Related papers: Budget-Constrained Agentic Large Language Models: …
To handle underspecified or ambiguous queries, AI assistants need a policy for managing their uncertainty to determine (a) when to guess the user intent and answer directly, (b) when to enumerate and answer multiple possible intents, and…
Full models of the world require complex knowledge of immense detail. While pre-trained large models have been hypothesized to contain similar knowledge due to extensive pre-training on vast amounts of internet scale data, using them…
Voice-controlled dialog systems have become immensely popular due to their ability to perform a wide range of actions in response to diverse user queries. These agents possess a predefined set of skills or intents to fulfill specific user…
Ranking ensemble is a critical component in real recommender systems. When a user visits a platform, the system will prepare several item lists, each of which is generally from a single behavior objective recommendation model. As multiple…
Although large language model (LLM) based multi-agent systems (MAS) show their capability to solve complex tasks and achieve higher performance over single agent systems, they lead to huge computational overheads because of heavy…
Agent assistance during human-human customer support spoken interactions requires triggering workflows based on the caller's intent (reason for call). Timeliness of prediction is essential for a good user experience. The goal is for a…
Large language models (LLMs) achieved remarkable performance across various tasks. However, they face challenges in managing long documents and extended conversations, due to significantly increased computational requirements, both in…
This paper proposes TIP-Search, a time-predictable inference scheduling framework for real-time market prediction under uncertain workloads. Motivated by the strict latency demands in high-frequency financial systems, TIP-Search dynamically…
Historically, programming language semantics has focused on assigning a precise mathematical meaning to programs. That meaning is a function from the program's input domain to its output domain determined solely by its syntactic structure.…
Deploying language models as autonomous agents requires more than per-task accuracy: when an agent faces a queue of problems under a finite token budget, it must decide which to attempt, in what order, and how much compute to commit to…
With the rise of service computing, cloud computing, and IoT, service ecosystems are becoming increasingly complex. The intricate interactions among intelligent agents make abnormal emergence analysis challenging, as traditional causal…
In-context learning is a promising paradigm that utilizes in-context examples as prompts for the predictions of large language models. These prompts are crucial for achieving strong performance. However, since the prompts need to be sampled…
The inference-time resource costs of large language and vision models present a growing challenge in production deployments. We propose the use of foundation model programs, i.e., programs that can invoke foundation models with varying…
Intelligent agents working in real-world environments must be able to learn about the environment and its capabilities which enable them to take actions to change to the state of the world to complete a complex multi-step task in a…
Generative Artificial Intelligence (AI), because of its emergent abilities, has empowered various fields, one typical of which is large language models (LLMs). One of the typical application fields of Generative AI is large language models…
Current communication technologies face limitations in terms of theoretical capacity, spectrum availability, and power resources. Pragmatic communication, leveraging terminal intelligence for selective data transmission, offers resource…
This paper delves into an advanced implementation of Chain-of-Thought-Prompting in Large Language Models, focusing on the use of tools (or "plug-ins") within the explicit reasoning paths generated by this prompting method. We find that…
The ability to predict a user's information need would have wide-ranging implications, from saving time and effort to mitigating vocabulary gaps. We study how to interactively predict a user's information need by letting them select a…
With the recent surge of NLP technologies in the financial domain, banks and other financial entities have adopted virtual agents (VA) to assist customers. A challenging problem for VAs in this domain is determining a user's reason or…
Large language models (LLMs) are increasingly being used to generate comprehensive, knowledge-intensive reports. However, while these models are trained on diverse academic papers and reports, they are not exposed to the reasoning processes…