Related papers: The Tool Illusion: Rethinking Tool Use in Web Agen…
To address intricate real-world tasks, there has been a rising interest in tool utilization in applications of large language models (LLMs). To develop LLM-based agents, it usually requires LLMs to understand many tool functions from…
We introduce a statistical agent based model to describe the phenomenon of drug abuse and its dynamical evolution at the individual and global level. The agents are heterogeneous with respect to their intrinsic inclination to drugs, to…
Large language models (LLMs) have precipitated a dramatic improvement in the legal domain, yet the deployment of standalone models faces significant limitations regarding hallucination, outdated information, and verifiability. Recently, LLM…
Large language model (LLM) agents with tool-calling capabilities are increasingly deployed in production systems, yet a fundamental reliability question remains under-explored: does the same agent behave the same way twice? We present a…
Much research in artificial intelligence is concerned with the development of autonomous agents that can interact effectively with other agents. An important aspect of such agents is the ability to reason about the behaviours of other…
In this work, we propose MetaAgent, an agentic paradigm inspired by the principle of learning-by-doing, where expertise is developed through hands-on practice and continual self-improvement. MetaAgent starts with a minimal workflow,…
An implicit expectation of asking users to rate agents, such as an AI decision-aid, is that they will use only relevant information -- ask them about an agent's benevolence, and they should consider whether or not it was kind. Behavioral…
The rapid proliferation of AI-generated image tools is transforming the art and design fields, challenging traditional notions of creativity and impacting both professional and non-professional users. For the purposes of this paper, we…
We present our preliminary work on a multi-agent system involving the complex human phenomena of identity and dynamic teams. We outline our ongoing experimentation into understanding how these factors can eliminate some of the naive…
Large language model-based agents are increasingly applied in the recommendation field due to their extensive knowledge and strong planning capabilities. While prior research has primarily focused on enhancing either the recommendation…
Tool agents interact with users through multi-turn dialogues to accomplish various tasks. Recent studies have adopted user simulation methods to develop these agents in multi-turn settings. However, existing user simulators tend to be…
AI Agents are changing the way work gets done, both in consumer and enterprise domains. However, the design patterns and architectures to build highly capable agents or multi-agent systems are still developing, and the understanding of the…
We investigate the emerging prospect of self-sovereign agents -- AI systems that can economically sustain and extend their own operation without human involvement. Recent advances in large language models and agent frameworks have…
The term 'agent' in artificial intelligence has long carried multiple interpretations across different subfields. Recent developments in AI capabilities, particularly in large language model systems, have amplified this ambiguity, creating…
A growing area of research investigates augmenting language models with tools (e.g., search engines, calculators) to overcome their shortcomings (e.g., missing or incorrect knowledge, incorrect logical inferences). Various few-shot…
Fulfilling user needs through Large Language Model multi-turn, multi-step tool-use is rarely a straightforward process. Real user interactions are inherently wild, being intricate, messy, and flexible. We identify three key challenges from…
Modelling and computational methods have been essential in advancing quantitative science, especially in the past two decades with the availability of vast amount of complex, voluminous, and heterogeneous data. In particular, there has been…
The observation that novice users seldom consult online help was made over twenty years ago. This observation still holds nowadays, although online help to the use of software for the general public has greatly improved in usability during…
The World Wide Web is a vast and continuously changing source of information where searching is a frequent, and sometimes critical, user task. Searching is not always the user's primary goal but an ancillary task that is performed to find…
LLM-powered agents are both a promising new technology and a source of complexity, where choices about models, tools, and prompting can affect their usefulness. While numerous benchmarks measure agent accuracy across domains, they mostly…