arXiv subjects

Kirandeep Kaur

Publications and source records attributed to Kirandeep Kaur.

At least 19 recordsLinked to original sources

arXiv2026

Report on The 1st Workshop on Human-Centered Proactive and Personalized Agents for Interactive Information Access at CHIIR 2026

Interactive information access is increasingly moving beyond reactive query-response paradigms toward agentic systems that can personalize interaction, retain context, infer latent needs, recommend next steps, and initiate support. This shift creates new opportunities for adaptive and context-aware assistance, while also raising important questions about autonomy, privacy, trust, transparency, user welfare, and evaluation. The First Workshop on Human-Centered Proactive and Personalized Agents for Interactive Information Access provided an interdisciplinary forum for examining these questions across information retrieval, human-computer interaction, dialogue systems, AI ethics, cognitive science, learning technologies, and human-centered AI. Through invited talks, paper presentations, and open discussion, the workshop engaged with topics including calibrated initiative, knowledge-gap navigation, long-term memory, value-sensitive design, implicit personalization, AI-mediated care, proactive dialogue, and evaluation beyond task accuracy. A central theme across the workshop was that proactivity should not be understood only as earlier action or improved prediction, but as a form of initiative that must be appropriately timed, transparent, contestable, and aligned with user goals. This report summarizes the workshop and synthesizes the research challenges it surfaced for designing proactive and personalized agents in interactive information access.

cs.HC↗

arXiv2026

B-index polynomial for twisted knots

A twisted link is a generalization of a virtual link associated with link diagrams on closed surfaces, which may be non-orientable. In this paper, we generalize the notion of the index value for twisted knots. Based on this generalization, we introduce a polynomial invariant for twisted knots, called the $\mathcal{B}$-Index polynomial. Furthermore, we construct a family of twisted knots $\{D_n\}_{n\geq 1}$ with arc shift number $n$ and determine their $\mathcal{B}$-Index polynomials explicitly in terms of $n$. These results demonstrate the effectiveness and sensitivity of the $\mathcal{B}$-Index polynomial as an invariant of twisted knots. We also study the behavior of this polynomial under mirror images and orientation reversal. Furthermore, we conclude this paper by investigating the cosmetic crossing change conjecture and establishing a condition under which a crossing does not admit cosmetic behavior.

math.GT↗

arXiv2026

Knowing Isn't Understanding: Re-grounding Generative Proactivity with Epistemic and Behavioral Insight

Generative AI agents equate understanding with resolving explicit queries, an assumption that confines interaction to what users can articulate. This assumption breaks down when users themselves lack awareness of what is missing, risky, or worth considering. In such conditions, proactivity is not merely an efficiency enhancement, but an epistemic necessity. We refer to this condition as epistemic incompleteness: where progress depends on engaging with unknown unknowns for effective partnership. Existing approaches to proactivity remain narrowly anticipatory, extrapolating from past behavior and presuming that goals are already well defined, thereby failing to support users meaningfully. However, surfacing possibilities beyond a user's current awareness is not inherently beneficial. Unconstrained proactive interventions can misdirect attention, overwhelm users, or introduce harm. Proactive agents, therefore, require behavioral grounding: principled constraints on when, how, and to what extent an agent should intervene. We advance the position that generative proactivity must be grounded both epistemically and behaviorally. Drawing on the philosophy of ignorance and research on proactive behavior, we argue that these theories offer critical guidance for designing agents that can engage responsibly and foster meaningful partnerships.

cs.CY↗

arXiv2026

PROPER Agents: Proactivity Driven Personalized Agents for Advancing Knowledge Gap Navigation

Current approaches to proactive assistance move beyond the ask-and-respond paradigm by anticipating user needs. In practice, they either burden users with clarifying questions or rely on context-based extrapolation, often leading to unnecessary or mistimed interventions. Such systems lack explicit mechanisms to model users' knowledge gaps, resulting in incomplete or suboptimal task outcomes. To address this, we propose PROPER, a framework that explicitly models user-specific knowledge gaps in a controlled manner. Central to our approach is the notion of dimensions: structured, task-relevant factors that define the considerations required for effective task completion. Given a user query, the DGA (Dimension Generating Agent) identifies explicit dimensions (from the user's query) and generates a set of candidate implicit dimensions capturing unarticulated aspects of the task. The RGA (Response Generating Agent) integrates both explicit and implicit dimensions selectively to produce personalized, context-aware, and proactively informative responses. We evaluate PROPER across multiple domains using a structured, gap-aware rubric that measures coverage, initiative appropriateness, and intent alignment. PROPER improves on quality scores and win rates across all domains, achieving up to 84% gains in single-turn evaluation and consistent dominance in multi-turn interactions. All code for PROPER is available at: https://github.com/i-kiran/ProPer-Agent.

