arXiv subjects

Ankush Agarwal

Publications and source records attributed to Ankush Agarwal.

At least 19 recordsLinked to original sources

arXiv2026

Implied Volatility Expansions for VIX Options in Forward Variance Models

We develop closed-form expansions for the implied volatility of VIX options within the class of forward variance models. Our approach builds on weak-approximation techniques for VIX option prices and yields explicit implied volatility expansions with computable correction terms. The resulting formulas enable fast and accurate calibration without requiring numerical root-finding using option prices. We illustrate the performance of the proposed expansions in both standard and rough Bergomi-type models, as well as in mixed specifications, and demonstrate their accuracy through numerical experiments.

q-fin.CP↗

arXiv2026

Forecasting implied volatility surface with generative diffusion models

Diffusion Probabilistic Model (DDPM) for generating one-day-ahead arbitrage-free implied volatility surfaces. To capture the path-dependent nature of volatility dynamics, we condition our model on a set of market variables, including exponentially weighted moving averages (EWMAs) of historical vol-surfaces, returns and squared returns of the underlying asset, and scalar risk indicators associated with the underlying asset. A key challenge is that historical data often contains arbitrage opportunities in the earlier dataset for training, which conflicts with the goal of generating arbitrage-free surfaces. We address this by using a parameter-free weighting scheme based on the signal-to-noise ratio (SNR) to incorporate the arbitrage penalty into the loss function. The scheme dynamically adjusts the penalty strength across the diffusion process. Through numerical experiments using market data, we demonstrate the superior performance of our proposed model in volatility forecasting compared to existing approaches.

q-fin.CP↗

arXiv2026

EnterpriseLab: A Full-Stack Platform for developing and deploying agents in Enterprises

Deploying AI agents in enterprise environments requires balancing capability with data sovereignty and cost constraints. While small language models offer privacy-preserving alternatives to frontier models, their specialization is hindered by fragmented development pipelines that separate tool integration, data generation, and training. We introduce EnterpriseLab, a full-stack platform that unifies these stages into a closed-loop framework. EnterpriseLab provides (1) a modular environment exposing enterprise applications via Model Context Protocol, enabling seamless integration of proprietary and open-source tools; (2) automated trajectory synthesis that programmatically generates training data from environment schemas; and (3) integrated training pipelines with continuous evaluation. We validate the platform through EnterpriseArena, an instantiation with 15 applications and 140+ tools across IT, HR, sales, and engineering domains. Our results demonstrate that 8B-parameter models trained within EnterpriseLab match GPT-4o's performance on complex enterprise workflows while reducing inference costs by 8-10x, and remain robust across diverse enterprise benchmarks, including EnterpriseBench (+10%) and CRMArena (+10%). EnterpriseLab provides enterprises a practical path to deploying capable, privacy-preserving agents without compromising operational capability.

cs.AI↗

arXiv2026

Numerical approximation of McKean-Vlasov SDEs via stochastic gradient descent

We propose a novel approach to numerically approximate McKean-Vlasov stochastic differential equations (MV-SDE) using stochastic gradient descent (SGD) while avoiding the use of interacting particle systems (IPS) {and the associated simulation costs required to achieve the ``propagation of chaos'' limit}. The SGD technique is deployed to solve a Euclidean minimization problem, obtained by first representing the MV-SDE as a minimization problem over the set of continuous functions of time, and then approximating the domain with a finite-dimensional subspace. Convergence is established by proving certain intermediate stability and moment estimates of the relevant stochastic processes, including the tangent processes. Numerical experiments illustrate the competitive performance of our SGD based method compared to the IPS benchmarks. This work offers a theoretical foundation for using the SGD method in the context of numerical approximation of MV-SDEs, and provides analytical tools to study its stability and convergence.

math.NA↗

arXiv2025

Can LLMs Help You at Work? A Sandbox for Evaluating LLM Agents in Enterprise Environments

Enterprise systems are crucial for enhancing productivity and decision-making among employees and customers. Integrating LLM based systems into enterprise systems enables intelligent automation, personalized experiences, and efficient information retrieval, driving operational efficiency and strategic growth. However, developing and evaluating such systems is challenging due to the inherent complexity of enterprise environments, where data is fragmented across multiple sources and governed by sophisticated access controls. We present EnterpriseBench, a comprehensive benchmark that simulates enterprise settings, featuring 500 diverse tasks across software engineering, HR, finance, and administrative domains. Our benchmark uniquely captures key enterprise characteristics including data source fragmentation, access control hierarchies, and cross-functional workflows. Additionally, we provide a novel data generation pipeline that creates internally consistent enterprise tasks from organizational metadata. Experiments with state-of-the-art LLM agents demonstrate that even the most capable models achieve only 41.8% task completion, highlighting significant opportunities for improvement in enterprise-focused AI systems.

cs.LG↗

arXiv2025

Finding Needles in Images: Can Multimodal LLMs Locate Fine Details?

