Related papers: Adaptive Contracts for Cost-Effective AI Delegatio…
We consider adaptive decision-making problems where an agent optimizes a cumulative performance objective by repeatedly choosing among a finite set of options. Compared to the classical prediction-with-expert-advice set-up, we consider…
In this paper, we present a probabilistic adaptation of an Assume/Guarantee contract formalism. For the sake of generality, we assume that the extended state machines used in the contracts and implementations define sets of runs on a given…
How much adversarial noise can protocols for interactive communication tolerate? This question was examined by Braverman and Rao (IEEE Trans. Inf. Theory, 2014) for the case of "robust" protocols, where each party sends messages only in…
The trade-off between accuracy and interpretability has long been a challenge in machine learning (ML). This tension is particularly significant for emerging interpretable-by-design methods, which aim to redesign ML algorithms for…
We investigate whether and why people might adjust compensation for workers who use AI tools. Across 13 studies (N = 4,956), participants consistently lowered compensation for workers who used AI compared to those who did not. This "AI…
The development of largely human-annotated benchmarks has driven the success of deep neural networks in various NLP tasks. To enhance the effectiveness of existing benchmarks, collecting new additional input-output pairs is often too costly…
Systems like ChatGPT and Claude assist billions through proactive dialogue-offering unsolicited, task-relevant information. Drawing on Cognitive Load Theory, we study how cognitive load shapes performance in AI-assisted knowledge work. We…
We consider an outsourcing problem where a software agent procures multiple services from providers with uncertain reliabilities to complete a computational task before a strict deadline. The service consumer requires a procurement strategy…
The remarkable capabilities of Large Language Model (LLM)-driven agents have enabled sophisticated systems to tackle complex, multi-step tasks, but their escalating costs threaten scalability and accessibility. This work presents the first…
Artificial intelligence (AI) is playing an increasingly significant role in our everyday lives. This trend is expected to continue, especially with recent pushes to move more AI to the edge. However, one of the biggest challenges associated…
We consider a sensor scheduling and remote estimation problem with one sensor and one estimator. At each time step, the sensor makes an observation on the state of a source, and then decides whether to transmit its observation to the…
I study whether and which expert incentives can be provided at what cost when the states of the world become non-contractible, but there is some noisy observation about the states that can be contracted upon. A principal hires an agent to…
As distributed artificial intelligence (AI) and multi-agent architectures grow increasingly complex, the need for adaptive, context-aware routing becomes paramount. This paper introduces an enhanced, adaptive routing algorithm tailored for…
Current language models decode text token by token according to probabilistic distribution, and determining the appropriate candidates for the next token is crucial to ensure generation quality. This study introduces adaptive decoding, a…
Edge AI is often framed as model compression and deployment under tight constraints. We argue a stronger operational thesis: Edge AI in realistic deployments is necessarily adaptive. In long-horizon operation, a fixed (non-adaptive)…
Contract scheduling is a general technique that allows to design a system with interruptible capabilities, given an algorithm that is not necessarily interruptible. Previous work on this topic has largely assumed that the interruption is a…
Explainable AI (XAI) is an active research area to interpret a neural network's decision by ensuring transparency and trust in the task-specified learned models. Recently, perturbation-based model analysis has shown better interpretation,…
Annotating large collections of textual data can be time consuming and expensive. That is why the ability to train models with limited annotation budgets is of great importance. In this context, it has been shown that under tight annotation…
We anticipate increased instances of humans and AI systems working together in what we refer to as a hybrid team. The increase in collaboration is expected as AI systems gain proficiency and their adoption becomes more widespread. However,…
"Vibe coding" and "vibe analytics" have been framed as a democratization of technical capability. This paper argues that AI-assisted methodology more broadly, or what I call "vibe methodology," also democratizes the failure modes specific…