cs.LG↗

arXiv2025

QLENS: Towards A Quantum Perspective of Language Transformers

In natural language processing, current methods for understanding Transformers are successful at identifying intermediate predictions during a model's inference. However, these approaches function as limited diagnostic checkpoints, lacking a mathematical framework for mechanistically modeling how each layer facilitates transitions between these evolving states. This interpretability gap and past successes of interdisciplinary outlooks inspire us to turn to physics in search of a descriptive mathematical framework for Transformers. We observe that language models are intrinsically probabilistic, an attribute that is echoed in the core postulates of quantum mechanics. This parallel inspires us to translate insights from this discipline to that of natural language processing. Towards this objective, we propose QLENS a novel attempt to develop a physics-based perspective on the Transformer generation process. Under QLENS, a Transformer is studied by converting its latent activations into a state vector in a Hilbert space derived from the model's output units. This state subsequently evolves through hidden layers - reformulated as unitary operators and analogously defined Hamiltonians - during inference. The model's final probability distribution is obtained by applying the Born rule to the end state using a specific measurement operator. To demonstrate QLENS's potential, we conduct a proof-of-concept by probing a toy Transformer to investigate the influence of individual layers in a model's prediction trajectory. We present our work as a foundation for cross-domain insights to be leveraged towards a broader understanding of Transformers.

cs.LG↗

arXiv2025

Efficient and Responsible Adaptation of Large Language Models for Robust and Equitable Top-k Recommendations

Conventional recommendation systems (RSs) are typically optimized to enhance performance metrics uniformly across all training samples, inadvertently overlooking the needs of diverse user populations. The performance disparity among various populations can harm the model's robustness to sub-populations due to the varying user properties. While large language models (LLMs) show promise in enhancing RS performance, their practical applicability is hindered by high costs, inference latency, and degraded performance on long user queries. To address these challenges, we propose a hybrid task allocation framework designed to promote social good by equitably serving all user groups. By adopting a two-phase approach, we promote a strategic assignment of tasks for efficient and responsible adaptation of LLMs. Our strategy works by first identifying the weak and inactive users that receive a suboptimal ranking performance by RSs. Next, we use an in-context learning approach for such users, wherein each user interaction history is contextualized as a distinct ranking task. We evaluate our hybrid framework by incorporating eight different recommendation algorithms and three different LLMs -- both open and close-sourced. Our results on three real-world datasets show a significant reduction in weak users and improved robustness to subpopulations without disproportionately escalating costs.

cs.IR↗

arXiv2025

Beyond Static Evaluation: Rethinking the Assessment of Personalized Agent Adaptability in Information Retrieval

Personalized AI agents are becoming central to modern information retrieval, yet most evaluation methodologies remain static, relying on fixed benchmarks and one-off metrics that fail to reflect how users' needs evolve over time. These limitations hinder our ability to assess whether agents can meaningfully adapt to individuals across dynamic, longitudinal interactions. In this perspective paper, we propose a conceptual lens for rethinking evaluation in adaptive personalization, shifting the focus from static performance snapshots to interaction-aware, evolving assessments. We organize this lens around three core components: (1) persona-based user simulation with temporally evolving preference models; (2) structured elicitation protocols inspired by reference interviews to extract preferences in context; and (3) adaptation-aware evaluation mechanisms that measure how agent behavior improves across sessions and tasks. While recent works have embraced LLM-driven user simulation, we situate this practice within a broader paradigm for evaluating agents over time. To illustrate our ideas, we conduct a case study in e-commerce search using the PersonalWAB dataset. Beyond presenting a framework, our work lays a conceptual foundation for understanding and evaluating personalization as a continuous, user-centric endeavor.

