Searcharxiv⌕ Search

arXiv subjects

Brent Harrison

Publications and source records attributed to Brent Harrison.

At least 19 recordsLinked to original sources
arXiv2026

Persona-Guided LLM Agents for Task-Oriented Dialogue

Prior work has shown that large language models (LLMs) can express diverse personality traits in open-ended text generation. However, it remains unclear whether they can do so in a goal-directed dialogue without compromising task completion, and whether adapting to the user's personality improves the interaction quality. We study these questions in task-oriented dialogue (TOD), where a system helps a user accomplish a goal via multi-turn interaction. We build a training-free framework that simulates a TOD interaction between two LLMs: a user agent that exhibits a target personality and a system agent that adapts to the user while completing the task. To isolate the effect of adaptation, we vary how much the system knows about the user's personality across three conditions. In Neutral, the system receives no personality information. In Try, it infers the personality from dialogue cues. In Oracle, it is given the personality explicitly. We evaluate GPT-4o, Qwen3-Next-80B, and Gemini 2.0 Flash on Hotel and Restaurant dialogues from the Schema-Guided Dialogue (SGD) dataset, across the Big Five traits and their opposite poles. We find that the user agent can express personality while the system maintains strong task performance, although some traits are realized far less reliably than others. Adapting to the user's personality improves constraint satisfaction, inform rate, and user satisfaction, but lowers truthfulness, revealing a trade-off between personalization and task-grounding. Oracle's gains grow when the target trait is strongly expressed, whereas Try's gains are largely insensitive to realization strength. Overall, cue-based adaptation in Try best resolves this trade-off and offers a more reliable route to personality-aware TOD without fine-tuning.

cs.CL↗
arXiv2026

Fermionic Insights into Measurement-Based Quantum Computation: Circle Graph States Are Not Universal Resources

Measurement-based quantum computation (MBQC) is a strong contender for realizing quantum computers. A critical question for MBQC is the identification of resource graph states that can enable universal quantum computation. Any such universal family must have unbounded entanglement width, which is equivalent to the ability to produce any circle graph state from the states in the family using only local Clifford operations, local Pauli measurements, and classical communication. Yet, it was not previously known whether or not circle graph states themselves are a universal resource. We show that, in spite of their expressivity, circle graph states are not efficiently universal for MBQC (i.e., assuming $\mathsf{BQP} \neq \mathsf{BPP}$). We prove this by articulating a precise graph-theoretic correspondence between circle graph states and a certain subset of fermionic Gaussian states. This is accomplished by synthesizing a variety of techniques that allow us to handle both stabilizer states and fermionic Gaussian states at the same time. As such, we anticipate that our developments may have broader applications beyond the domain of MBQC as well.

quant-ph↗
arXiv2026

Putting fermions onto a digital quantum computer

Quantum computers are expected to become a powerful tool for studying physical quantum systems. Consequently, a number of quantum algorithms for studying the physical properties of such systems have been developed. While qubit-based quantum computers are naturally suited to the study of spin-1/2 systems, systems containing other degrees of freedom must first be encoded into qubits. Transformations to and from fermionic degrees of freedom have long been an important tool in physics and, now the simulation of fermionic systems on quantum computers based on qubits provides yet another application. In this perspective, we review methods for encoding fermionic degrees of freedom into qubits and attempt to dispel the persistent notion that fermionic systems beyond one dimension are fundamentally more difficult to deal with.

quant-ph↗
arXiv2025

The Goofus & Gallant Story Corpus for Practical Value Alignment

Values or principles are key elements of human society that influence people to behave and function according to an accepted standard set of social rules to maintain social order. As AI systems are becoming ubiquitous in human society, it is a major concern that they could violate these norms or values and potentially cause harm. Thus, to prevent intentional or unintentional harm, AI systems are expected to take actions that align with these principles. Training systems to exhibit this type of behavior is difficult and often requires a specialized dataset. This work presents a multi-modal dataset illustrating normative and non-normative behavior in real-life situations described through natural language and artistic images. This training set contains curated sets of images that are designed to teach young children about social principles. We argue that this is an ideal dataset to use for training socially normative agents given this fact.

