skip to main content
US FlagAn official website of the United States government
dot gov icon
Official websites use .gov
A .gov website belongs to an official government organization in the United States.
https lock icon
Secure .gov websites use HTTPS
A lock ( lock ) or https:// means you've safely connected to the .gov website. Share sensitive information only on official, secure websites.

Explore Research Products in the PAR
It may take a few hours for recently added research products to appear in PAR search results.


Title: Nova : Value-based Negotiation of Norms
Specifying a normative multiagent system (nMAS) is challenging, because different agents often have conflicting requirements. Whereas existing approaches can resolve clear-cut conflicts, tradeoffs might occur in practice among alternative nMAS specifications with no apparent resolution. To produce an nMAS specification that is acceptable to each agent, we model the specification process as a negotiation over a set of norms. We propose an agent-based negotiation framework, where agents’ requirements are represented as values (e.g., patient safety, privacy, and national security), and an agent revises the nMAS specification to promote its values by executing a set of norm revision rules that incorporate ontology-based reasoning. To demonstrate that our framework supports creating a transparent and accountable nMAS specification, we conduct an experiment with human participants who negotiate against our agent. Our findings show that our negotiation agent reaches better agreements (with small p -value and large effect size) faster than a baseline strategy. Moreover, participants perceive that our agent enables more collaborative and transparent negotiations than the baseline (with small p -value and large effect size in particular settings) toward reaching an agreement.  more » « less
Award ID(s):
1908374
PAR ID:
10287342
Author(s) / Creator(s):
; ; ; ;
Date Published:
Journal Name:
ACM Transactions on Intelligent Systems and Technology
Volume:
12
Issue:
4
ISSN:
2157-6904
Page Range / eLocation ID:
1 to 29
Format(s):
Medium: X
Sponsoring Org:
National Science Foundation
More Like this
  1. ; (, IEEE Transactions on Control of Network Systems)
    This article is a study on the use of additive obfuscation signals to keep the reference values of the agents in the continuous-time Laplacian average consensus algorithm private from eavesdroppers. Obfuscation signals are perturbations that agents add to their local dynamics and their transmitted-out messages to conceal their private reference values. An eavesdropper is an agent inside or outside the network that has access to some subset of the interagent communication messages, and its knowledge set also includes the network topology. Rather than focusing on using a zero-sum and vanishing additive signal, our work determines the necessary and sufficient conditions that define the set of admissible obfuscation signals that do not perturb the convergence point of the algorithm from the average of the reference values of the agents. Of theoretical interest, our results show that this class includes nonvanishing signals as well. Given this broader class of admissible obfuscation signals, we define a deterministic notion of privacy preservation. In this definition, privacy preservation for an agent means that neither the private reference value nor a finite set of values to which the private reference value of the agent belongs to can be obtained. Then, we evaluate the agents’ privacy against eavesdroppers with different knowledge sets. 
    more » « less
  2. ; (, Proceedings of the American Control Conference)
    In this paper, we study the problem of privacy preservation of the continuous-time Laplacian static average consensus algorithm using additive perturbation signals. We consider this problem over a strongly connected and weight-balanced digraph. Starting from a local reference value, in static average consensus algorithm each agent constantly communicates with its neighboring agents to update its local state to compute the average of the reference values across the network. Since every agent transmits its local reference value to its in-neighbors, the reference value of the agents are trivially disclosed. In this paper, we investigate the possibility of preserving the privacy of the reference value of the agents by adding admissible perturbation signals to the local dynamics and the transmitted out signals of the agents. Admissible additive perturbation signals are those signals that do not perturb the final convergence point of the algorithm from the average of the reference values of the agents. Our results show that if an adversarial agent has access to the output of another agent and all the input signals transmitted to that agent, the adversary can discover the private reference value of that agent, regardless of the perturbation signals. Otherwise, the privacy of the agent can be preserved. We demonstrate our results through a numerical example. 
    more » « less
  3. ; ; ; (, Proceedings of the National Academy of Sciences)
    Regardless of how much data artificial intelligence agents have available, agents will inevitably encounter previously unseen situations in real-world deployments. Reacting to novel situations by acquiring new information from other people—socially situated learning—is a core faculty of human development. Unfortunately, socially situated learning remains an open challenge for artificial intelligence agents because they must learn how to interact with people to seek out the information that they lack. In this article, we formalize the task of socially situated artificial intelligence—agents that seek out new information through social interactions with people—as a reinforcement learning problem where the agent learns to identify meaningful and informative questions via rewards observed through social interaction. We manifest our framework as an interactive agent that learns how to ask natural language questions about photos as it broadens its visual intelligence on a large photo-sharing social network. Unlike active-learning methods, which implicitly assume that humans are oracles willing to answer any question, our agent adapts its behavior based on observed norms of which questions people are or are not interested to answer. Through an 8-mo deployment where our agent interacted with 236,000 social media users, our agent improved its performance at recognizing new visual information by 112%. A controlled field experiment confirmed that our agent outperformed an active-learning baseline by 25.6%. This work advances opportunities for continuously improving artificial intelligence (AI) agents that better respect norms in open social environments. 
    more » « less
  4. ; ; ; (, Empirical Software Engineering)
    Abstract Automatic Program Repair (APR) has garnered significant attention as a practical research domain focused on automatically fixing bugs in programs. While existing APR techniques primarily target imperative programming languages like C and Java, there is a growing need for effective solutions applicable to declarative software specification languages. This paper systematically investigates the capacity of Large Language Models (LLMs) to repair declarative specifications in Alloy, a declarative formal language used for software specification. We designed six different repair settings, encompassing single-agent and dual-agent paradigms, utilizing various LLMs. These configurations also incorporate different levels of feedback, including an auto-prompting mechanism for generating prompts autonomously using LLMs. Our study reveals that dual-agent with auto-prompting setup outperforms the other settings, albeit with a marginal increase in the number of iterations and token usage. This dual-agent setup demonstrated superior effectiveness compared to state-of-the-art Alloy APR techniques when evaluated on a comprehensive set of benchmarks. This work is the first to empirically evaluate LLM capabilities to repair declarative specifications, while taking into account recent trending LLM concepts such as LLM-based agents, feedback, auto-prompting, and tools, thus paving the way for future agent-based techniques in software engineering. 
    more » « less
  5. ; ; ; (, IEEE)
    Agent-based models (ABMs) are used to simulate human-subject experiments. A comprehensive understanding of these human systems often requires executing large numbers of simulations, but these requirements are constrained by computational and other resources. In this work, we build a framework of digital twins for modeling human-subject experiments. The framework has three modules: ABMs of player behaviors built from game data; extensions of these models to represent virtual assistants (agents that are exogenously manipulated to create controlled environments for human agents); and an uncertainty quantification module composed of functional ANOVA and a Gaussian process-based emulator. The emulator is built from the extended ABM; we focus on emulator validation. By incorporating experimental data and agent-based simulation data, our proposed framework enhances the virtual representation of the dynamics in human-subject word formation experiments, which we consider a digital twin. Networked anagram experiments are used as an exemplar to demonstrate the methods. 
    more » « less
  • Citation Formats
  • MLA
  • APA
  • Chicago
  • BibTeX
  • Save / Share this Record
  • Send to Email