cs.IR↗

arXiv2025

Extending Quasi-alternating Links II

Champanerkar and Kofman [1] introduced an innovative method for constructing quasi-alternating links by substituting a quasi-alternating crossing c in a quasi-alternating link with a rational tangle of the same type. This construction was later extended by Chbili and Kaur [2] for any alternating tangle of same type. However, this approach does not generally apply to non-alternating tangles or alternating tangles of opposite types, although there are examples where it holds for alternating tangles of opposite type and certain non-alternating tangles. This raises a natural question to find the conditions and specific tangles for which this approach is applicable. In this paper, we explore this question by identifying several conditions under which this construction of new quasi-alternating links can still be valid for alternating tangles of opposite types. Additionally, we establish specific families of non-alternating tangles for which this construction is effective in creating new quasi-alternating links.

math.GT↗

arXiv2025

Effects of noise-induced coherence on the performance of a four-level laser heat engine

In this work, we study the effect of noise-induced coherence on the performance analysis of a degenerate four-level quantum heat engine with particular focus on the universal nature of efficiency, which refers to the appearance of the first two universal terms $η_C/2$ and $η_C^2/8$ in series expansion of the efficiency at maximum power under a left-right symmetry in the system. Firstly, for a two-parameter optimization scheme, we derive an analytic expression for the efficiency at maximum power for the near-equilibrium condition and show that presence of noise-induced coherence breaks the left-right symmetry of the system. However, when the operation of the engine is restricted to either high-temperature or low-temperature regime, we discuss the conditions under which the left-right symmetry can be retained in each case, giving rise to the universal characteristic of efficiency. In case of one-parameter optimization, we show that while the universality of the first linear term $η_c/2$ is robust and holds consistently across all conditions, the universality of the quadratic term $η_C^2/8$ depends on the constraints imposed on the control parameters. Finally, we examine the behavior of power as a function of noise-induced coherence parameter highlighting the role of matter-field coupling in determining the suitable operation regime for the heat engine to reap the benefits of noise-induced coherence.

quant-ph↗

arXiv2025

Dynamic Evaluation Framework for Personalized and Trustworthy Agents: A Multi-Session Approach to Preference Adaptability

Recent advancements in generative AI have significantly increased interest in personalized agents. With increased personalization, there is also a greater need for being able to trust decision-making and action taking capabilities of these agents. However, the evaluation methods for these agents remain outdated and inadequate, often failing to capture the dynamic and evolving nature of user interactions. In this conceptual article, we argue for a paradigm shift in evaluating personalized and adaptive agents. We propose a comprehensive novel framework that models user personas with unique attributes and preferences. In this framework, agents interact with these simulated users through structured interviews to gather their preferences and offer customized recommendations. These recommendations are then assessed dynamically using simulations driven by Large Language Models (LLMs), enabling an adaptive and iterative evaluation process. Our flexible framework is designed to support a variety of agents and applications, ensuring a comprehensive and versatile evaluation of recommendation strategies that focus on proactive, personalized, and trustworthy aspects.

cs.IR↗

arXiv2024

Asymmetric Quantum Harmonic Otto Engine Under Hot Squeezed Thermal Reservoir

We study a quantum harmonic Otto engine under a hot squeezed thermal reservoir with asymmetry between the two adiabatic branches introduced by considering different speeds of the driving protocols. In the first configuration, the driving protocol for the expansion stroke is sudden-switch in nature and compression stroke is driven adiabatically, while the second configuration deals with the converse situation. In both cases, we obtain analytic expressions for the upper bound on efficiency and efficiency at optimal work output, which reveals a significant difference between the two configurations. Additionally, we find that the maximum achievable efficiency in sudden expansion case is 1/2 only while it approaches unity for the sudden compression stroke. Further, we study the effect of increasing degree of squeezing on the efficiency and work output of the engine and indicate the optimal operational regime for both configurations under consideration. Finally, by studying the full phase-diagram of the Otto cycle we observe that the operational region of the engine mode grows with increasing squeezing at the expense of refrigeration regime.

quant-ph↗

arXiv2024

Towards Fairness in Provably Communication-Efficient Federated Recommender Systems