While Multi-modal Large Language Models (MLLMs) have shown impressive capabilities in document understanding tasks, their ability to locate and reason about fine-grained details within complex documents remains understudied. Consider searching a restaurant menu for a specific nutritional detail or identifying a disclaimer in a lengthy newspaper article tasks that demand careful attention to small but significant details within a broader narrative, akin to Finding Needles in Images (NiM). To address this gap, we introduce NiM, a carefully curated benchmark spanning diverse real-world documents including newspapers, menus, and lecture images, specifically designed to evaluate MLLMs' capability in these intricate tasks. Building on this, we further propose Spot-IT, a simple yet effective approach that enhances MLLMs capability through intelligent patch selection and Gaussian attention, motivated from how humans zoom and focus when searching documents. Our extensive experiments reveal both the capabilities and limitations of current MLLMs in handling fine-grained document understanding tasks, while demonstrating the effectiveness of our approach. Spot-IT achieves significant improvements over baseline methods, particularly in scenarios requiring precise detail extraction from complex layouts.

cs.CV↗

arXiv2025

Robust valuation and optimal harvesting of forestry resources in the presence of catastrophe risk and parameter uncertainty

We determine forest lease value and optimal harvesting strategies under model parameter uncertainty within stochastic bio-economic models that account for catastrophe risk. Catastrophic events are modeled as a Poisson point process, with a two-factor stochastic convenience yield model capturing the lumber spot price dynamics. Using lumber futures and US wildfire data, we estimate model parameters through a Kalman filter and maximum likelihood estimation and define the model parameter uncertainty set as the 95% confidence region. We numerically determine the forest lease value under catastrophe risk and parameter uncertainty using reflected backward stochastic differential equations (RBSDEs) and establish conservative and optimistic bounds for lease values and optimal stopping boundaries for harvesting, facilitating Monte Carlo simulations. Numerical experiments further explore how parameter uncertainty, catastrophe intensity, and carbon sequestration impact the lease valuation and harvesting decision. In particular, we explore the costs arising from this form of uncertainty in the form of a reduction of the lease value. These are implicit costs that can be attributed to climate risk and will be emphasized through the importance of forestry resources in the energy transition process. We conclude that in the presence of parameter uncertainty, it is better to lean toward a conservative strategy reflecting, to some extent, the worst case than being overly optimistic. Our results also highlight the critical role of convenience yield in determining optimal harvesting strategies.

q-fin.MF↗

arXiv2025

Hybrid Graphs for Table-and-Text based Question Answering using LLMs

Answering questions that require reasoning and aggregation across both structured (tables) and unstructured (raw text) data sources presents significant challenges. Current methods rely on fine-tuning and high-quality, human-curated data, which is difficult to obtain. Recent advances in Large Language Models (LLMs) have shown promising results for multi-hop question answering (QA) over single-source text data in a zero-shot setting, yet exploration into multi-source Table-Text QA remains limited. In this paper, we present a novel Hybrid Graph-based approach for Table-Text QA that leverages LLMs without fine-tuning. Our method constructs a unified Hybrid Graph from textual and tabular data, pruning information based on the input question to provide the LLM with relevant context concisely. We evaluate our approach on the challenging Hybrid-QA and OTT-QA datasets using state-of-the-art LLMs, including GPT-3.5, GPT-4, and LLaMA-3. Our method achieves the best zero-shot performance on both datasets, improving Exact Match scores by up to 10% on Hybrid-QA and 5.4% on OTT-QA. Moreover, our approach reduces token usage by up to 53% compared to the original context.

cs.CL↗

arXiv2024

Integrating Artificial Intelligence Models and Synthetic Image Data for Enhanced Asset Inspection and Defect Identification

In the past utilities relied on in-field inspections to identify asset defects. Recently, utilities have started using drone-based inspections to enhance the field-inspection process. We consider a vast repository of drone images, providing a wealth of information about asset health and potential issues. However, making the collected imagery data useful for automated defect detection requires significant manual labeling effort. We propose a novel solution that combines synthetic asset defect images with manually labeled drone images. This solution has several benefits: improves performance of defect detection, reduces the number of hours spent on manual labeling, and enables the capability to generate realistic images of rare defects where not enough real-world data is available. We employ a workflow that combines 3D modeling tools such as Maya and Unreal Engine to create photorealistic 3D models and 2D renderings of defective assets and their surroundings. These synthetic images are then integrated into our training pipeline augmenting the real data. This study implements an end-to-end Artificial Intelligence solution to detect assets and asset defects from the combined imagery repository. The unique contribution of this research lies in the application of advanced computer vision models and the generation of photorealistic 3D renderings of defective assets, aiming to transform the asset inspection process. Our asset detection model has achieved an accuracy of 92 percent, we achieved a performance lift of 67 percent when introducing approximately 2,000 synthetic images of 2k resolution. In our tests, the defect detection model achieved an accuracy of 73 percent across two batches of images. Our analysis demonstrated that synthetic data can be successfully used in place of real-world manually labeled data to train defect detection model.

