequential information elicitation in strategic multi-agent systems. In an information elicitation setup a center attempts to compute the value of a function based on private information (a-k-a secrets) accessible…
AI-driven speech-to-text (STT) documentation systems are increasingly adopted in clinical settings to reduce documentation burden and improve workflow efficiency. However, adoption has outpaced systematic evaluation of socio-technical risks…
We present iBERT (interpretable-BERT), an encoder to produce inherently interpretable and controllable embeddings - designed to modularize and expose the discriminative cues present in language, such as semantic or stylistic structure. Each…
Agentic AI systems produce decision evidence at scale through execution telemetry, but property-level reconstruction often fails when an external party asks a specific governance question about a specific decision: the assembled evidence is…
Analyzing the behaviour of a concurrent program is made difficult by the number of possible executions. This problem can be alleviated by applying the theory of Mazurkiewicz traces to focus only on the canonical representatives of the…
Although data may be abundant, complete data is less so, due to missing columns or rows. This missingness undermines the performance of downstream data products that either omit incomplete cases or create derived completed data for…
LLM-based agents are increasingly deployed for complex tasks requiring planning, tool use, and interaction with external services. Their reliance on untrusted external content exposes them to indirect prompt injection (IPI), in which…
In Agentic AI, Large Language Models (LLMs) are increasingly used in the orchestration layer to coordinate multiple agents and to interact with external services, retrieval components, and shared memory. In this setting, failures are not…
Responsible AI has risen to the forefront of the AI research community. As neural network-based learning algorithms continue to permeate real-world applications, the field of Responsible AI has played a large role in ensuring that such…
Event extraction is challenging due to the complex structure of event records and the semantic gap between text and event. Traditional methods usually extract event records by decomposing the complex structure prediction task into multiple…
When automated decision systems fail, organizations frequently discover that formally compliant governance infrastructure cannot reconstruct what happened or why. This paper synthesizes an operational governance evidence framework --…
A semantic gap separates how users describe tasks from how tools are documented. As API ecosystems scale to tens of thousands of endpoints, static retrieval from the initial query alone cannot bridge this gap: the agent's understanding of…
Energy efficiency technologies (EETs) are crucial for saving energy and reducing carbon dioxide emissions. However, the diffusion of EETs in small and medium-sized enterprises is rather slow. Literature shows the interactions between…
As autonomous AI agents increasingly call other agents to complete tasks on behalf of a human principal, a structural accountability gap has emerged: the calling agent accepts the terms of service of the callee without any protocol-level…
We study a general task allocation problem, involving multiple agents that collaboratively accomplish tasks and where agents may fail to successfully complete the tasks assigned to them (known as execution uncertainty). The goal is to…
Automatic multi-agent systems aim to instantiate agent workflows without relying on manually designed or fixed orchestration. However, existing automatic MAS approaches remain only partially adaptive: they either perform training-free…
Sequence-to-Sequence (S2S) neural text generation models, especially the pre-trained ones (e.g., BART and T5), have exhibited compelling performance on various natural language generation tasks. However, the black-box nature of these models…
Target Safety Assessment (TSA) requires systematic integration of heterogeneous evidence, including genetic, transcriptomic, target homology, pharmacological, and clinical data, to evaluate potential safety liabilities of therapeutic…
Large pre-trained language models have recently enabled open-ended generation frameworks (e.g., prompt-to-text NLG) to tackle a variety of tasks going beyond the traditional data-to-text generation. While this framework is more general, it…