cs.AI↗
arXiv2024

Ternary tree transformations are equivalent to linear encodings of the Fock basis

We consider two approaches to designing fermion-qubit mappings: (1) ternary tree transformations, which use Pauli representations of the Majorana operators that correspond to root-to-leaf paths of a tree graph and (2) linear encodings of the Fock basis, such as the Jordan-Wigner and Bravyi-Kitaev transformations, which store linear binary transformations of the fermionic occupation number vectors in the computational basis of qubits. These approaches have emerged as distinct concepts, with little notational consistency between them. In this paper we propose a universal description of fermion-qubit mappings, which reveals the relationship between ternary tree transformations and linear encodings. Using our notation, we show that every product-preserving ternary tree transformation is equivalent to a linear encoding of the Fock basis.

quant-ph↗
arXiv2024

Fermionic Mean-Field Theory as a Tool for Studying Spin Hamiltonians

The Jordan--Wigner transformation permits one to convert spin $1/2$ operators into spinless fermion ones, or vice versa. In some cases, it transforms an interacting spin Hamiltonian into a noninteracting fermionic one which is exactly solved at the mean-field level. Even when the resulting fermionic Hamiltonian is interacting, its mean-field solution can provide surprisingly accurate energies and correlation functions. Jordan--Wigner is, however, only one possible means of interconverting spin and fermionic degrees of freedom. Here, we apply several such techniques to the XXZ and $J_1\text{--}J_2$ Heisenberg models, as well as to the pairing or reduced BCS Hamiltonian, with the aim of discovering which of these mappings is most useful in applying fermionic mean-field theory to the study of spin Hamiltonians.

cond-mat.str-el↗
arXiv2024

Guiding Reinforcement Learning Using Uncertainty-Aware Large Language Models

Human guidance in reinforcement learning (RL) is often impractical for large-scale applications due to high costs and time constraints. Large Language Models (LLMs) offer a promising alternative to mitigate RL sample inefficiency and potentially replace human trainers. However, applying LLMs as RL trainers is challenging due to their overconfidence and less reliable solutions in sequential tasks. We address this limitation by introducing a calibrated guidance system that uses Monte Carlo Dropout to enhance LLM advice reliability by assessing prediction variances from multiple forward passes. Additionally, we develop a novel RL policy shaping method based on dynamic model average entropy to adjust the LLM's influence on RL policies according to guidance uncertainty. This approach ensures robust RL training by relying on reliable LLM guidance. To validate our contributions, we conduct extensive experiments in a Minigrid environment with three goals in varying environment sizes. The results showcase superior model performance compared to uncalibrated LLMs, unguided RL, and calibrated LLMs with different shaping policies. Moreover, we analyze various uncertainty estimation methods, demonstrating the effectiveness of average entropy in reflecting higher uncertainty in incorrect guidance. These findings highlight the persistent overconfidence in fine-tuned LLMs and underscore the importance of effective calibration in sequential decision-making problems.

cs.LG↗
arXiv2024

A Sierpinski Triangle Fermion-to-Qubit Transform

In order to simulate a system of fermions on a quantum computer, it is necessary to represent the fermionic states and operators on qubits. This can be accomplished in multiple ways, including the well-known Jordan-Wigner transform, as well as the parity, Bravyi-Kitaev, and ternary tree encodings. Notably, the Bravyi-Kitaev encoding can be described in terms of a classical data structure, the Fenwick tree. Here we establish a correspondence between a class of classical data structures similar to the Fenwick tree, and a class of one-to-one fermion-to-qubit transforms. We present a novel fermion-to-qubit encoding based on the recently discovered "Sierpinski tree" data structure, which matches the operator locality of the ternary tree encoding, and has the additional benefit of encoding the fermionic states as computational basis states. This is analogous to the formulation of the Bravyi-Kitaev encoding in terms of the Fenwick tree.