cs.CV↗

arXiv2024

Utilizing Spatiotemporal Data Analytics to Pinpoint Outage Location

Understanding the exact fault location in the post-event analysis is the key to improving the accuracy of outage management. Unfortunately, the fault location is not generally well documented during the restoration process, creating a big challenge for post-event analysis. By utilizing various data source systems, including outage management system (OMS) data, asset geospatial information system (GIS) data, and vehicle location data, this paper creates a novel method to pinpoint the outage location accurately to create additional insights for distribution operations and performance teams during the post-event analysis.

cs.DB↗

arXiv2024

Efficient calibration of the shifted square-root diffusion model to credit default swap spreads using asymptotic approximations

We derive a closed-form approximation for the credit default swap (CDS) spread in the two-dimensional shifted square-root diffusion (SSRD) model using asymptotic coefficient expansion technique to approximate solutions of nonlinear partial differential equations. Specifically, we identify the Cauchy problems associated with two terms in the CDS spread formula that lack analytical solutions and derive asymptotic approximations for these terms. Our approximation does not require the assumption of uncorrelated interest rate and default intensity processes as typically required for calibration in the SSRD model. Through several calibration studies using market data on CDS spread, we demonstrate the accuracy and efficiency of our proposed formula.

q-fin.MF↗

arXiv2024

HOLMES: Hyper-Relational Knowledge Graphs for Multi-hop Question Answering using LLMs

Given unstructured text, Large Language Models (LLMs) are adept at answering simple (single-hop) questions. However, as the complexity of the questions increase, the performance of LLMs degrade. We believe this is due to the overhead associated with understanding the complex question followed by filtering and aggregating unstructured information in the raw text. Recent methods try to reduce this burden by integrating structured knowledge triples into the raw text, aiming to provide a structured overview that simplifies information processing. However, this simplistic approach is query-agnostic and the extracted facts are ambiguous as they lack context. To address these drawbacks and to enable LLMs to answer complex (multi-hop) questions with ease, we propose to use a knowledge graph (KG) that is context-aware and is distilled to contain query-relevant information. The use of our compressed distilled KG as input to the LLM results in our method utilizing up to $67\%$ fewer tokens to represent the query relevant information present in the supporting documents, compared to the state-of-the-art (SoTA) method. Our experiments show consistent improvements over the SoTA across several metrics (EM, F1, BERTScore, and Human Eval) on two popular benchmark datasets (HotpotQA and MuSiQue).

cs.CL↗

arXiv2023

KITLM: Domain-Specific Knowledge InTegration into Language Models for Question Answering

Large language models (LLMs) have demonstrated remarkable performance in a wide range of natural language tasks. However, as these models continue to grow in size, they face significant challenges in terms of computational costs. Additionally, LLMs often lack efficient domain-specific understanding, which is particularly crucial in specialized fields such as aviation and healthcare. To boost the domain-specific understanding, we propose, KITLM, a novel knowledge base integration approach into language model through relevant information infusion. By integrating pertinent knowledge, not only the performance of the language model is greatly enhanced, but the model size requirement is also significantly reduced while achieving comparable performance. Our proposed knowledge-infused model surpasses the performance of both GPT-3.5-turbo and the state-of-the-art knowledge infusion method, SKILL, achieving over 1.5 times improvement in exact match scores on the MetaQA. KITLM showed a similar performance boost in the aviation domain with AeroQA. The drastic performance improvement of KITLM over the existing methods can be attributed to the infusion of relevant knowledge while mitigating noise. In addition, we release two curated datasets to accelerate knowledge infusion research in specialized fields: a) AeroQA, a new benchmark dataset designed for multi-hop question-answering within the aviation domain, and b) Aviation Corpus, a dataset constructed from unstructured text extracted from the National Transportation Safety Board reports. Our research contributes to advancing the field of domain-specific language understanding and showcases the potential of knowledge infusion techniques in improving the performance of language models on question-answering.

cs.CL↗

arXiv2023

There is No Big Brother or Small Brother: Knowledge Infusion in Language Models for Link Prediction and Question Answering