To reduce the communication overhead caused by parallel training of multiple clients, various federated learning (FL) techniques use random client sampling. Nonetheless, ensuring the efficacy of random sampling and determining the optimal number of clients to sample in federated recommender systems (FRSs) remains challenging due to the isolated nature of each user as a separate client. This challenge is exacerbated in models where public and private features can be separated, and FL allows communication of only public features (item gradients). In this study, we establish sample complexity bounds that dictate the ideal number of clients required for improved communication efficiency and retained accuracy in such models. In line with our theoretical findings, we empirically demonstrate that RS-FairFRS reduces communication cost (~47%). Second, we demonstrate the presence of class imbalance among clients that raises a substantial equity concern for FRSs. Unlike centralized machine learning, clients in FRS can not share raw data, including sensitive attributes. For this, we introduce RS-FairFRS, first fairness under unawareness FRS built upon random sampling based FRS. While random sampling improves communication efficiency, we propose a novel two-phase dual-fair update technique to achieve fairness without revealing protected attributes of active clients participating in training. Our results on real-world datasets and different sensitive features illustrate a significant reduction in demographic bias (~approx40\%), offering a promising path to achieving fairness and communication efficiency in FRSs without compromising the overall accuracy of FRS.

cs.IR↗

arXiv2024

Efficient and Responsible Adaptation of Large Language Models for Robust Top-k Recommendations

Conventional recommendation systems (RSs) are typically optimized to enhance performance metrics uniformly across all training samples. This makes it hard for data-driven RSs to cater to a diverse set of users due to the varying properties of these users. The performance disparity among various populations can harm the model's robustness with respect to sub-populations. While recent works have shown promising results in adapting large language models (LLMs) for recommendation to address hard samples, long user queries from millions of users can degrade the performance of LLMs and elevate costs, processing times and inference latency. This challenges the practical applicability of LLMs for recommendations. To address this, we propose a hybrid task allocation framework that utilizes the capabilities of both LLMs and traditional RSs. By adopting a two-phase approach to improve robustness to sub-populations, we promote a strategic assignment of tasks for efficient and responsible adaptation of LLMs. Our strategy works by first identifying the weak and inactive users that receive a suboptimal ranking performance by RSs. Next, we use an in-context learning approach for such users, wherein each user interaction history is contextualized as a distinct ranking task and given to an LLM. We test our hybrid framework by incorporating various recommendation algorithms -- collaborative filtering and learning-to-rank recommendation models -- and two LLMs -- both open and close-sourced. Our results on three real-world datasets show a significant reduction in weak users and improved robustness of RSs to sub-populations $(\approx12\%)$ and overall performance without disproportionately escalating costs.

cs.IR↗

arXiv2023

Aperiodic MEG abnormality in patients with focal to bilateral tonic-clonic seizures

Aperiodic activity is a physiologically distinct component of the electrophysiological power spectrum. It is suggested to reflect the balance of excitation and inhibition in the brain, within selected frequency bands. However, the impact of recurrent seizures on aperiodic activity remains unknown, particularly in patients with severe bilateral seizures. Here, we hypothesised greater aperiodic abnormality in the epileptogenic zone, in patients with focal to bilateral tonic clonic (FBTC) seizures, and earlier age of seizure onset. Pre-operative magnetoencephalography (MEG) recordings were acquired from 36 patients who achieved complete seizure freedom (Engel I outcome) post-surgical resection. A normative whole brain map of the aperiodic exponent was computed by averaging across subjects for each region in the hemisphere contralateral to the side of resection. Selected regions of interest were then tested for abnormality using deviations from the normative map in terms of z-scores. Resection masks drawn from postoperative structural imaging were used as an approximation of the epileptogenic zone. Patients with FBTC seizures had greater abnormality compared to patients with focal onset seizures alone in the resection volume (p=0.003, area under the ROC curve = 0.78 ). Earlier age of seizure onset was correlated with greater abnormality of the aperiodic exponent in the resection volume (correlation coefficient = -0.3, p= 0.04)) as well as the whole cortex (rho = -0.33, p=0.03). The abnormality of the aperiodic exponent did not significantly differ between the resected and non-resected regions of the brain. Abnormalities in aperiodic components relate to important clinical characteristics such as severity and age of seizure onset. This suggests the potential use of the aperiodic band power component as a marker for severity of epilepsy.