quant-ph↗
arXiv2024

A Sierpinski Triangle Data Structure for Efficient Array Value Update and Prefix Sum Calculation

The binary indexed tree, or Fenwick tree, is a data structure that can efficiently update values and calculate prefix sums in an array. It allows both of these operations to be performed in $O(\log_2 N)$ time. Here we present a novel data structure resembling the Sierpinski triangle, which accomplishes these operations with the same memory usage in $O(\log_3 N)$ time instead. We show this order to be optimal by making use of a connection to quantum computing.

cs.DS↗
arXiv2023

Reducing the qubit requirement of Jordan-Wigner encodings of $N$-mode, $K$-fermion systems from $N$ to $\lceil \log_2 {N \choose K} \rceil$

To simulate a fermionic system on a quantum computer, it is necessary to encode the state of the fermions onto qubits. Fermion-to-qubit mappings such as the Jordan-Wigner and Bravyi-Kitaev transformations do this using $N$ qubits to represent systems of $N$ fermionic modes. In this work, we demonstrate that for particle number conserving systems of $K$ fermions and $N$ modes, the qubit requirement can be reduced to the information theoretic minimum of $\lceil \log_2 {N \choose K} \rceil$. This will improve the feasibility of simulation of molecules and many-body systems on near-term quantum computers with limited qubit number.

quant-ph↗
arXiv2023

Controllable Neural Story Plot Generation via Reward Shaping

Language-modeling--based approaches to story plot generation attempt to construct a plot by sampling from a language model (LM) to predict the next character, word, or sentence to add to the story. LM techniques lack the ability to receive guidance from the user to achieve a specific goal, resulting in stories that don't have a clear sense of progression and lack coherence. We present a reward-shaping technique that analyzes a story corpus and produces intermediate rewards that are backpropagated into a pre-trained LM in order to guide the model towards a given goal. Automated evaluations show our technique can create a model that generates story plots which consistently achieve a specified goal. Human-subject studies show that the generated stories have more plausible event ordering than baseline plot generation techniques.

cs.CL↗
arXiv2022

Machine Learning Approaches for Principle Prediction in Naturally Occurring Stories

Value alignment is the task of creating autonomous systems whose values align with those of humans. Past work has shown that stories are a potentially rich source of information on human values; however, past work has been limited to considering values in a binary sense. In this work, we explore the use of machine learning models for the task of normative principle prediction on naturally occurring story data. To do this, we extend a dataset that has been previously used to train a binary normative classifier with annotations of moral principles. We then use this dataset to train a variety of machine learning models, evaluate these models and compare their results against humans who were asked to perform the same task. We show that while individual principles can be classified, the ambiguity of what "moral principles" represent, poses a challenge for both human participants and autonomous systems which are faced with the same task.

cs.CL↗
arXiv2022

DinoDroid: Testing Android Apps Using Deep Q-Networks

The large demand of mobile devices creates significant concerns about the quality of mobile applications (apps). Developers need to guarantee the quality of mobile apps before it is released to the market. There have been many approaches using different strategies to test the GUI of mobile apps. However, they still need improvement due to their limited effectiveness. In this paper, we propose DinoDroid, an approach based on deep Q-networks to automate testing of Android apps. DinoDroid learns a behavior model from a set of existing apps and the learned model can be used to explore and generate tests for new apps. DinoDroid is able to capture the fine-grained details of GUI events (e.g., the content of GUI widgets) and use them as features that are fed into deep neural network, which acts as the agent to guide app exploration. DinoDroid automatically adapts the learned model during the exploration without the need of any modeling strategies or pre-defined rules. We conduct experiments on 64 open-source Android apps. The results showed that DinoDroid outperforms existing Android testing tools in terms of code coverage and bug detection.