The integration of knowledge graphs with deep learning is thriving in improving the performance of various natural language processing (NLP) tasks. In this paper, we focus on knowledge-infused link prediction and question answering using language models, T5, and BLOOM across three domains: Aviation, Movie, and Web. In this context, we infuse knowledge in large and small language models and study their performance, and find the performance to be similar. For the link prediction task on the Aviation Knowledge Graph, we obtain a 0.2 hits@1 score using T5-small, T5-base, T5-large, and BLOOM. Using template-based scripts, we create a set of 1 million synthetic factoid QA pairs in the aviation domain from National Transportation Safety Board (NTSB) reports. On our curated QA pairs, the three models of T5 achieve a 0.7 hits@1 score. We validate out findings with the paired student t-test and Cohen's kappa scores. For link prediction on Aviation Knowledge Graph using T5-small and T5-large, we obtain a Cohen's kappa score of 0.76, showing substantial agreement between the models. Thus, we infer that small language models perform similar to large language models with the infusion of knowledge.

cs.CL↗

arXiv2022

Knowledge Graph - Deep Learning: A Case Study in Question Answering in Aviation Safety Domain

In the commercial aviation domain, there are a large number of documents, like, accident reports (NTSB, ASRS) and regulatory directives (ADs). There is a need for a system to access these diverse repositories efficiently in order to service needs in the aviation industry, like maintenance, compliance, and safety. In this paper, we propose a Knowledge Graph (KG) guided Deep Learning (DL) based Question Answering (QA) system for aviation safety. We construct a Knowledge Graph from Aircraft Accident reports and contribute this resource to the community of researchers. The efficacy of this resource is tested and proved by the aforesaid QA system. Natural Language Queries constructed from the documents mentioned above are converted into SPARQL (the interface language of the RDF graph database) queries and answered. On the DL side, we have two different QA models: (i) BERT QA which is a pipeline of Passage Retrieval (Sentence-BERT based) and Question Answering (BERT based), and (ii) the recently released GPT-3. We evaluate our system on a set of queries created from the accident reports. Our combined QA system achieves 9.3% increase in accuracy over GPT-3 and 40.3% increase over BERT QA. Thus, we infer that KG-DL performs better than either singly.

cs.CL↗

arXiv2020

Hedging longevity risk in defined contribution pension schemes

Pension schemes all over the world are under increasing pressure to efficiently hedge the longevity risk posed by ageing populations. In this work, we study an optimal investment problem for a defined contribution pension scheme which decides to hedge the longevity risk using a mortality-linked security, typically a longevity bond. The pension scheme invests in the risky assets available in the market, including the longevity bond, by using the contributions from a representative scheme member to ensure a minimum guarantee such that the member is able to purchase a lifetime annuity upon retirement. We transform this constrained optimal investment problem into an unconstrained problem by replicating a self-financing portfolio of future contributions from the member and the minimum guarantee provided by the scheme. We solve the resulting optimisation problem using the dynamic programming principle and through a series of numerical studies reveal that the longevity risk has an important impact on the performance of investment strategies. Our results provide mathematical evidence supporting the use of mortality-linked securities for efficient hedging of the longevity risk.

q-fin.RM↗

arXiv2020

Sharing of longevity basis risk in pension schemes with income-drawdown guarantees

This work studies a stochastic optimal control problem for a pension scheme which provides an income-drawdown policy to its members after their retirement. To manage the scheme efficiently, the manager and members agree to share the investment risk based on a pre-decided risk-sharing rule. The objective is to maximise both sides' utilities by controlling the manager's investment in risky assets and members' benefit withdrawals. We use stochastic affine class models to describe the force of mortality of the members' population and consider a longevity bond whose coupon payment is linked to a survival index. In our framework, we also investigate the longevity basis risk, which arises when the members' and the longevity bond's reference populations show different mortality behaviours. By applying the dynamic programming principle to solve the corresponding HJB equations, we derive optimal solutions for the single- and sub-population cases. Our numerical results show that by sharing the risk, both manager and members increase their utility. Moreover, even in the presence of longevity basis risk, we demonstrate that the longevity bond acts as an effective hedging instrument.

q-fin.RM↗

arXiv2019

The implied Sharpe ratio

In an incomplete market, including liquidly-traded European options in an investment portfolio could potentially improve the expected terminal utility for a risk-averse investor. However, unlike the Sharpe ratio, which provides a concise measure of the relative investment attractiveness of different underlying risky assets, there is no such measure available to help investors choose among the different European options. We introduce a new concept -- the implied Sharpe ratio -- which allows investors to make such a comparison in an incomplete financial market. Specifically, when comparing various European options, it is the option with the highest implied Sharpe ratio that, if included in an investor's portfolio, will improve his expected utility the most. Through the method of Taylor series expansion of the state-dependent coefficients in a nonlinear partial differential equation, we also establish the behaviour of the implied Sharpe ratio with respect to an investor's risk-aversion parameter. In a series of numerical studies, we compare the investment attractiveness of different European options by studying their implied Sharpe ratio.

q-fin.MF↗