q-bio.NC↗

arXiv2023

Performance analysis of quantum harmonic Otto engine and refrigerator under a trade-off figure of merit

We investigate the optimal performance of quantum Otto engine and refrigeration cycles of a time-dependent harmonic oscillator under a trade-off figure of merit for both adiabatic and nonadiabatic (sudden-switch) frequency modulations. For heat engine (refrigerator), the chosen trade-off figure of merit is an objective function defined by the product of efficiency (coefficient of performance) and work output (cooling load), thus representing a compromise between them. We obtain analytical expressions for the efficiency and coefficient of performance of the harmonic Otto cycle for the optimal performance of the thermal machine in various operational regimes. Particularly, in the sudden-switch regime, we discuss the implications of the nonadiabatic driving on the performance of the thermal machine under consideration, and obtain analytic expressions for the maximum achievable efficiency and coefficient of performance of the harmonic Otto thermal machine. Further, by carrying out a detailed comparative analysis of the heat engine operating under the chosen trade-off objective function with one operating at maximum work output, we show that the trade-off objective functions have desirable operation only for the adiabatic driving whereas for the sudden switch operation, the choice of a trade-off objective function does not make much difference as the performance of the engine is dominated by frictional effects.

quant-ph↗

arXiv2023

Optimization analysis of an endoreversible quantum heat engine with efficient power function

We study the optimal performance of an endoreversible quantum dot heat engine, in which the heat transfer between the system and baths is mediated by qubits, operating under the conditions of a trade-off objective function known as maximum efficient power function defined by the product of power and efficiency of the engine. First, we numerically study the optimization of the efficient power function for the engine under consideration. Then, we obtain some analytic results by applying hightemperature limit and compare the performance of the engine at maximum efficient power functionto the engine operating in the maximum power regime. We find that the engine operating at maximum efficient power function produces at least 88.89% of the maximum power output while at the same time reduces the power loss due to entropy production by considerable amount. We conclude by studying the stochastic simulations of the efficiency of the engine in maximum power and maximum efficient power regime. We find that the engine operating at maximum power is subjected to less power fluctuations as compared to the on one operating at maximum efficient power function.

cond-mat.stat-mech↗

arXiv2020

Unified trade-off optimization of a three-level quantum refrigerator

We study the optimal performance of a three-level quantum refrigerator using a trade-off objective function, $Ω$ function, which represents a compromise between the energy benefits and the energy losses of a thermal device. First, we optimize the performance of our refrigerator by employing a two-parameter optimization scheme and show that the first two-terms in the series expansion of the obtained coefficient of performance (COP) match with those of some classical models of refrigerator. Then, in the high-temperature limit, optimizing with respect to one parameter while constraining the other one, we obtain the lower and upper bounds on the COP for both strong as well as weak (intermediate) matter-field coupling conditions. In the strong matter-field coupling regime, the obtained bounds on the COP exactly match with the bounds already known for some models of classical refrigerators. Further for weak matter-field coupling, we derive some new bounds on the the COP of the refrigerator which lie beyond the range covered by bounds obtained for strong matter-field coupling. Finally, in the parameter regime where both cooling power and $Ω$ function can be maximized, we compare the cooling power of the quantum refrigerator at maximum $Ω$ function with the maximum cooling power.

quant-ph↗

arXiv2020

Extending Quasi-Alternating Links

Champanerkar and Kofman introduced an interesting way to construct new examples of quasi-alternating links from existing ones. Actually, they proved that replacing a quasi-alternating crossing c in a quasi-alternating link by a rational tangle of same type yields a new quasi-alternating link. This construction has been extended to alternating algebraic tangles and applied to characterize all quasi-alternating Montesinos links. In this paper, we extend this technique to any alternating tangle of same type as c. As an application, we give new examples of quasi-alternating knots of 13 and 14 crossings. Moreover, we prove that the Jones polynomial of a quasi-alternating link that is obtained in this way has no gap if the original link has no gap in its Jones polynomial. This supports a conjecture introduced in arXiv:1810.11773 [math.GT], which states that Jones polynomial of any prime quasi-alternating link except (2; n)-torus link has no gap.

math.GT↗