cs.SE↗
arXiv2022

Quantum Computing 2022

Quantum technology is full of figurative and literal noise obscuring its promise. In this overview, we will attempt to provide a sober assessment of the promise of quantum technology with a focus on computing. We provide a tour of quantum computing and quantum technology that is aimed to be comprehensible to scientists and engineers without becoming a popular account. The goal is not a comprehensive review nor a superficial introduction but rather to serve as a useful map to navigate the hype, the scientific literature, and upcoming press releases about quantum technology and quantum computing. We have aimed to cite the most recent topical reviews, key results, and guide the reader away from fallacies and towards active discussions in the current quantum computing literature. The goal of this article was to be pedantic and introductory without compromising on the science.

quant-ph↗
arXiv2022

Using Non-Stationary Bandits for Learning in Repeated Cournot Games with Non-Stationary Demand

Many past attempts at modeling repeated Cournot games assume that demand is stationary. This does not align with real-world scenarios in which market demands can evolve over a product's lifetime for a myriad of reasons. In this paper, we model repeated Cournot games with non-stationary demand such that firms/agents face separate instances of non-stationary multi-armed bandit problem. The set of arms/actions that an agent can choose from represents discrete production quantities; here, the action space is ordered. Agents are independent and autonomous, and cannot observe anything from the environment; they can only see their own rewards after taking an action, and only work towards maximizing these rewards. We propose a novel algorithm 'Adaptive with Weighted Exploration (AWE) $ε$-greedy' which is remotely based on the well-known $ε$-greedy approach. This algorithm detects and quantifies changes in rewards due to varying market demand and varies learning rate and exploration rate in proportion to the degree of changes in demand, thus enabling agents to better identify new optimal actions. For efficient exploration, it also deploys a mechanism for weighing actions that takes advantage of the ordered action space. We use simulations to study the emergence of various equilibria in the market. In addition, we study the scalability of our approach in terms number of total agents in the system and the size of action space. We consider both symmetric and asymmetric firms in our models. We found that using our proposed method, agents are able to swiftly change their course of action according to the changes in demand, and they also engage in collusive behavior in many simulations.

cs.LG↗
arXiv2022

Modelling Cournot Games as Multi-agent Multi-armed Bandits

We investigate the use of a multi-agent multi-armed bandit (MA-MAB) setting for modeling repeated Cournot oligopoly games, where the firms acting as agents choose from the set of arms representing production quantity (a discrete value). Agents interact with separate and independent bandit problems. In this formulation, each agent makes sequential choices among arms to maximize its own reward. Agents do not have any information about the environment; they can only see their own rewards after taking an action. However, the market demand is a stationary function of total industry output, and random entry or exit from the market is not allowed. Given these assumptions, we found that an $ε$-greedy approach offers a more viable learning mechanism than other traditional MAB approaches, as it does not require any additional knowledge of the system to operate. We also propose two novel approaches that take advantage of the ordered action space: $ε$-greedy+HL and $ε$-greedy+EL. These new approaches help firms to focus on more profitable actions by eliminating less profitable choices and hence are designed to optimize the exploration. We use computer simulations to study the emergence of various equilibria in the outcomes and do the empirical analysis of joint cumulative regrets.

cs.GT↗
arXiv2021

Multi-agent Reinforcement Learning for Decentralized Stable Matching

In the real world, people/entities usually find matches independently and autonomously, such as finding jobs, partners, roommates, etc. It is possible that this search for matches starts with no initial knowledge of the environment. We propose the use of a multi-agent reinforcement learning (MARL) paradigm for a spatially formulated decentralized two-sided matching market with independent and autonomous agents. Having autonomous agents acting independently makes our environment very dynamic and uncertain. Moreover, agents lack the knowledge of preferences of other agents and have to explore the environment and interact with other agents to discover their own preferences through noisy rewards. We think such a setting better approximates the real world and we study the usefulness of our MARL approach for it. Along with conventional stable matching case where agents have strictly ordered preferences, we check the applicability of our approach for stable matching with incomplete lists and ties. We investigate our results for stability, level of instability (for unstable results), and fairness. Our MARL approach mostly yields stable and fair outcomes.

cs.LG↗